ECCV 2024 Papers

mini compact topic detail

FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis

Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection

WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation

Improving Text-guided Object Inpainting with Semantic Pre-inpainting

PosterLlama: Bridging Design Ability of Langauge Model to Content-Aware Layout Generation

RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation

Binomial Self-compensation for Motion Error in Dynamic 3D Scanning

Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models

Region-Aware Sequence-to-Sequence Learning for Hyperspectral Denoising

On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy

ScanTalk: 3D Talking Heads from Unregistered Scans

Vamos: Versatile Action Models for Video Understanding

Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Models

SLIM: Spuriousness Mitigation with Minimal Human Annotations

OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction

DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation

Energy-induced Explicit quantification for Multi-modality MRI fusion

Beta-Tuned Timestep Diffusion Model

R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection

Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition

Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors

ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction

Agent3D-Zero: An Agent for Zero-shot 3D Understanding

EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification

Learning Chain of Counterfactual Thought for Bias-Robust Vision-Language Reasoning

Tri^{2}-plane: Thinking Head Avatar via Feature Pyramid

A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation

Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models

Open-set Domain Adaptation via Joint Error based Multi-class Positive and Unlabeled Learning

Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection

Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs

Kernel Diffusion: An Alternate Approach to Blind Deconvolution

S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis

Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation

SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution

Towards Unified Representation of Invariant-Specific Features in Missing Modality Face Anti-Spoofing

TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generation

Agent Attention: On the Integration of Softmax and Linear Attention

SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Clouds

SOS: Segment Object System for Open-World Instance Segmentation With Object Priors

Learning Non-Linear Invariants for Unsupervised Out-of-Distribution Detection

O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation

BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling

I2-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM

Drag Anything: Motion Control for Anything using Entity Representation

Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation

Foster Adaptivity and Balance in Learning with Noisy Labels

UniM2AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving

VF-NeRF: Viewshed Fields for Rigid NeRF Registration

Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization

Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching

Masked Angle-Aware Autoencoder for Remote Sensing Images

Using My Artistic Style? You Must Obtain My Authorization

VP-SAM: Taming Segment Anything Model for Video Polyp Segmentation via Disentanglement and Spatio-temporal Side Network

Real-time Holistic Robot Pose Estimation with Unknown States

Classification Matters: Improving Video Action Detection with Class-Specific Attention

Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors

VEON: Vocabulary-Enhanced Occupancy Prediction

PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving

Bridging the Gap Between Human Motion and Action Semantics via Kinematics Phrases

Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction

ComFusion: Enhancing Personalized Generation by Instance-Scene Compositing and Fusion

EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion

Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training

Emerging Property of Masked Token for Effective Pre-training

Generalizable Symbolic Optimizer Learning

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

E3V-K5: An Authentic Benchmark for Redefining Video-Based Energy Expenditure Estimation

HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects

Language-Driven 6-DoF Grasp Detection Using Negative Prompt Guidance

RegionDrag: Fast Region-Based Image Editing with Diffusion Models

MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation

Language-Assisted Skeleton Action Understanding for Skeleton-Based Temporal Action Segmentation

SENC: Handling Self-collision in Neural Cloth Simulation

GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding

Adaptive Multi-task Learning for Few-shot Object Detection

Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement

Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model

DetailSemNet: Elevating Signature Verification through Detail-Semantic Integration

PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training

StyleCity: Large-Scale 3D Urban Scenes Stylization

Clean & Compact: Efficient Data-Free Backdoor Defense with Model Compactness

Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery

Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors

FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models

WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models

Few-shot Defect Image Generation based on Consistency Modeling

OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models

PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation

MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders

LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors

Fundamental Matrix Estimation Using Relative Depths

Investigating Style Similarity in Diffusion Models

Topology-Preserving Downsampling of Binary Images

Multi-Person Pose Forecasting with Individual Interaction Perceptron and Prior Learning

GlobalPointer: Large-Scale Plane Adjustment with Bi-Convex Relaxation

SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision

Self-Cooperation Knowledge Distillation for Novel Class Discovery

H-V2X: A Large Scale Highway Dataset for BEV Perception

UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction

Insect Identification in the Wild: The AMI Dataset

Hierarchical Unsupervised Relation Distillation for Source Free Domain Adaptation

Unsupervised Exposure Correction

Mitigating Background Shift in Class-Incremental Semantic Segmentation

SAIR: Learning Semantic-aware Implicit Representation

Unsupervised Multi-modal Medical Image Registration via Invertible Translation

Improving Video Segmentation via Dynamic Anchor Queries

Faceptor: A Generalist Model for Face Perception

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation

Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression

Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken

Open-Vocabulary Camouflaged Object Segmentation

UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues

PFGS: High Fidelity Point Cloud Rendering via Feature Splatting

Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting

High-Resolution and Few-shot View Synthesis from Asymmetric Dual-lens Inputs

Dependency-aware Differentiable Neural Architecture Search

PQ-SAM: Post-training Quantization for Segment Anything Model

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model

Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-v2)

ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model

Pathformer3D: A 3D Scanpath Transformer for 360° Images

Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation

Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection

EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis

Post-training Quantization with Progressive Calibration and Activation Relaxing for Text-to-Image Diffusion Models

Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution

Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context

Optimal Transport of Diverse Unsupervised Tasks for Robust Learning from Noisy Few-Shot Data

Gaussian in the wild: 3D Gaussian Splatting for Unconstrained Image Collections

Video Editing via Factorized Diffusion Distillation

Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and Visual Analysis Strategy

SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer

MANIKIN: Biomechanically Accurate Neural Inverse Kinematics for Human Motion Estimation

Enriching Information and Preserving Semantic Congruence in Expanding Curvilinear Object Segmentation Datasets

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentation

Masked Motion Prediction with Semantic Contrast for Point Cloud Sequence Learning

Exploring the Feature Extraction and Relation Modeling For Light-Weight Transformer Tracking

Efficient and Versatile Robust Fine-Tuning of Zero-shot Models

Fast Registration of Photorealistic Avatars for VR Facial Animation

DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation

Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion

Crowd-SAM:SAM as a smart annotator for object detection in crowded scenes

EAFormer: Scene Text Segmentation with Edge-Aware Transformers

Improving Zero-Shot Generalization for CLIP with Variational Adapter

On the Evaluation Consistency of Attribution-based Explanations

LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models

Superpixel-informed Implicit Neural Representation for Multi-Dimensional Data

See and Think: Embodied Agent in Virtual Environment

CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant

3D Single-object Tracking in Point Clouds with High Temporal Variation

Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions

GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection

Veil Privacy on Visual Data: Concealing Privacy for Humans, Unveiling for DNNs

Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation

WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting

DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting

MoAI: Mixture of All Intelligence for Large Language and Vision Models

Click-Gaussian: Interactive Segmentation to Any 3D Gaussians

HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting

Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models

Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation

Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding

GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Corrections

EcoMatcher: Efficient Clustering Oriented Matcher for Detector-free Image Matching

Aligning Neuronal Coding of Dynamic Visual Scenes with Foundation Vision Models

MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving

FreestyleRet: Retrieving Images from Style-Diversified Queries

CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts

PolyRoom: Room-aware Transformer for Floorplan Reconstruction

Straightforward Layer-wise Pruning for More Efficient Visual Adaptation

Test-Time Stain Adaptation with Diffusion Models for Histopathology Image Classification

ChEX: Interactive Localization and Region Description in Chest X-rays

DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion

LongVLM: Efficient Long Video Understanding via Large Language Models

Zero-shot Object Counting with Good Exemplars

PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects

View-Consistent 3D Editing with Gaussian Splatting

Weighted Ensemble Models Are Strong Continual Learners

Retargeting Visual Data with Deformation Fields

LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model

PoseSOR: Human Pose Can Guide Our Attention

STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians

Similarity of Neural Architectures using Adversarial Attack Transferability

ParCo: Part-Coordinating Text-to-Motion Synthesis

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model

Rotary Position Embedding for Vision Transformer

Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge

DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment

Certifiably Robust Image Watermark

Imaging with Confidence: Uncertainty Quantification for High-dimensional Undersampled MR Images

Sur^2f: A Hybrid Representation for High-Quality and Efficient Surface Reconstruction from Multi-view Images

Stable Preference: Redefining training paradigm of human preference model for Text-to-Image Synthesis

Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation

Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking

Idling Neurons, Appropriately Lenient Workload During Fine-tuning Leads to Better Generalization

Stitched ViTs are Flexible Vision Backbones

Sketch2Vox: Learning 3D Reconstruction from a Single Monocular Sketch Image

Labeled Data Selection for Category Discovery

MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning

When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset

Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation

Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos

Tiny Models are the Computational Saver for Large Models

An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshes

OneRestore: A Universal Restoration Framework for Composite Degradation

Fisher Calibration for Backdoor-Robust Heterogeneous Federated Learning

SDPT: Synchronous Dual Prompt Tuning for Fusion-based Visual-Language Pre-trained Models

Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models

OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation

TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data

Self-Training Room Layout via Geometry-aware Ray-casting

IAM-VFI : Interpolate Any Motion for Video Frame Interpolation with motion complexity map

A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment

Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models

PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation

Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks

Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor

Multi-Modal Video Dialog State Tracking in the Wild

LiDAR-Event Stereo Fusion with Hallucinations

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

HiFi-123: Towards High-fidelity One Image to 3D Content Generation

Efficient Frequency-Domain Image Deraining with Contrastive Regularization

A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars

R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Bayesian Self-Training for Semi-Supervised 3D Segmentation

DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception

Reinforcement Learning Friendly Vision-Language Model for Minecraft

Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer

A Comparative Study of Image Restoration Networks for General Backbone Network Design

DNI: Dilutional Noise Initialization for Diffusion Video Editing

Learning Exhaustive Correlation for Spectral Super-Resolution: Where Spatial-Spectral Attention Meets Linear Dependence

GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation

All You Need is Your Voice: Emotional Face Representation with Audio Perspective for Emotional Talking Face Generation

Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization

DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition

Diverse Text-to-3D Synthesis with Augmented Text Embedding

Camera Calibration using a Collimator System

Grounding Image Matching in 3D with MASt3R

You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

Timestep-Aware Correction for Quantized Diffusion Models

Easing 3D Pattern Reasoning with Side-view Features for Semantic Scene Completion

Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching

Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation

GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth

Online Zero-Shot Classification with CLIP

Prediction Exposes Your Face: Black-box Model Inversion via Prediction Alignment

RecurrentBEV: A Long-term Temporal Fusion Framework for Multi-view 3D Detection

HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning

SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning

Multi-scale Cross Distillation for Object Detection in Aerial Images

SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM

Multi-Label Cluster Discrimination for Visual Representation Learning

OMR: Occlusion-Aware Memory-Based Refinement for Video Lane Detection

Appearance-based Refinement for Object-Centric Motion Segmentation

ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization

Human-in-the-Loop Visual Re-ID for Population Size Estimation

PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation

CrossScore: A Multi-View Approach to Image Evaluation and Scoring

SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection

Length-Aware Motion Synthesis via Latent Diffusion

Local Occupancy-Enhanced Object Grasping with Multiple Triplanar Projection

M3DBench: Towards Omni 3D Assistant with Interleaved Multi-modal Instructions

E.T. the Exceptional Trajectory: Text-to-camera-trajectory generation with character awareness

Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance

Attention Decomposition for Cross-Domain Semantic Segmentation

Retrieval Robust to Object Motion Blur

ReCON: Training-Free Acceleration for Text-to-Image Synthesis with Retrieval of Concept Prompt Trajectories

MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering

Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation

Visual Grounding for Object-Level Generalization in Reinforcement Learning

Revisit Anything: Visual Place Recognition via Image Segment Retrieval

DoubleTake: Geometry Guided Depth Estimation

Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts

Towards Robust Full Low-bit Quantization of Super Resolution Networks

WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing

SINDER: Repairing the Singular Defects of DINOv2

Unsqueeze [CLS] Bottleneck to Learn Rich Representations

Reliable Spatial-Temporal Voxels For Multi-Modal Test-Time Adaptation

Gaze Target Detection Based on Head-Local-Global Coordination

Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection

PreLAR: World Model Pre-training with Learnable Action Representation

MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment

MRSP: Learn Multi-Representations of Single Primitive for Compositional Zero-Shot Learning

ProMerge: Prompt and Merge for Unsupervised Instance Segmentation

ExMatch: Self-guided Exploitation for Semi-Supervised Learning with Scarce Labeled Samples

AnimateMe: 4D Facial Expressions via Diffusion Models

Learning Representations from Foundation Models for Domain Generalized Stereo Matching

Removing Rows and Columns of Tokens in Vision Transformer enables Faster Dense Prediction without Retraining

Probabilistic Image-Driven Traffic Modeling via Remote Sensing

On Spectral Properties of Gradient-based Explanation Methods

Customized Generation Reimagined: Fidelity and Editability Harmonized

ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting

DataDream: Few-shot Guided Dataset Generation

MEVG : Multi-event Video Generation with Text-to-Video Models

The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations

PISR: Polarimetric Neural Implicit Surface Reconstruction for Textureless and Specular Objects

4D Contrastive Superflows are Dense 3D Representation Learners

Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-based Approach

Frontier-enhanced Topological Memory with Improved Exploration Awareness for Embodied Visual Navigation

Online Temporal Action Localization with Memory-Augmented Transformer

Compress3D: a Compressed Latent Space for 3D Generation from a Single Image

GenRC: Generative 3D Room Completion from Sparse Image Collections

Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation

Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion

COMO: Compact Mapping and Odometry

COMPOSE: Comprehensive Portrait Shadow Editing

Open Vocabulary Multi-Label Video Classification

SUMix: Mixup with Semantic and Uncertain Information

Continuous SO(3) Equivariant Convolution for 3D Point Cloud Analysis

Training A Small Emotional Vision Language Model for Visual Art Comprehension

DiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior

SignGen: End-to-End Sign Language Video Generation with Latent Diffusion

UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models

Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation

A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks

Event-Aided Time-To-Collision Estimation for Autonomous Driving

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs

VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space

Prompting Future Driven Diffusion Model for Hand Motion Prediction

HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts

Attention Beats Linear for Fast Implicit Neural Representation Generation

Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation

Unsupervised Dense Prediction using Differentiable Normalized Cuts

An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation

DomainFusion: Generalizing To Unseen Domains with Latent Diffusion Models

LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimation

Image-adaptive 3D Lookup Tables for Real-time Image Enhancement with Bilateral Grids

N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields

3DFG-PIFu: 3D Feature Grids for Human Digitization from Sparse Views

Label-anticipated Event Disentanglement for Audio-Visual Video Parsing

Reinforcement Learning Meets Visual Odometry

UniFS: Universal Few-shot Instance Perception with Point Representations

Long-term Temporal Context Gathering for Neural Video Compression

On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now

POA: Pre-training Once for Models of All Sizes

Physically Plausible Color Correction for Neural Radiance Fields

SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks

Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation

Improving Vision and Language Concepts Understanding with Multimodal Counterfactual Samples

EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks

Long-range Turbulence Mitigation: A Large-scale Dataset and A Coarse-to-fine Framework

Fully Sparse 3D Occupancy Prediction

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer

Improving Medical Multi-modal Contrastive Learning with Expert Annotations

OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks

TCC-Det: Temporarily consistent cues for weakly-supervised 3D detection

LPViT: Low-Power Semi-structured Pruning for Vision Transformers

DQ-DETR: DETR with Dynamic Query for Tiny Object Detection

Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm

Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution

MLPHand: Real Time Multi-View 3D Hand Reconstruction via MLP Modeling

Pre-trained Visual Dynamics Representations for Efficient Policy Learning

Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection

Time-Efficient and Identity-Consistent Virtual Try-On Using A Variant of Altered Diffusion Models

TrafficNight : An Aerial Multimodal Benchmark For Nighttime Vehicle Surveillance

PiTe: Pixel-Temporal Alignment for Large Video-Language Model

Single-Mask Inpainting for Voxel-based Neural Radiance Fields

FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimation

Fast Sprite Decomposition from Animated Graphics

Responsible Visual Editing

ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments

Let the Avatar Talk using Texts without Paired Training Data

Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph

Real Appearance Modeling for More General Deepfake Detection

LASS3D: Language-Assisted Semi-Supervised 3D Semantic Segmentation with Progressive Unreliable Data Exploitation

ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference

TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering

COM Kitchens: An Unedited Overhead-view Procedural Videos Dataset a Vision-Language Benchmark

OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding

SEED: A Simple and Effective 3D DETR in Point Clouds

Edge-Guided Fusion and Motion Augmentation for Event-Image Stereo

GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths

PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations

SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization

Exploring Guided Sampling of Conditional GANs

Rethinking Features-Fused-Pyramid-Neck for Object Detection

Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection

Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering

Domain-adaptive Video Deblurring via Test-time Blurring

AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors

Paying More Attention to Images: A Training-Free Method for Alleviating Hallucination in LVLMs

CoReS: Orchestrating the Dance of Reasoning and Segmentation

Computing the Lipschitz constant needed for fast scene recovery from CASSI measurements

Domesticating SAM for Breast Ultrasound Image Segmentation via Spatial-frequency Fusion and Uncertainty Correction

ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion

The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation

Learning Anomalies with Normality Prior for Unsupervised Video Anomaly Detection

OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection

M^2Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation

FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous Driving

ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer

ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

Neural Volumetric World Models for Autonomous Driving

Vision-Language Action Knowledge Learning for Semantic-Aware Action Quality Assessment

Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks

VividDreamer: Invariant Score Distillation for Hyper-Realistic Text-to-3D Generation

PoseAugment: Generative Human Pose Data Augmentation with Physical Plausibility for IMU-based Motion Capture

CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion

Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control

XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution

VideoMamba: State Space Model for Efficient Video Understanding

QueryCDR: Query-based Controllable Distortion Rectification Network for Fisheye Images

Visual Text Generation in the Wild

ActionVOS: Actions as Prompts for Video Object Segmentation

Agglomerative Token Clustering

A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

iMatching: Imperative Correspondence Learning

RePOSE: 3D Human Pose Estimation via Spatio-Temporal Depth Relational Consistency

Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection

Asynchronous Large Language Model Enhanced Planner for Autonomous Driving

Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses

Texture-GS: Disentangle the Geometry and Texture for 3D Gaussian Splatting Editing

CIC-BART-SSA: : Controllable Image Captioning with Structured Semantic Augmentation

Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds

Domain Shifting: A Generalized Solution for Heterogeneous Cross-Modality Person Re-Identification

Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging

Diffusion Bridges for 3D Point Cloud Denoising

Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing

A Graph-Based Approach for Category-Agnostic Pose Estimation

Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes

Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning

PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology

Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification

Towards a Density Preserving Objective Function for Learning on Point Sets

Unleashing the Power of Prompt-driven Nucleus Instance Segmentation

Attention Prompting on Image for Large Vision-Language Models

Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation

Emergent Visual-Semantic Hierarchies in Image-Text Representations

Plan, Posture and Go: Towards Open-vocabulary Text-to-Motion Generation

3D Hand Sequence Recovery from Real Blurry Images and Event Stream

Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization

VideoStudio: Generating Consistent-Content and Multi-Scene Videos

Uncertainty-Driven Spectral Compressive Imaging with Spatial-Frequency Transformer

Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation

Object-Oriented Anchoring and Modal Alignment in Multimodal Learning

ControlCap: Controllable Region-level Captioning

REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices

Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation

SemanticHuman-HD: High Resolution Semantic disentangled 3D Human Generation

Pose Guided Fine-Grained Sign Language Video Generation

A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis

Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution

DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation

Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable Repainting

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Towards Reliable Advertising Image Generation Using Human Feedback

Merlin: Empowering Multimodal LLMs with Foresight Minds

RangeLDM: Fast Realistic LiDAR Point Cloud Generation

ST-LDM: A Universal Framework for Text-Grounded Object Generation in Real Images

Modelling Competitive Behaviors in Autonomous Driving Under Generative World Model

Visual Alignment Pre-training for Sign Language Translation

OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving

Bidirectional Progressive Transformer for Interaction Intention Anticipation

GVGEN: Text-to-3D Generation with Volumetric Representation

HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis

VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation

Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model

Exploring Vulnerabilities in Spiking Neural Networks: Direct Adversarial Attacks on Raw Event Data

EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models

Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models

DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning

Panel-Specific Degradation Representation for Raw Under-Display Camera Image Restoration

Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors

HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation

Realistic Human Motion Generation with Cross-Diffusion Models

Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching

Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression

FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models

Learning Natural Consistency Representation for Face Forgery Video Detection

Cascade Prompt Learning for Visual-Language Model Adaptation

Dynamic Neural Radiance Field From Defocused Monocular Video

Spatially-Variant Degradation Model for Dataset-free Super-resolution

Dual-Rain: Video Rain Removal using Assertive and Gentle Teachers

Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation

MeshSegmenter: Zero-Shot Mesh Segmentation via Texture Synthesis

Spatial-Temporal Multi-level Association for Video Object Segmentation

A Cephalometric Landmark Regression Method based on Dual-encoder for High-resolution X-ray Image

EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere

Stream Query Denoising for Vectorized HD-Map Construction

Hiding Imperceptible Noise in Curvature-Aware Patches for 3D Point Cloud Attack

Keypoint Promptable Re-Identification

RealViformer: Investigating Attention for Real-World Video Super-Resolution

Enhancing Diffusion Models with Text-Encoder Reinforcement Learning

MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks

On the Approximation Risk of Few-Shot Class-Incremental Learning

OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model

Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolution

CaesarNeRF: Calibrated Semantic Representation for Few-Shot Generalizable Neural Rendering

U-COPE: Taking a Further Step to Universal 9D Category-level Object Pose Estimation

RoadPainter: Points Are Ideal Navigators for Topology transformER

Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition

ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation

SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning

MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model

milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing

GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation

MERLiN: Single-Shot Material Estimation and Relighting for Photometric Stereo

Learning 3D-aware GANs from Unposed Images with Template Feature Field

Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation

Instant Uncertainty Calibration of NeRFs Using a Meta-Calibrator

RS-NeRF: Neural Radiance Fields from Rolling Shutter Images

PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation

3DEgo: 3D Editing on the Go!

FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior

Leveraging Text Localization for Scene Text Removal via Text-aware Masked Image Modeling

LivePhoto: Real Image Animation with Text-guided Motion Control

Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention

Uncertainty-aware sign language video retrieval with probability distribution modeling

WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation

Exploring Reliable Matching with Phase Enhancement for Night-time Semantic Segmentation

JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation

Unveiling Privacy Risks in Stochastic Neural Networks Training: Effective Image Reconstruction from Gradients

Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation

InterFusion: Text-Driven Generation of 3D Human-Object Interaction

LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models

BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering

Domain Generalization of 3D Object Detection by Density-Resampling

ELSE: Efficient Deep Neural Network Inference through Line-based Sparsity Exploration

GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing

BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow

Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models

WRIM-Net: Wide-Ranging Information Mining Network for Visible-Infrared Person Re-Identification

Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data

SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions

Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking

Handling The Non-Smooth Challenge in Tensor SVD: A Multi-Objective Tensor Recovery Framework

DreamReward: Aligning Human Preference in Text-to-3D Generation

Deblurring 3D Gaussian Splatting

Adversarial Robustification via Text-to-Image Diffusion Models

ConGeo: Robust Cross-view Geo-localization across Ground View Variations

Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth

Learning Camouflaged Object Detection from Noisy Pseudo Label

Motion Keyframe Interpolation for Any Human Skeleton using Point Cloud-based Human Motion Data Homogenisation

Prompt-Based Test-Time Real Image Dehazing: A Novel Pipeline

CSOT: Cross-Scan Object Transfer for Semi-Supervised LiDAR Object Detection

Animate Your Motion: Turning Still Images into Dynamic Videos

Language-Image Pre-training with Long Captions

DoughNet: A Visual Predictive Model for Topological Manipulation of Deformable Objects

Visible and Clear: Finding Tiny Objects in Difference Map

AID-AppEAL: Automatic Image Dataset and Algorithm for Content Appeal Enhancement and Assessment Labeling

COSMU: Complete 3D human shape from monocular unconstrained images

Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images

GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image

KDProR: A Knowledge-Decoupling Probabilistic Framework for Video-Text Retrieval

Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection

When Fast Fourier Transform Meets Transformer for Image Restoration

Revisiting Domain-Adaptive Object Detection in Adverse Weather by the Generation and Composition of High-Quality Pseudo-Labels

CipherDM: Secure Three-Party Inference for Diffusion Model Sampling

Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher

DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control

EDformer: Transformer-Based Event Denoising Across Varied Noise Levels

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

Interactive 3D Object Detection with Prompts

HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution

CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection

Temporally Consistent Stereo Matching

Good Teachers Explain: Explanation-Enhanced Knowledge Distillation

An Information Theoretical View for Out-Of-Distribution Detection

HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance

HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenes

Any2Point: Empowering Any-modality Transformers for Efficient 3D Understanding

HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos

PALM: Predicting Actions through Language Models

PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers

Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks

Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem

Online Vectorized HD Map Construction using Geometry

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

BRAVE: Broadening the visual encoding of vision-language models

ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers

DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion

RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting

Revisit Human-Scene Interaction via Space Occupancy

MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution

AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale

SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion

Zero-Shot Image Feature Consensus with Deep Functional Maps

Event-based Head Pose Estimation: Benchmark and Method

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning

Plug and Play: A Representation Enhanced Domain Adapter for Collaborative Perception

Textual-Visual Logic Challenge: Understanding and Reasoning in Text-to-Image Generation

Deep Feature Surgery: Towards Accurate and Efficient Multi-Exit Networks

Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning

Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation

Pixel-GS Density Control with Pixel-aware Gradient for 3D Gaussian Splatting

Bidirectional Uncertainty-Based Active Learning for Open-Set Annotation

Boosting 3D Single Object Tracking with 2D Matching Distillation and 3D Pre-training

TAPTR: Tracking Any Point with Transformers as Detection

A New Dataset and Framework for Real-World Blurred Images Super-Resolution

Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Model

Learned Image Enhancement via Color Naming

latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

Learned HDR Image Compression for Perceptually Optimal Storage and Display

Towards Scene Graph Anticipation

Diffusion for Natural Image Matting

DreamMotion: Space-Time Self-Similar Score Distillation for Zero-Shot Video Editing

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

General and Task-Oriented Video Segmentation

denoiSplit: a method for joint microscopy image splitting and unsupervised denoising

SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras

Class-Agnostic Object Counting with Text-to-Image Diffusion Model

ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention

CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation

MeshFeat: Multi-Resolution Features for Neural Fields on Meshes

Personalized Video Relighting With an At-Home Light Stage

Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion

Multimodal Label Relevance Ranking via Reinforcement Learning

CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning

Real-time 3D-aware Portrait Editing from a Single Image

HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning

Trackastra: Transformer-based cell tracking for live-cell microscopy

Audio-driven Talking Face Generation with Stabilized Synchronization Loss

A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging

Nonverbal Interaction Detection

Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation

Global-to-Pixel Regression for Human Mesh Recovery

Asymmetric Mask Scheme for Self-Supervised Real Image Denoising

Can Textual Semantics Mitigate Sounding Object Segmentation Preference?

LEROjD: Lidar Extended Radar-Only Object Detection

Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes

Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration

Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering

Learning to Complement and to Defer to Multiple Users

MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection

GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity

Scalable Group Choreography via Variational Phase Manifold Learning

Occupancy as Set of Points

VISA: Reasoning Video Object Segmentation via Large Language Model

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models

Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation

SlotLifter: Slot-guided Feature Lifting for Learning Object-Centric Radiance Fields

Efficient Pre-training for Localized Instruction Generation of Procedural Videos

OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects

A Fair Ranking and New Model for Panoptic Scene Graph Generation

GroundUp: Rapid Sketch-Based 3D City Massing

DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences

Pathology-knowledge Enhanced Multi-instance Prompt Learning for Few-shot Whole Slide Image Classification

Enhanced Motion Forecasting with Visual Relation Reasoning

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

Implicit Steganography Beyond the Constraints of Modality

VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving

Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning

Dynamic Data Selection for Efficient SSL via Coarse-to-Fine Refinement

Training-free Composite Scene Generation for Layout-to-Image Synthesis

GTMS: A Gradient-driven Tree-guided Mask-free Referring Image Segmentation Method

Online Continuous Generalized Category Discovery

Active Generation for Image Classification

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model

FedHARM: Harmonizing Model Architectural Diversity in Federated Learning

TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Autonomous Driving

Frequency-Spatial Entanglement Learning for Camouflaged Object Detection

RGBD GS-ICP SLAM

Test-time Model Adaptation for Image Reconstruction Using Self-supervised Adaptive Layers

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing

DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

Deep Companion Learning: Enhancing Generalization Through Historical Consistency

3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing

Integer-Valued Training and Spike-driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection

Relation DETR: Exploring Explicit Position Relation Prior for Object Detection

Cocktail Universal Adversarial Attack on Deep Neural Networks

Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation

MotionChain: Conversational Motion Controllers via Multimodal Prompts

CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model

CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation

WAVE: Warping DDIM Inversion Features for Zero-shot Text-to-Video Editing

High-Fidelity 3D Textured Shapes Generation by Sparse Encoding and Adversarial Decoding

AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing

SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis

GRA: Detecting Oriented Objects through Group-wise Rotating and Attention

Open-Vocabulary RGB-Thermal Semantic Segmentation

Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture

SemGrasp: Semantic Grasp Generation via Language Aligned Discretization

VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors

Online Video Quality Enhancement with Spatial-Temporal Look-up Tables

Efficient Active Domain Adaptation for Semantic Segmentation by Selecting Information-rich Superpixels

Upper-body Hierarchical Graph for Skeleton Based Emotion Recognition in Assistive Driving

Neural Poisson Solver: A Universal and Continuous Framework for Natural Signal Blending

Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics

Training-Free Model Merging for Multi-target Domain Adaptation

SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning

MambaIR: A Simple Baseline for Image Restoration with State-Space Model

GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning

AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting

HARIVO: Harnessing Text-to-Image Models for Video Generation

WHAC: World-grounded Humans and Cameras

Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks

3DSA:Multi-View 3D Human Pose Estimation With 3D Space Attention Mechanisms

MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References

Towards Certifiably Robust Face Recognition

EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS

Unmasking Bias in Diffusion Model Training

HoloADMM: High-Quality Holographic Complex Field Recovery

CPM: Class-conditional Prompting Machine for Audio-visual Segmentation

RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control

RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fields

Bayesian Detector Combination for Object Detection with Crowdsourced Annotations

Physics-informed Knowledge Transfer for Underwater Monocular Depth Estimation

Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation

Referring Atomic Video Action Recognition

CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning

CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Images

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos

VideoClusterNet: Self-Supervised and Adaptive Face Clustering for Videos

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving

SuperGaussian: Repurposing Video Models for 3D Super Resolution

Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations

DreamDiffusion: High-Quality EEG-to-Image Generation with Temporal Masked Signal Modeling and CLIP Alignment

OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

Gradient-based Out-of-Distribution Detection

Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution

RPBG: Towards Robust Neural Point-based Graphics in the Wild

Generating 3D House Wireframes with Semantics

QUAR-VLA: Vision-Language-Action Model for Quadruped Robots

Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection

Efficient Training of Spiking Neural Networks with Multi-Parallel Implicit Stream Architecture

Distractor-Free Novel View Synthesis via Exploiting Memorization Effect in Optimization

PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion

MoEAD: A Parameter-efficient Model for Multi-class Anomaly Detection

Decomposition Betters Tracking Everything Everywhere

MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation

EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation

Leveraging temporal contextualization for video action recognition

Flying with Photons: Rendering Novel Views of Propagating Light

Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction

SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians

RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes

Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks

FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection

Fine-grained Dynamic Network for Generic Event Boundary Detection

Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering

PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification

Efficient Vision Transformers with Partial Attention

SemTrack: A Large-scale Dataset for Semantic Tracking in the Wild

Statewide Visual Geolocalization in the Wild

Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition

STSP: Spatial-Temporal Subspace Projection for Video Class-incremental Learning

Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes

Progressive Pretext Task Learning for Human Trajectory Prediction

Learning to Make Keypoints Sub-Pixel Accurate

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection

HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression

LayoutFlow: Flow Matching for Layout Generation

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

Deep Online Probability Aggregation Clustering

Reliability in Semantic Segmentation: Can We Use Synthetic Data?

Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions

Vision-Language Dual-Pattern Matching for Out-of-Distribution Detection

De-confounded Gaze Estimation

PairingNet: A Learning-based Pair-searching and -matching Network for Image Fragments

WindPoly: Polygonal Mesh Reconstruction via Winding Numbers

Monocular Occupancy Prediction for Scalable Indoor Scenes

PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration

Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators

CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field

Motion and Structure from Event-based Normal Flow

SCAPE: A Simple and Strong Category-Agnostic Pose Estimator

Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification

FLAT: Flux-aware Imperceptible Adversarial Attacks on 3D Point Clouds

A high-quality robust diffusion framework for corrupted dataset

Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts

Data Augmentation via Latent Diffusion for Saliency Prediction

DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling

GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer

Nuvo: Neural UV Mapping for Unruly 3D Representations

Region-Adaptive Transform with Segmentation Prior for Image Compression

A Diffusion Model for Simulation Ready Coronary Anatomy with Morpho-skeletal Control

KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter

BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues

Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality

Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models

Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence

UNIKD: UNcertainty-Filtered Incremental Knowledge Distillation for Neural Implicit Representation

An Explainable Vision Question Answer Model via Diffusion Chain-of-Thought

AnyHome: Open-Vocabulary Large-Scale Indoor Scene Generation with First-Person View Exploration

Layered Rendering Diffusion Model for Controllable Zero-Shot Image Synthesis

Rethinking Directional Parameterization in Neural Implicit Surface Reconstruction

Shape-guided Configuration-aware Learning for Endoscopic-image-based Pose Estimation of Flexible Robotic Instruments

Efficient Depth-Guided Urban View Synthesis

GRAPE: Generalizable and Robust Multi-view Facial Capture

Learning Unsigned Distance Functions from Multi-view Images with Volume Rendering Priors

CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting

GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection

Flatness-aware Sequential Learning Generates Resilient Backdoors

SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model

Reprojection Errors as Prompts for Efficient Scene Coordinate Regression

LLM as Copilot for Coarse-grained Vision-and-Language Navigation

Recursive Visual Programming

Functional Transform-Based Low-Rank Tensor Factorization for Multi-Dimensional Data Recovery

PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation

TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling

DragVideo: Interactive Drag-style Video Editing

Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction

Diffusion Models as Data Mining Tools

ReMatching: Low-Resolution Representations for Scalable Shape Correspondence

Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling

High-Precision Self-Supervised Monocular Depth Estimation with Rich-Resource Prior

Efficient Snapshot Spectral Imaging: Calibration-Free Parallel Structure with Aperture Diffraction Fusion

Tackling Structural Hallucination in Image Translation with Local Diffusion

PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model

Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval

Compositional Substitutivity of Visual Reasoning for Visual Question Answering

Bi-directional Contextual Attention for 3D Dense Captioning

Self-Supervised Video Desmoking for Laparoscopic Surgery

Ray-Distance Volume Rendering for Neural Scene Reconstruction

RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception

Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition

Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation

Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions

CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring

Elegantly Written: Disentangling Writer and Character Styles for Enhancing Online Chinese Handwriting

DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation

FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

CountFormer: Multi-View Crowd Counting Transformer

Restoring Images in Adverse Weather Conditions via Histogram Transformer

Nickel and Diming Your GAN: A Dual-Method Approach to Enhancing GAN Efficiency via Knowledge Distillation

HUMOS: Human Motion Model Conditioned on Body Shape

Delving into Adversarial Robustness on Document Tampering Localization

Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention

Quantization-Friendly Winograd Transformations for Convolutional Neural Networks

Text Motion Translator: A Bi-Directional Model for Enhanced 3D Human Motion Generation from Open-Vocabulary Descriptions

Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis

DEPICT: Diffusion-Enabled Permutation Importance for Image Classification Tasks

Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation

Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity

TPA3D: Triplane Attention for Fast Text-to-3D Generation

Learning Equilibrium Transformation for Gamut Expansion and Color Restoration

Energy-Clibrated VAE with Test Time Free Lunch

RAW-Adapter: Adapting Pretrained Visual Model to Camera RAW Images

ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation

3x2: 3D Object Part Segmentation by 2D Semantic Correspondences

MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery

Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network

DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rays

BaSIC: BayesNet Structure Learning for Computational Scalable Neural Image Compression

SNeRV: Spectra-preserving Neural Representation for Video

Multiscale Graph Texture Network

Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors

Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance

MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models

UMBRAE: Unified Multimodal Brain Decoding

Large-Scale Multi-Hypotheses Cell Tracking Using Ultrametric Contours Maps

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models

Geometry Fidelity for Spherical Images

Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View

Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning

Benchmarking the Robustness of Cross-view Geo-localization Models

EgoLifter: Open-world 3D Segmentation for Egocentric Perception

Analysis-by-Synthesis Transformer for Single-View 3D Reconstruction

Heterogeneous Graph Learning for Scene Graph Prediction in 3D Point Clouds

Diffusion Model is a Good Pose Estimator from 3D RF-Vision

Object-Aware NIR-to-Visible Translation

CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization

Leveraging Enhanced Queries of Point Sets for Vectorized Map Construction

Enhancing Vectorized Map Perception with Historical Rasterized Maps

Gated Temporal Diffusion for Stochastic Long-term Dense Anticipation

ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders

Event-Based Motion Magnification

TimeLens-XL: Real-time Event-based Video Frame Interpolation with Large Motion

VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions

M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models

Editable Image Elements for Controllable Synthesis

TurboEdit: Real-time text-based disentangled real image editing

One-stage Prompt-based Continual Learning

Camera-LiDAR Cross-modality Gait Recognition

nuCraft: Crafting High Resolution 3D Semantic Occupancy for Unified 3D Scene Understanding

Delving Deep into Engagement Prediction of Short Videos

Two-Stage Video Shadow Detection via Temporal-Spatial Adaption

Quanta Video Restoration

ARoFace: Alignment Robustness to Improve Low-quality Face Recognition

MTaDCS: Moving Trace and Feature Density-based Confidence Sample Selection under Label Noise

Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment

Occluded Gait Recognition with Mixture of Experts: An Action Detection Perspective

Cut out the Middleman: Revisiting Pose-based Gait Recognition

VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding

RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios

Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective

Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation

IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers

SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding

Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning

SAH-SCI: Self-Supervised Adapter for Efficient Hyperspectral Snapshot Compressive Imaging

Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation

Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery

LingoQA: Video Question Answering for Autonomous Driving

AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization

HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning

GENIXER: Empowering Multimodal Large Language Models as a Powerful Data Generator

ViG-Bias: Visually Grounded Bias Discovery and Mitigation

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Synergy of Sight and Semantics: Visual Intention Understanding with CLIP

FlexAttention for Efficient High-Resolution Vision-Language Models

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks

Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation

Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery

InfMAE: A Foundation Model in The Infrared Modality

Unified Medical Image Pre-training in Language-Guided Common Semantic Space

Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models

Snuffy: Efficient Whole Slide Image Classifier

Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion

Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras

Enhanced Sparsification via Stimulative Training

RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception

Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense

Leveraging Imperfect Restoration for Data Availability Attack

Open-Set Recognition in the Age of Vision-Language Models

PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis

Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation

PartSTAD: 2D-to-3D Part Segmentation Task Adaptation

PartCraft: Crafting Creative Objects by Parts

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off

Self-supervised co-salient object detection via feature correspondences at multiple scales

Stepwise Multi-grained Boundary Detector for Point-supervised Temporal Action Localization

Bucketed Ranking-based Losses for Efficient Training of Object Detectors

The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation

Semi-supervised Segmentation of Histopathology Images with Noise-Aware Topological Consistency

Multistain Pretraining for Slide Representation Learning in Pathology

A Rotation-invariant Texture ViT for Fine-Grained Recognition of Esophageal Cancer Endoscopic Ultrasound Images

Bridging the Pathology Domain Gap: Efficiently Adapting CLIP for Pathology Image Analysis with Limited Labeled Data

HERGen: Elevating Radiology Report Generation with Longitudinal Data

Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization

MultiDelete for Multimodal Machine Unlearning

Robustness Preserving Fine-tuning using Neuron Importance

Understanding Multi-compositional learning in Vision and Language models via Category Theory

This Probably Looks Exactly Like That: An Invertible Prototypical Network

Confidence Self-Calibration for Multi-Label Class-Incremental Learning

Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimation

Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection

Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Composition

UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework

Efficient NeRF Optimization - Not All Samples Remain Equally Hard

Differentiable Product Quantization for Memory Efficient Camera Relocalization

Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion

Semantic Residual Prompts for Continual Learning

Representation Enhancement-Stabilization: Reducing Bias-Variance of Domain Generalization

Encapsulating Knowledge in One Prompt

SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments

Compact 3D Scene Representation via Self-Organizing Gaussian Grids

Consistent 3D Line Mapping

Dataset Distillation by Automatic Training Trajectories

Graph Neural Network Causal Explanation via Neural Causal Models

Optimization-based Uncertainty Attribution Via Learning Informative Perturbations

CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction

SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning

MobileNetV4: Universal Models for the Mobile Ecosystem

Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation

Adaptive Parametric Activation

CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection

Dataset Enhancement with Instance-Level Augmentations

Efficient Bias Mitigation Without Privileged Information

Momentum Auxiliary Network for Supervised Local Learning

From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition

Zero-Shot Detection of AI-Generated Images

Smoothness, Synthesis, and Sampling: Re-thinking Unsupervised Multi-View Stereo with DIV Loss

Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer

Improving Virtual Try-On with Garment-focused Diffusion Models

TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

Synthesizing Time-varying BRDFs via Latent Space

Resolving Scale Ambiguity in Multi-view 3D Reconstruction using Dual-Pixel Sensors

Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos

T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning

LISO: Lidar-only Self-Supervised 3D Object Detection

SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic

LaRa: Efficient Large-Baseline Radiance Fields

RaFE: Generative Radiance Fields Restoration

EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding

LLMCO4MR: LLMs-aided Neural Combinatorial Optimization for Ancient Manuscript Restoration from Fragments with Case Studies on Dunhuang

Neural graphics texture compression supporting random access

A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis

GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views

MVDD: Multi-View Depth Diffusion Models

Hypernetworks for Generalizable BRDF Representation

Non-Line-of-Sight Estimation of Fast Human Motion with Slow Scanning Imagers

Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models

Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization

KeypointDETR: An End-to-End 3D Keypoint Detector

Beat-It: Beat-Synchronized Multi-Condition 3D Dance Generation

SceneTeller: Language-to-3D Scene Generation

InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping

DiscoMatch: Fast Discrete Optimisation for Geometrically Consistent 3D Shape Matching

FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation

UMERegRobust – Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration

Light-in-Flight for a World-in-Motion

FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation

Osmosis: RGBD Diffusion Prior for Underwater Image Restoration

Photon Inhibition for Energy-Efficient Single-Photon Imaging

Synchronization of Projective Transformations

GMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoring

LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System

EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation

Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?

Free-Viewpoint Video of Outdoor Sports Using a Drone

Learning Cross-hand Policies of High-DOF Reaching and Grasping

Improving Domain Generalization in Self-Supervised Monocular Depth Estimation via Stabilized Adversarial Training

Deep Cost Ray Fusion for Sparse Depth Video Completion

SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data

MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain

Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction

FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversion

Quality Assured: Rethinking Annotation Strategies in Imaging AI

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

Sparse Refinement for Efficient High-Resolution Semantic Segmentation

PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priors

Unified Local-Cloud Decision-Making via Reinforcement Learning

MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction

Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving

LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow

Efficient Learning of Event-based Dense Representation using Hierarchical Memories with Adaptive Update

Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching

Understanding Physical Dynamics with Counterfactual World Modeling

Towards Real-world Event-guided Low-light Video Enhancement and Deblurring

AugDETR: Improving Multi-scale Learning for Detection Transformer

Accelerating Image Generation with Sub-path Linear Approximation Model

InternVideo2: Scaling Foundation Models for Multimodal Video Understanding

AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?

VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition

DriveLM: Driving with Graph Visual Question Answering

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Better Regression Makes Better Test-time Adaptive 3D Object Detection

Embodied Understanding of Driving Scenarios

Commonly Interesting Images

The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization

The All-Seeing Project V2: Towards General Relation Comprehension of the Open World

Zero-shot Text-guided Infinite Image Synthesis with LLM guidance

UGG: Unified Generative Grasping

Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy

VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding

PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control

Assessing Sample Quality via the Latent Space of Generative Models

DiffiT: Diffusion Vision Transformers for Image Generation

Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

LoA-Trans: Enhancing Visual Grounding by Location-Aware Transformers

Robust Nearest Neighbors for Source-Free Domain Adaptation under Class Distribution Shift

Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems

Efficient Cascaded Multiscale Adaptive Network for Image Restoration

Taming Lookup Tables for Efficient Image Retouching

Identity-Consistent Diffusion Network for Grading Knee Osteoarthritis Progression in Radiographic Imaging

Neural Metamorphosis

Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme

Generalizable Facial Expression Recognition

RICA^2: Rubric-Informed, Calibrated Assessment of Actions

Semantically Guided Representation Learning For Action Anticipation

Training-free Video Temporal Grounding using Large-scale Pre-trained Models

WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering

GraspXL: Generating Grasping Motions for Diverse Objects at Scale

FedVAD: Enhancing Federated Video Anomaly Detection with GPT-Driven Semantic Distillation

Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach

Spectral Subsurface Scattering for Material Classification

MeshVPR: Citywide Visual Place Recognition Using 3D Meshes

Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

MetaAug: Meta-Data Augmentation for Post-Training Quantization

INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding

Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs

BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training

PromptFusion: Decoupling Stability and Plasticity for Continual Learning

Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training

DEAL: Disentangle and Localize Concept-level Explanations for VLMs

Instruction Tuning-free Visual Token Complement for Multimodal LLMs

IVTP: Instruction-guided Visual Token Pruning for Large Vision-Language Models

LookupViT: Compressing visual information to a limited number of tokens

SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-Device Inference

DεpS: Delayed ε-Shrinking for Faster Once-For-All Training

Integration of Global and Local Representations for Fine-grained Cross-modal Alignment

Diffusion Models for Open-Vocabulary Segmentation

DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing

View Selection for 3D Captioning via Diffusion Ranking

WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models

Source-Free Domain-Invariant Performance Prediction

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

Wavelength-Embedding-guided Filter-Array Transformer for Spectral Demosaicing

CARB-Net: Camera-Assisted Radar-Based Network for Vulnerable Road User Detection

Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions

The Sky's the Limit: Relightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility

RANRAC: Robust Neural Scene Representations via Random Ray Consensus

TAG: Text Prompt Augmentation for Zero-Shot Out-of-Distribution Detection

ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild

Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation

Grid-Attention: Enhancing Computational Efficiency of Large Vision Models without Fine-Tuning

Rethinking and Improving Visual Prompt Selection for In-Context Learning Segmentation Framework

Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation

McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction

SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection

EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models

Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation

MonoTTA: Fully Test-Time Adaptation for Monocular 3D Object Detection

ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image

Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data

4Diff: 3D-Aware Diffusion Model for Third-to-First Viewpoint Translation

GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation

Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector

Fairness-aware Vision Transformer via Debiased Self-Attention

Modality Translation for Object Detection Adaptation without forgetting prior knowledge

Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts

Semantic-guided Robustness Tuning for Few-Shot Transfer Across Extreme Domain Shift

FlowCon: Out-of-Distribution Detection using Flow-based Contrastive Learning

PixOOD: Pixel-Level Out-of-Distribution Detection

Distributionally Robust Loss for Long-Tailed Multi-Label Image Classification

Improving 3D Semi-supervised Learning by Effectively Utilizing All Unlabelled Data

CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning

Disentangling Masked Autoencoders for Unsupervised Domain Generalization

Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding

Information Bottleneck Based Data Correction in Continual Learning

Markov Knowledge Distillation: Make Nasty Teachers trained by Self-undermining Knowledge Distillation Fully Distillable

FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients

SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks

Uncertainty Calibration with Energy Based Instance-wise Scaling in the Wild Dataset

Catastrophic Overfitting: A Potential Blessing in Disguise

LaWa: Using Latent Space for In-Generation Image Watermarking

Rethinking Data Bias: Dataset Copyright Protection via Embedding Class-wise Hidden Bias

Towards Model-Agnostic Dataset Condensation by Heterogeneous Models

VETRA: A Dataset for Vehicle Tracking in Aerial Imagery - New Challenges for Multi-Object Tracking

UniIR: Training and Benchmarking Universal Multimodal Information Retrievers

MarineInst: A Foundation Model for Marine Image Analysis with Instance Visual Description

Adaptive Correspondence Scoring for Unsupervised Medical Image Registration

Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights

Revisiting Calibration of Wide-Angle Radially Symmetric Cameras

Weakly-Supervised 3D Hand Reconstruction with Knowledge Prior and Uncertainty Guidance

SparseSSP: 3D Subcellular Structure Prediction from Sparse-View Transmitted Light Images

CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videos

FoundPose: Unseen Object Pose Estimation with Foundation Features

Continuous Memory Representation for Anomaly Detection

Differentiable Convex Polyhedra Optimization from Multi-view Images

HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation

3D Human Pose Estimation via Non-Causal Retentive Networks

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation

RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation

Stable Video Portraits

S-JEPA: A Joint Embedding Predictive Architecture for Skeletal Action Recognition

Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

Depth-guided NeRF Training via Earth Mover’s Distance

Watch Your Steps: Local Image and Scene Editing by Text Instructions

TriNeRFLet: A Wavelet Based Triplane NeRF Representation

SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization

F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding

Unifying 3D Vision-Language Understanding via Promptable Queries

SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

Revising Densification in Gaussian Splatting

PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidance

Decomposition of Neural Discrete Representations for Large-Scale 3D Mapping

Scene-Conditional 3D Object Stylization and Composition

SMooDi: Stylized Motion Diffusion Model

ZeST: Zero-Shot Material Transfer from a Single Image

BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion

ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs

3D Congealing: 3D-Aware Image Alignment in the Wild

Learning Neural Deformation Representation for 4D Dynamic Shape Generation

AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation

Efficient Training with Denoised Neural Weights

GIVT: Generative Infinite-Vocabulary Transformers

Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians

AddMe: Zero-shot Group-photo Synthesis by Inserting People into Scenes

Neural Surface Detection for Unsigned Distance Fields

Transferable 3D Adversarial Shape Completion using Diffusion Models

JDT3D: Addressing the Gaps in LiDAR-Based Tracking-by-Attention

Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos

MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices

GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondence

MONTAGE: Monitoring Training for Attribution of Generative Diffusion Models

AdversariaLeak: External Information Leakage Attack Using Adversarial Samples on Face Recognition Systems

Rotated Orthographic Projection for Self-Supervised 3D Human Pose Estimation

Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding

Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image

Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather

Memory-Efficient Fine-Tuning for Quantized Diffusion Model

SeiT++: Masked Token Modeling Improves Storage-efficient Training

Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion

Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration

Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding

SEDiff: Structure Extraction for Domain Adaptive Depth Estimation via Denoising Diffusion Models

Formula-Supervised Visual-Geometric Pre-training

LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection

Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detection

MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor Perception

UAV First-Person Viewers Are Radiance Field Learners

Caltech Aerial RGB-Thermal Dataset in the Wild

V2X-Real: a Largs-Scale Dataset for Vehicle-to-Everything Cooperative Perception

CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction

DiffFAS: Face Anti-Spoofing via Generative Diffusion Models

PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation

Rethinking Few-shot Class-incremental Learning: Learning from Yourself

Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection

An Economic Framework for 6-DoF Grasp Detection

EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding

DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation

Direct Distillation between Different Domains

UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection

Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

Motion Aware Event Representation-driven Image Deblurring

Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

Temporal-Mapping Photography for Event Cameras

COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation

An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding

AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation

UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding

Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing

Long-CLIP: Unlocking the Long-Text Capability of CLIP

RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF

FuseTeacher: Modality-fused Encoders are Strong Vision Supervisors

StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models

MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation

PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking

DCDM: Diffusion-Conditioned-Diffusion Model for Scene Text Image Super-Resolution

PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control

ReMamber: Referring Image Segmentation with Mamba Twister

Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization

IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection

HiEI: A Universal Framework for Generating High-quality Emerging Images from Natural Images

Efficient 3D-Aware Facial Image Editing via Attribute-Specific Prompt Learning

Continual Learning and Unknown Object Discovery in 3D Scenes via Self-Distillation

A Simple Background Augmentation Method for Object Detection with Diffusion Model

∞-Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite Dimensions

Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks

Compensation Sampling for Improved Convergence in Diffusion Models

Urban Waterlogging Detection: A Challenging Benchmark and Large-Small Model Co-Adapter

Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Prediction

Rethinking Deep Unrolled Model for Accelerated MRI Reconstruction

Implicit Neural Models to Extract Heart Rate from Video

A Watermark-Conditioned Diffusion Model for IP Protection

Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures

Image Manipulation Detection With Implicit Neural Representation and Limited Supervision

PetFace: A Large-Scale Dataset and Benchmark for Animal Identification

NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation

Occlusion-Aware Seamless Segmentation

Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds

Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation

SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition

Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment

Self-Supervised Video Copy Localization with Regional Token Representation

Learning with Counterfactual Explanations for Radiology Report Generation

Placing Objects in Context via Inpainting for Out-of-distribution Segmentation

Elysium: Exploring Object-level Perception in Videos through Semantic Integration Using MLLMs

Pseudo-Embedding for Generalized Few-Shot Point Cloud Segmentation

Learning Diffusion Models for Multi-View Anomaly Detection

RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos

VideoAgent: Long-form Video Understanding with Large Language Model as Agent

AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models

Learning Representations of Satellite Images From Metadata Supervision

Get Your Embedding Space in Order: Domain-Adaptive Regression for Forest Monitoring

Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition

Wavelet Convolutions for Large Receptive Fields

Trainable Highly-expressive Activation Functions

SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images

V-IRL: Grounding Virtual Intelligence in Real Life

OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web

Chains of Diffusion Models

Grounding Language Models for Visual Entity Recognition

Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models

Align before Collaborate: Mitigating Feature Misalignment for Robust Multi-Agent Perception

UniCode : Learning a Unified Codebook for Multimodal Large Language Models

Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning

Non-Exemplar Domain Incremental Learning via Cross-Domain Concept Integration

Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities

Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models

Simple Unsupervised Knowledge Distillation With Space Similarity

InstructGIE: Towards Generalizable Image Editing

StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion

3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance

Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval

Towards Open-Ended Visual Recognition with Large Language Models

AFreeCA: Annotation-Free Counting for All

InstructIR: High-Quality Image Restoration Following Human Instructions

Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs

DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment

Dataset Growth

Dolphins: Multimodal Language Model for Driving

Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation

MO-EMT-NAS: Multi-Objective Continuous Transfer of Architectural Knowledge Between Tasks from Different Datasets

SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation

AttnZero: Efficient Attention Discovery for Vision Transformers

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation

One-Shot Diffusion Mimicker for Handwritten Text Generation

KMTalk: Speech-Driven 3D Facial Animation with Key Motion Embedding

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos

Prioritized Semantic Learning for Zero-shot Instance Navigation

Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos

Temporal Residual Jacobians for Rig-free Motion Transfer

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond

Operational Open-Set Recognition and PostMax Refinement

AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking

Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer

TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection

Learning with Unmasked Tokens Drives Stronger Vision Learners

Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt

Asynchronous Bioplausible Neuron for Spiking Neural Networks for Event-Based Vision

Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding

The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers

FYI: Flip Your Images for Dataset Distillation

Contrastive Learning with Synthetic Positives

Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers

Data-to-Model Distillation: Data-Efficient Learning Framework

Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment

FunQA: Towards Surprising Video Comprehension

Robust Calibration of Large Vision-Language Adapters

FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning

Benchmarking Spurious Bias in Few-Shot Image Classifiers

Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network

ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detection

Adapting to Shifting Correlations with Unlabeled Data Calibration

Distribution-Aware Robust Learning from Long-Tailed Data with Noisy Labels

De-Confusing Pseudo-Labels in Source-Free Domain Adaptation

Improving Unsupervised Domain Adaptation: A Pseudo-Candidate Set Approach

Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation

Feature Diversification and Adaptation for Federated Domain Generalization

Harmonizing knowledge Transfer in Neural Network with Unified Distillation

PFedEdit: Personalized Federated Learning via Automated Model Editing

Layer-Wise Relevance Propagation with Conservation Property for ResNet

Training A Secure Model against Data-Free Model Extraction

Augmented Neural Fine-tuning for Efficient Backdoor Purification

MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition

Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields

FisherRF: Active View Selection and Mapping with Radiance Fields using Fisher Information

UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation

Few-shot NeRF by Adaptive Rendering Loss Regularization

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis

Weight Conditioning for Smooth Optimization of Neural Networks

Invertible Neural Warp for NeRF

Generating Human Interaction Motions in Scenes with Text Control

VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing

MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping

CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians

Towards Image Ambient Lighting Normalization

MVDiffHD: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

Efficient Neural Video Representation with Temporally Coherent Modulation

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting

VersatileGaussian: Real-time Neural Rendering for Versatile Tasks using Gaussian Splatting

LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning

NeRMo: Learning Implicit Neural Representations for 3D Human Motion Prediction

Motion Mamba: Efficient and Long Sequence Motion Generation

ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation

Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance

Pyramid Diffusion for Fine 3D Large Scene Generation

Taming Latent Diffusion Model for Neural Radiance Field Inpainting

HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras

Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models

POET: Prompt Offset Tuning for Continual Human Action Adaptation

NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model

AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild

Modeling and Driving Human Body Soundfields through Acoustic Primitives

Kinetic Typography Diffusion Model

3R-INN: How to be climate friendly while consuming/delivering videos?

Rethinking Unsupervised Outlier Detection via Multiple Thresholding

Domain Reduction Strategy for Non-Line-of-Sight Imaging

Intrinsic Single-Image HDR Reconstruction

NeRF-XL: NeRF at Any Scale with Multi-GPU

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering

Synthesizing Environment-Specific People in Photographs

GAURA: Generalizable Approach for Unified Restoration and Rendering of Arbitrary Views

Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization

HybridBooth: Hybrid Prompt Inversion for Efficient Subject-Driven Generation

FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation

Collaborative Control for Geometry-Conditioned PBR Image Generation

Distilling Knowledge from Large-Scale Image Models for Object Detection

Text2LiDAR: Text-guided LiDAR Point Clouds Generation via Equirectangular Transformer

URS-NeRF: Unordered Rolling Shutter Bundle Adjustment for Neural Radiance Fields

Reinforcement Learning via Auxillary Task Distillation

NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields

Concise Plane Arrangements for Low-Poly Surface and Volume Modelling

SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstruction

Revisit Self-supervision with Local Structure-from-Motion

Open-Set Biometrics: Beyond Good Closed-Set Models

Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry

CoTracker: It is Better to Track Together

On the Viability of Monocular Depth Pre-training for Semantic Segmentation

Weakly-supervised Camera Localization by Ground-to-satellite Image Registration

AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation

FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis

SemReg: Semantics Constrained Point Cloud Registration

NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation

Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation

CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization

Latent Guard: a Safety Framework for Text-to-image Generation

SPIRE: Semantic Prompt-Driven Image Restoration

ControlLLM: Augment Language Models with Tools by Searching on Graphs

AWOL: Analysis WithOut synthesis using Language

GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns

Synchronous Diffusion for Unsupervised Smooth Non-Rigid 3D Shape Matching

Scalar Function Topology Divergence: Comparing Topology of 3D Objects

Finding Visual Task Vectors

EgoPet: Egomotion and Interaction Data from an Animal's Perspective

Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement

Frugal 3D Point Cloud Model Training via Progressive Near Point Filtering and Fused Aggregation

ProtoComp: Diverse Point Cloud Completion with Controllable Prototype

DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation

3D Small Object Detection with Dynamic Spatial Pruning

Adaptive Annealing for Robust Averaging

Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization

DySeT: a Dynamic Masked Self-distillation Approach for Robust Trajectory Prediction

Learning Pseudo 3D Guidance for View-consistent Texturing with 2D Diffusion

LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation

Physical-Based Event Camera Simulator

Learning Neural Volumetric Pose Features for Camera Localization

ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions

ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations

Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos

Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos

LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction

ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities

IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

Volumetric Rendering with Baked Quadrature Fields

Exact Diffusion Inversion via Bidirectional Integration Approximation

Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation

Lagrangian Hashing for Compressed Neural Field Representations

PointNeRF++: A multi-scale, point-based Neural Radiance Field

Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignment

OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics

Fast Encoding and Decoding for Implicit Video Representation

LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation

Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models

Do text-free diffusion models learn discriminative visual representations?

EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

High-Fidelity and Transferable NeRF Editing by Frequency Decomposition

Implicit Style-Content Separation using B-LoRA

MyVLM: Personalizing VLMs for User-Specific Queries

Curved Diffusion: A Generative Model With Optical Geometry Control

Lazy Diffusion Transformer for Interactive Image Editing

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

Continuity Preserving Online CenterLine Graph Learning

GAMMA-FACE: GAussian Mixture Models Amend Diffusion Models for Bias Mitigation in Face Images

AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation

Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs

FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models

Rate-Distortion-Cognition Controllable Versatile Neural Image Compression

Closed-Loop Unsupervised Representation Disentanglement with $\beta$-VAE Distillation and Diffusion Probabilistic Feedback

Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers’ Opinion Scores

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

Blind image deblurring with noise-robust kernel estimation

Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems

Self-Guided Generation of Minority Samples Using Diffusion Models

OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation

DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models

ZigMa: A DiT-style Zigzag Mamba Diffusion Model

FMBoost: Boosting Latent Diffusion with Flow Matching

WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians

BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events

Three Things We Need to Know About Transferring Stable Diffusion to Visual Dense Prediciton Tasks

FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis

Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing

Towards compact reversible image representations for neural style transfer

InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser

ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model

When and How do negative prompts take effect?

Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models

WeConvene: Learned Image Compression with Wavelet-Domain Convolution and Entropy Model

Global Counterfactual Directions

AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation

Point-supervised Panoptic Segmentation via Estimating Pseudo Labels from Learnable Distance

General Geometry-aware Weakly Supervised 3D Object Detection

OneTrack: Demystifying the Conflict Between Detection and Tracking in End-to-End 3D Trackers

CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians

Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modeling

Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models

UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt

Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation

Regularizing Dynamic Radiance Fields with Kinematic Fields

In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation

Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers

Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients

Learned Rate Control for Frame-Level Adaptive Neural Video Compression via Dynamic Neural Network

Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems

NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image

HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization

Face Reconstruction Transfer Attack as Out-of-Distribution Generalization

Bottom-Up Domain Prompt Tuning for Generalized Face Anti-Spoofing

Norface: Improving Facial Expression Analysis by Identity Normalization

Brain Netflix: Scaling Data to Reconstruct Videos from Brain Signals

VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG

Elucidating the Hierarchical Nature of Behavior with Masked Autoencoders

Bayesian Evidential Deep Learning for Online Action Detection

Event Camera Data Dense Pre-training

Unsupervised Moving Object Segmentation with Atmospheric Turbulence

Beyond MOT: Semantic Multi-Object Tracking

Optimizing Factorized Encoder Models: Time and Memory Reduction for Scalable and Efficient Action Recognition

Rethinking Image-to-Video Adaptation: An Object-centric Perspective

Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation

NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models

PointLLM: Empowering Large Language Models to Understand Point Clouds

StableDrag: Stable Dragging for Point-based Image Editing

BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion

DMiT: Deformable Mipmapped Tri-Plane Representation for Dynamic Scenes

ST-LLM: Large Language Models Are Effective Temporal Learners

Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models

Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation

NAMER: Non-Autoregressive Modeling for Handwritten Mathematical Expression Recognition

Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data

Navigation Instruction Generation with BEV Perception and Large Language Models

UniProcessor: A Text-induced Unified Low-level Image Processor

Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation

Tokenize Anything via Prompting

Think before Placement: Common Sense Enhanced Transformer for Object Placement

HiFi-Score: Fine-grained Image Description Evaluation with Hierarchical Parsing Graphs

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

Getting it Right: Improving Spatial Consistency in Text-to-Image Models

MultiGen: Zero-shot Image Generation from Multi-modal Prompts

VeCLIP: Improving CLIP Training via Visual-enriched Captions

MC-PanDA: Mask Confidence for Panoptic Domain Adaptation

Adapt without Forgetting: Distill Proximity from Dual Teachers in Vision-Language Models

GRACE: Graph-Based Contextual Debiasing for Fair Visual Question Answering

Look Hear: Gaze Prediction for Speech-directed Human Attention

Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection

Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection

FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection

CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs

Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing

You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation

I Can't Believe It's Not Scene Flow!

FlashTex: Fast Relightable Mesh Texturing with LightControlNet

Evaluating Text-to-Visual Generation with Image-to-Text Generation

DOCCI: Descriptions of Connected and Contrasting Images

SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment

SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis

Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection

A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting

3DGazeNet: Generalizing Gaze Estimation with Weak Supervision from Synthetic Views

Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation

Arc2Face: A Foundation Model for ID-Consistent Human Faces

SAGS: Structure-Aware 3D Gaussian Splatting

PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery

FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions

MemBN: Robust Test-Time Adaptation via Batch Norm with Statistics Memory

Towards More Practical Group Activity Detection: A New Benchmark and Model

Distilling Diffusion Models into Conditional GANs

On-the-fly Category Discovery for LiDAR Semantic Segmentation

Risk-Aware Self-Consistent Imitation Learning for Trajectory Planning in Autonomous Driving

OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation

Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights

Watching it in Dark: A Target-aware Representation Learning Framework for High-Level Vision Tasks in Low Illumination

Gradient-Aware for Class-Imbalanced Semi-supervised Medical Image Segmentation

DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation

AMD: Automatic Multi-step Distillation of Large-scale Vision Models

Linking in Style: Understanding learned features in deep learning models

On Learning Discriminative Features from Synthesized Data for Self-Supervised Fine-Grained Visual Recognition

Robust Multimodal Learning via Representation Decoupling

Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning

Region-centric Image-Language Pretraining for Open-Vocabulary Detection

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort

Image-Feature Weak-to-Strong Consistency: An Enhanced Paradigm for Semi-Supervised Learning

Strike a Balance in Continual Panoptic Segmentation

IGNORE: Information Gap-based False Negative Loss Rejection for Single Positive Multi-Label Learning

Learning to Distinguish Samples for Generalized Category Discovery

HVCLIP: High-dimensional Vector in CLIP for Unsupervised Domain Adaptation

DiffClass: Diffusion-Based Class Incremental Learning

Adversarial Prompt Tuning for Vision-Language Models

Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images

How to Train the Teacher Model for Effective Knowledge Distillation

Dataset Quantization with Active Learning based Adaptive Sampling

Local and Global Flatness for Federated Domain Generalization

Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search

Cross-Input Certified Training for Universal Perturbations

Interpretability-Guided Test-Time Adversarial Defense

Self-Supervised Representation Learning for Adversarial Attack Detection

On the Vulnerability of Skip Connections to Model Inversion Attacks

Non-transferable Pruning

CONDA: Condensed Deep Association Learning for Co-Salient Object Detection.

PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning

SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection

Just a Hint: Point-Supervised Camouflaged Object Detection

Controllable Navigation Instruction Generation with Chain of Thought Prompting

A Geometric Distortion Immunized Deep Watermarking Framework with Robustness Generalizability

PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition

COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation

Geospecific View Generation - Geometry-Context Aware High-resolution Ground View Inference from Satellite Views

Learning Multimodal Latent Generative Models with Energy-Based Prior

Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization

FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation

IRGen: Generative Modeling for Image Retrieval

Decoupling Common and Unique Representations for Multimodal Self-supervised Learning

Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer

3D Gaussian Parametric Head Model

I-MedSAM: Implicit Medical Image Segmentation with Segment Anything

Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging

MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models

A Probability-guided Sampler for Neural Implicit Surface Rendering

G2fR: Frequency Regularization in Grid-based Feature Encoding Neural Radiance Fields

InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstruction

DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators

Vista3D: unravel the 3d darkside of a single image

Isomorphic Pruning for Vision Models

GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval

Adversarially Robust Distillation by Reducing the Student-Teacher Variance Gap

Adaptive Multi-head Contrastive Learning

RCS-Prompt: Learning Prompt to Rearrange Class Space for Prompt-based Continual Learning

Rethinking Normalization Layers for Domain Generalizable Person Re-identification

How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs

PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery

A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties

Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling

MagMax: Leveraging Model Merging for Seamless Continual Learning

Revisiting Supervision for Continual Representation Learning

Exemplar-free Continual Representation Learning via Learnable Drift Compensation

Rethinking Fast Adversarial Training: A Splitting Technique To Overcome Catastrophic Overfitting

Debiasing surgeon: fantastic weights and how to find them

Privacy-Preserving Adaptive Re-Identification without Image Transfer

An Adaptive Screen-Space Meshing Approach for Normal Integration

GGRt: Towards Generalizable 3D Gaussians without Pose Priors in Real-Time

Rasterized Edge Gradients: Handling Discontinuities Differentially

Hierarchical Separable Video Transformer for Snapshot Compressive Imaging

SRPose: Two-view Relative Pose Estimation with Sparse Keypoints

Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis

MagicMirror: Fast and High-Quality Avatar Generation with Constrained Search Space

3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation

Viewpoint textual inversion: discovering scene representations and 3D view control in 2D diffusion models

Sapiens: Foundation for Human Vision Models

Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture

Expressive Whole-Body 3D Gaussian Avatar

Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model

DPA-Net: Structured 3D Abstraction from Sparse Views via Differentiable Primitive Assembly

Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images

SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweepers

MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views

Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction

Disentangled Generation and Aggregation for Robust Radiance Fields

Dual-Camera Smooth Zoom on Mobile Phones

Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondences

Multi-modal Crowd Counting via a Broker Modality

SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes

Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360°

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians

DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction

Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration

SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models

IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination

SAM-guided Graph Cut for 3D Instance Segmentation

CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

Text to Layer-wise 3D Clothed Human Generation

DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose

Learned Neural Physics Simulation for Articulated 3D Human Pose Reconstruction

HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting

Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion

TLControl: Trajectory and Language Control for Human Motion Synthesis

TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds

EINet: Point Cloud Completion via Extrapolation and Interpolation

CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation

Disentangled Clothed Avatar Generation from Text Descriptions

StructLDM: Structured Latent Diffusion for 3D Human Generation

FreeInit: Bridging Initialization Gap in Video Diffusion Models

ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance

TC4D: Trajectory-Conditioned Text-to-4D Generation

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

Canonical Shape Projection is All You Need for 3D Few-shot Class Incremental Learning

DGD: Dynamic 3D Gaussians Distillation

SHIC: Shape-Image Correspondences with no Keypoint Supervision

LineFit: A Geometric Approach for Fitting Line Segments in Images

MMBENCH: Is Your Multi-Modal Model an All-around Player?

Large Motion Model for Unified Multi-Modal Motion Generation

Octopus: Embodied Vision-Language Programmer from Environmental Feedback

Robust Fitting on a Gate Quantum Computer

The Nerfect Match: Exploring NeRF Features for Visual Localization

Physics-Based Interaction with 3D Objects via Video Generation

IMMA: Immunizing text-to-image Models against Malicious Adaptation

HPE-Li: WiFi-enabled Lightweight Dual Selective Kernel Convolution for Human Pose Estimation

Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time

Learning to Obstruct Few-Shot Image Classification over Restricted Classes

UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model

iHuman: Instant Animatable Digital Humans From Monocular Videos

Optimizing Illuminant Estimation in Dual-Exposure HDR Imaging

Text-Conditioned Resampler For Long Form Video Understanding

EgoBody3M: Egocentric Body Tracking on a VR Headset using a Diverse Dataset

GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering

D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction

Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning

R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding

Ex2Eg-MAE: A Framework for Adaptation of Exocentric Video Masked Autoencoders for Egocentric Social Role Understanding

FutureDepth: Learning to Predict the Future Improves Video Depth Estimation

A Riemannian Approach for Spatiotemporal Analysis and Generation of 4D Tree-shaped Structures

UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation

AEDNet: Adaptive Embedding and Multiview-Aware Disentanglement for Point Cloud Completion

Adaptive Human Trajectory Prediction via Latent Corridors

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding

Holodepth: Programmable Depth-Varying Projection via Computer-Generated Holography

Flowed Time of Flight Radiance Fields

Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering

Denoising Vision Transformers

SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather

LiDAR-based All-weather 3D Object Detection via Prompting and Distilling 4D Radar

SkyScenes: A Synthetic Dataset for Aerial Scene Understanding

ViPer: Visual Personalization of Generative Models via Individual Preference Learning

How Far Can a 1-Pixel Camera Go? Solving Vision Tasks using Photoreceptors and Computationally Designed Visual Morphology

Temporal Event Stereo via Joint Learning with Stereoscopic Flow

Early Anticipation of Driving Maneuvers

Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention

Probabilistic Weather Forecasting with Deterministic Guidance-based Diffusion Model

FARSE-CNN: Fully Asynchronous, Recurrent and Sparse Event-Based CNN

Event-Adapted Video Super-Resolution

Diffusion Models as Optimizers for Efficient Planning in Offline RL

Scene-aware Human Motion Forecasting via Mutual Distance Prediction

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

Track Everything Everywhere Fast and Robustly

CoMo: Controllable Motion Generation through Language Guided Pose Code Editing

Gravity-aligned Rotation Averaging with Circular Regression

Semicalibrated Relative Pose from an Affine Correspondence and Monodepth

MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps

Global Structure-from-Motion Revisited

GeoCalib: Learning Single-image Calibration with Geometric Optimization

Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information

Where am I? Scene Retrieval with Language

Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels

SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs

StereoGlue: Joint Feature Matching and Robust Estimation

Robust Incremental Structure-from-Motion with Hybrid Features

Relightable Neural Actor with Intrinsic Decomposition and Pose Control

Controlling the World by Sleight of Hand

DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields

Co-speech Gesture Video Generation with 3D Human Meshes

NOVUM: Neural Object Volumes for Robust Object Classification

Solving Motion Planning Tasks with a Scalable Generative Model

iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning

BlenderAlchemy: Editing 3D Graphics with Vision-Language Models

View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling

ConDense: Consistent 2D-3D Pre-training for Dense and Sparse Features from Multi-View Images

PACE: Pose Annotations in Cluttered Environments

Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation

3D Hand Pose Estimation in Everyday Egocentric Images

3D Reconstruction of Objects in Hands without Real World 3D Supervision

Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition

WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding

Controllable Human-Object Interaction Synthesis

Nymeria: A Massive Collection of Egocentric Multi-modal Human Motion in the Wild

DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving

OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models

Factorized Diffusion: Perceptual Illusions by Noise Decomposition

DiffusionPen: Towards Controlling the Style of Handwritten Text Generation

Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation

WordRobe: Text-Guided Generation of Textured 3D Garments

Deep Patch Visual SLAM

SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive Transformers

FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition

Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density

Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas

Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets

SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding

CityGuessr: City-Level Video Geo-Localization on a Global Scale

Möbius Transform for Mitigating Perspective Distortions in Representation Learning

X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs

DrivingDiffusion: Layout-Guided Multi-View Driving Scenarios Video Generation with Latent Diffusion Model

Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching

Depth-Aware Blind Image Decomposition for Real-World Adverse Weather Recovery

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning

Diff3DETR: Agent-based Diffusion Model for Semi-supervised 3D Object Detection

Free Lunch for Gait Recognition: A Novel Relation Descriptor

Generative End-to-End Autonomous Driving

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion

GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

SpatialFormer: Towards Generalizable Vision Transformers with Explicit Spatial Understanding

Safe-Sim: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries

Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation

Learning to Build by Building Your Own Instructions

G3R: Gradient Guided Generalizable Reconstruction

DeTra: A Unified Model for Object Detection and Trajectory Forecasting

UniCal: Unified Neural Sensor Calibration

NePhi: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registration

BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting

RSL-BA: Rolling Shutter Line Bundle Adjustment

BeNeRF:Neural Radiance Fields from a Single Blurry Image and Event Stream

Six-Point Method for Multi-Camera Systems with Reduced Solution Space

Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection

Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities

Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations

AlignDiff: Aligning Diffusion Models for General Few-Shot Segmentation

UniINR: Event-guided Unified Rolling Shutter Correction, Deblurring, and Interpolation

EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding

Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentation

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection

EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation

HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

TTT-MIM: Test-Time Training with Masked Image Modeling for Denoising Distribution Shifts

Adaptive Selection of Sampling-Reconstruction in Fourier Compressed Sensing

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance

Confidence-Based Iterative Generation for Real-World Image Super-Resolution

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation

Tuning-Free Image Customization with Image and Text Guidance

Dolfin: Diffusion Layout Transformers without Autoencoder

Fast View Synthesis of Casual Videos with Soup-of-Planes

Explorative Inbetweening of Time and Space

Accelerating Image Super-Resolution Networks with Pixel-Level Classification

SAVE: Protagonist Diversification with Structure Agnostic Video Editing

Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks

Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision

SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder

RadEdit: stress-testing biomedical vision models via diffusion image editing

Stripe Observation Guided Inference Cost-free Attention Mechanism

Trajectory-aligned Space-time Tokens for Few-shot Action Recognition

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design

DSA: Discriminative Scatter Analysis for Early Smoke Segmentation

FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing

BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation

Factorizing Text-to-Video Generation by Explicit Image Conditioning

AdaIFL: Adaptive Image Forgery Localization via a Dynamic and Importance-aware Transformer Network

Toward Tiny and High-quality Facial Makeup with Data Amplify Learning

GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting

When Do We Not Need Larger Vision Models?

Open Panoramic Segmentation

SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging

Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation

Self-Supervised Any-Point Tracking by Contrastive Random Walks

A Secure Image Watermarking Framework with Statistical Guarantees via Adversarial Attacks on Secret Key Networks

Robust Zero-Shot Crowd Counting and Localization with Adaptive Resolution SAM

Non-parametric Sensor Noise Modeling and Synthesis

ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement

SegPoint: Segment Any Point Cloud via Large Language Model

Learning to Robustly Reconstruct Dynamic Scenes from Low-light Spike Streams

Learning a Dynamic Privacy-preserving Camera Robust to Inversion Attacks

Improving image synthesis with diffusion-negative sampling

ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos

Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement

Contextual Correspondence Matters: Bidirectional Graph Matching for Video Summarization

Weakly-Supervised Spatio-Temporal Video Grounding with Variational Cross-Modal Alignment

MagicEraser: Erasing Any Objects via Semantics-Aware Control

Cross-Domain Learning for Video Anomaly Detection with Limited Supervision

GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction

TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling

EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections

TimeCraft: Navigate Weakly-Supervised Temporal Grounded Video Question Answering via Bi-directional Reasoning

LITA: Language Instructed Temporal-Localization Assistant

CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing

Siamese Vision Transformers are Scalable Audio-visual Learners

EvSign: Sign Language Recognition and Translation with Streaming Events

Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification

Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL

Take A Step Back: Rethinking the Two Stages in Visual Reasoning

Multi-Task Domain Adaptation for Language Grounding with 3D Objects

Preventing Catastrophic Forgetting through Memory Networks in Continuous Detection

TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models

Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge

Navigating Text-to-Image Generative Bias across Indic Languages

HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions

Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction

Improving Diffusion Models for Authentic Virtual Try-on in the Wild

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion

ReNoise: Real Image Inversion Through Iterative Noising

LCM-Lookahead for Encoder-based Text-to-Image Personalization

COIN-Matting: Confounder Intervention for Image Matting

GaussReg: Fast 3D Registration with Gaussian Splatting

SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation

DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors

Parrot Captions Teach CLIP to Spot Text

Free-ATM: Harnessing Free Attention Masks for Representation Learning on Diffusion-Generated Images

MotionDirector: Motion Customization of Text-to-Video Diffusion Models

Learning Video Context as Interleaved Multimodal Sequences

Score Distillation Sampling with Learned Manifold Corrective

Instant 3D Human Avatar Generation using Image Diffusion Models

WAS: Dataset and Methods for Artistic Text Segmentation

SwapAnything: Enabling Arbitrary Object Swapping in Personalized Image Editing

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

Thinking Outside the BBox: Unconstrained Generative Object Compositing

Free-Editor: Zero-shot Text-driven 3D Scene Editing

Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective

Towards Multi-modal Transformers in Federated Learning

LatentEditor: Text Driven Local Editing of 3D Scenes

VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models

BAMM: Bidirectional Autoregressive Motion Model

From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

Spline-based Transformers

Lossy Image Compression with Foundation Diffusion Models

Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models

Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models

AdaDiffSR: Adaptive Region-aware Dynamic acceleration Diffusion Model for Real-World Image Super-Resolution

DEVIAS: Learning Disentangled Video Representations of Action and Scene

Neural Spectral Decomposition for Dataset Distillation

ReGround: Improving Textual and Spatial Grounding at No Cost

Platypus: A Generalized Specialist Model for Reading Text in Various Forms

Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation

RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

TF-FAS: Twofold-Element Fine-Grained Semantic Guidance for Generalizable Face Anti-Spoofing

Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model

Multi-branch Collaborative Learning Network for 3D Visual Grounding

Enhancing Tampered Text Detection through Frequency Feature Fusion and Decomposition

Textual Grounding for Open-vocabulary Visual Information Extraction in Layout-diversified Documents

CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection

DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation

Bi-TTA: Bidirectional Test-Time Adapter for Remote Physiological Measurement

Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models

GalLop: Learning global and local prompts for vision-language models

Can OOD Object Detectors Learn from Foundation Models?

SAFARI: Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation

Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition

MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion

Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models

Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution

Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

VideoMamba: Spatio-Temporal Selective State Space Model

Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition

Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation

Interaction-centric Spatio-Temporal Context Reasoning for Multi-Person Video HOI Recognition

GRiT: A Generative Region-to-text Transformer for Object Understanding

IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation

Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images

Click Prompt Learning with Optimal Transport for Interactive Segmentation

Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier

Made to Order: Discovering monotonic temporal changes via self-supervised video ordering

Knowledge-enhanced Visual-Language Pretraining for Computational Pathology

Multi-Sentence Grounding for Long-term Instructional Video

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

LLMGA: Multimodal Large Language Model based Generation Assistant

Audio-visual Generalized Zero-shot Learning the Easy Way

Audio-Synchronized Visual Animation

Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations

Goldfish: Vision-Language Understanding of Arbitrarily Long Videos

Spherical World-Locking for Audio-Visual Localization in Egocentric Videos

V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation

Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time

PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion

Implicit Concept Removal of Diffusion Models

WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation

Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing

Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving

Benchmarking Object Detectors with COCO: A New Path Forward

CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model

AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval

Pix2Gif: Motion-Guided Diffusion for GIF Generation

cDP-MIL: Robust Multiple Instance Learning via Cascaded Dirichlet Process

PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines

DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM

UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation

EA-VTR: Event-Aware Video-Text Retrieval

Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures

SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning

LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer

Learning-based Axial Video Motion Magnification

BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models

BAFFLE: A Baseline of Backpropagation-Free Federated Learning

TrojVLM: Backdoor Attack Against Vision Language Models

Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment

Structured-NeRF: Hierarchical Scene Graph with Neural Representation

Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models

Enhancing Optimization Robustness in 1-bit Neural Networks through Stochastic Sign Descent

Pseudo-Labelling Should Be Aware of Disguising Channel Activations

SNP: Structured Neuron-level Pruning to Preserve Attention Scores

To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning

Unsupervised Representation Learning by Balanced Self Attention Matching

HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion

Linearly Controllable GAN: Unsupervised Feature Categorization and Decomposition for Image Generation and Manipulation

Diagnosing and Re-learning for Balanced Multimodal Learning

Visual Prompting via Partial Optimal Transport

MetaWeather: Few-Shot Weather-Degraded Image Restoration

Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild

Modeling Label Correlations with Latent Context for Multi-Label Recognition

Rebalancing Using Estimated Class Distribution for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch

X-Pose: Detecting Any Keypoints

Segment and Recognize Anything at Any Granularity

Making Large Language Models Better Planners with Reasoning-Decision Alignment

Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting

Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams

Few-shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation

CPT-VR: Improving Surface Rendering via Closest Point Transform with View-Reflection Appearance

Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments

OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents

APL: Anchor-based Prompt Learning for One-stage Weakly Supervised Referring Expression Comprehension

Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation

AdaDistill: Adaptive Knowledge Distillation for Deep Face Recognition

Defect Spectrum: A Granular Look of Large-scale Defect Datasets with Rich Semantics

Combining Generative and Geometry Priors for Wide-Angle Portrait Correction

Improving 2D Feature Representations by 3D-Aware Fine-Tuning

DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion Consistency

Eliminating Feature Ambiguity for Few-Shot Segmentation

GroupDiff: Diffusion-based Group Portrait Editing

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

Loc3Diff: Local Diffusion for 3D Human Head Synthesis and Editing

Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment

DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting

Improving Adversarial Transferability via Model Alignment

Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

DragAPart: Learning a Part-Level Motion Prior for Articulated Objects

Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imaging

Surface Reconstruction for 3D Gaussian Splatting via Local Structural Hints

Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal

3iGS: Factorised Tensorial Illumination for 3D Gaussian Splatting

Adversarial Diffusion Distillation

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decomposition

LogoSticker: Inserting Logos into Diffusion Models for Customized Generation

Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation

PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Learning to Unlearn for Robust Machine Unlearning

Towards Physical World Backdoor Attacks against Skeleton Action Recognition

Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers

Harnessing Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation

Echoes of the Past: Boosting Long-tail Recognition via Reflective Learning

MinD-3D: Reconstruct High-quality 3D objects in Human Brain

Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Models

Self-supervised Shape Completion via Involution and Implicit Correspondences

MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment

Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits

C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition

AMEGO: Active Memory from long EGOcentric videos

Towards Neuro-Symbolic Video Understanding

SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance

SILC: Improving Vision Language Pretraining with Self-Distillation

MoVideo: Motion-Aware Video Generation with Diffusion Models

MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty

SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation

Co-Student: Collaborating Strong and Weak Students for Sparsely Annotated Object Detection

Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views

E3M: Zero-Shot Spatio-Temporal Video Grounding with Expectation-Maximization Multimodal Modulation

A Unified Image Compression Method for Human Perception and Multiple Vision Tasks

Region-Native Visual Tokenization

Towards Dual Transparent Liquid Level Estimation in Biomedical Lab: Dataset, Methods and Practice

Eliminating Warping Shakes for Unsupervised Online Video Stitching

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation

Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network

Facial Affective Behavior Analysis with Instruction Tuning

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

An Incremental Unified Framework for Small Defect Inspection

Learn to Optimize Denoising Scores: A Unified and Improved Diffusion Prior for 3D Generation

Dissolving Is Amplifying: Towards Fine-Grained Anomaly Detection

Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models

Towards Open-ended Visual Quality Comparison

D4-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On

GenQ: Quantization in Low Data Regimes with Generative Synthetic Data

Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach

Characterizing Model Robustness via Natural Input Gradients

Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models

LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis

Hetecooper: Feature Collaboration Graph for Heterogeneous Collaborative Perception

Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively

ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders

Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders

On Pretraining Data Diversity for Self-Supervised Learning

DATENeRF: Depth-Aware Text-based Editing of NeRFs

GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning

TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks

Multi-Granularity Sparse Relationship Matrix Prediction Network for End-to-End Scene Graph Generation

Soft Prompt Generation for Domain Generalization

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion

The Hard Positive Truth about Vision-Language Compositionality

m&m’s: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

BLINK: Multimodal Large Language Models Can See but Not Perceive

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery

Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Object Appearance Graphs

HowToCaption: Prompting LLMs to Transform Video Annotations at Scale

GiT: Towards Generalist Vision Transformer through Universal Language Interface

SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery

OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing

Scaling Backwards: Minimal Synthetic Pre-training?

Rethinking Image Super Resolution from Training Data Perspectives

Object-Centric Diffusion for Efficient Video Editing

SIGMA: Sinkhorn-Guided Masked Video Modeling

GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features

Quantized Prompt for Efficient Generalization of Vision-Language Models

uCAP: An Unsupervised Prompting Method for Vision-Language Models

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

Improving Knowledge Distillation via Regularizing Feature Direction and Norm

DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images

SIMBA: Split Inference - Mechanisms, Benchmarks and Attacks

Event Trojan: Asynchronous Event-based Backdoor Attacks

Data Poisoning Quantization Backdoor Attack

Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory

Real-data-driven 2000 FPS Color Video from Mosaicked Chromatic Spikes

Self-Supervised Underwater Caustics Removal and Descattering via Deep Monocular SLAM

Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats

Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis

City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web

Generalizable Human Gaussians for Sparse View Synthesis

Improving Neural Surface Reconstruction with Feature Priors from Multi-View Images

SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization

End-to-End Rate-Distortion Optimized 3D Gaussian Representation

DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting

Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting

POCA: Post-training Quantization with Temporal Alignment for Codec Avatars

TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation

Shapefusion: 3D localized human diffusion models

Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution

Open-World Dynamic Prompt and Continual Visual Representation Learning

MSD: A Benchmark Dataset for Floor Plan Generation of Building Complexes

RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion

T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy

PSALM: Pixelwise Segmentation with Large Multi-modal Model

Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains

Multi-modal Relation Distillation for Unified 3D Representation Learning

Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM

Zero-Shot Multi-Object Scene Completion

Single-Photon 3D Imaging with Equi-Depth Photon Histograms

Leveraging scale- and orientation-covariant features for planar motion estimation

TreeSBA: Tree-Transformer for Self-Supervised Sequential Brick Assembly

Human Pose Recognition via Occlusion-Preserving Abstract Images

RT-Pose: A 4D Radar-Tensor based 3D Human Pose Estimation and Localization Benchmark

6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry

On the Utility of 3D Hand Poses for Action Recognition

Towards Stable 3D Object Detection

Beyond the Data Imbalance: Employing the Heterogeneous Datasets for Vehicle Maneuver Prediction

ADMap: Anti-disturbance Framework for Vectorized HD Map Construction

CarFormer: Self-Driving with Learned Object-Centric Representations

Visual Relationship Transformation

Un-EVIMO: Unsupervised Event-based Independent Motion Segmentation

Local All-Pair Correspondence for Point Tracking

REDIR: Refocus-free Event-based De-occlusion Image Reconstruction

Exploiting Dual-Correlation for Multi-frame Time-of-Flight Denoising

Teach CLIP to Develop a Number Sense for Ordinal Regression

Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models

Self-Supervised Audio-Visual Soundscape Stylization

Photorealistic Video Generation with Diffusion Models

Diffusion-Based Image-to-Image Translation by Noise Correction via Prompt Interpolation

Text2Place: Affordance-aware Text Guided Human Placement

Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression

EraseDraw : Learning to Insert Objects by Erasing Them from Images

ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generation

Label-free Neural Semantic Image Synthesis

Inf-DiT: Upsampling any-resolution image with memory-efficient diffusion transformer.

Context Diffusion: In-Context Aware Image Generation

SpeedUpNet: A Plug-and-Play Adapter Network for Accelerating Text-to-Image Diffusion Models

Large-scale Reinforcement Learning for Diffusion Models

Revisiting Feature Disentanglement Strategy in Diffusion Training and Breaking Conditional Independence Assumption in Sampling

Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion

Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis

AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation

L-DiffER: Single Image Reflection Removal with Language-based Diffusion Model

LMT-GP: Combined Latent Mean-Teacher and Gaussian Process for Semi-supervised Low-light Image Enhancement

Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal

OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal

DualDn: Dual-domain Denoising via Differentiable ISP

Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation

GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields

Personalized Privacy Protection Mask Against Unauthorized Facial Recognition

An Optimal Control View of LoRA and Binary Controller Design for Vision Transformers

DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video

SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders

Context-Aware Action Recognition: Introducing a Comprehensive Dataset for Behavior Contrast

Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment

Data Collection-free Masked Video Modeling

Self-supervised visual learning from interactions with objects

Efficient Few-Shot Action Recognition via Multi-Level Post-Reasoning

Sequential Representation Learning via Static-Dynamic Conditional Disentanglement

Video Question Answering with Procedural Programs

ViLA: Efficient Video-Language Alignment for Video Question Answering

RAP: Retrieval-Augmented Planner for Adaptive Procedure Planning in Instructional Videos

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

Situated Instruction Following

WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language

LLaVA-UHD: an LMM Perceiving any Aspect Ratio and High-Resolution Images

Common Sense Reasoning for Deep Fake Detection

Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning

Conceptual Codebook Learning for Vision-Language Models

DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism

Do Generalised Classifiers really work on Human Drawn Sketches?

Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs

Discovering Unwritten Visual Classifiers with Large Language Models

Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction

LiteSAM is Actually what you Need for segment Everything

CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings

SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation

OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection

DECOLLAGE: 3D Detailization by Controllable, Localized, and Learned Geometry Enhancement

Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation

Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation

Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation

Shifted Autoencoders for Point Annotation Restoration in Object Counting

Rectify the Regression Bias in Long-Tailed Object Detection

Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning

Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation

Norma: A Noise Robust Memory-Augmented Framework for Whole Slide Image Classification

GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes

BugNIST - a Large Volumetric Dataset for Detection under Domain Shift

AD3: Introducing a score for Anomaly Detection Dataset Difficulty assessment using VIADUCT dataset

Unsupervised, Online and On-The-Fly Anomaly Detection For Non-Stationary Image Distributions

Robustness Tokens: Towards Adversarial Robustness of Transformers

Contribution-based Low-Rank Adaptation with Pre-training Model for Real Image Restoration

Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models

LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration

Improving Hyperbolic Representations via Gromov-Wasserstein Regularization

External Knowledge Enhanced 3D Scene Generation from Sketch

SCOD: From Heuristics to Theory

SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning

Forget More to Learn More: Domain-specific Feature Unlearning for Semi-supervised and Unsupervised Domain Adaptation

Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervision

Resilience of Entropy Model in Distributed Neural Networks

Generalized Coverage for More Robust Low-Budget Active Learning

Pick-a-back: Selective Device-to-Device Knowledge Transfer in Federated Continual Learning

UNIC: Universal Classification Models via Multi-teacher Distillation

Distributed Active Client Selection With Noisy Clients Using Model Association Scores

FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning

Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data

WBP: Training-time Backdoor Attacks through Hardware-based Weight Bit Poisoning

Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model

Anytime Continual Learning for Open Vocabulary Classification

COD: Learning Conditional Invariant Representation for Domain Adaptation Regression

On the Topology Awareness and Generalization Performance of Graph Neural Networks

Model Stock: All we need is just a few fine-tuned models

A Direct Approach to Viewing Graph Solvability

ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems

Gaussian Grouping: Segment and Edit Anything in 3D Scenes

Shape from Heat Conduction

PAV: Personalized Head Avatar from Unstructured Video Collection

NICP: Neural ICP for 3D Human Registration at Scale

High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering

Image Demoireing in RAW and sRGB Domains

Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopy

NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis

2S-ODIS: Two-Stage Omni-Directional Image Synthesis by Geometric Distortion Correction

Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimation

Look Around and Learn: Self-Training Object Detection by Exploration

6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model

EpipolarGAN: Omnidirectional Image Synthesis with Explicit Camera Control

Segmentation-guided Layer-wise Image Vectorization with Gradient Fills

Freeview Sketching: View-Aware Fine-Grained Sketch-Based Image Retrieval

Convex Relaxations for Manifold-Valued Markov Random Fields with Approximation Guarantees

Language-Driven Physics-Based Scene Synthesis and Editing via Feature Splatting

High-Fidelity Modeling of Generalizable Wrinkle Deformation

Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos

Seeing Faces in Things: A Model and Dataset for Pareidolia

Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder

ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistency

MAD-DR: Map Compression for Visual Localization with Matchness Aware Descriptor Dimension Reduction

Tensorial template matching for fast cross-correlation with rotations and its application for tomography

Hyperion – A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAM

SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views

CliffPhys: Camera-based Respiratory Measurement using Clifford Neural Networks

Image-to-Lidar Relational Distillation for Autonomous Driving Data

Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene

LetsMap: Unsupervised Representation Learning for Label-Efficient Semantic BEV Mapping

Learning to Drive via Asymmetric Self-Play

Event-based Mosaicing Bundle Adjustment

DIM: Dyadic Interaction Modeling for Social Behavior Generation

Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation

Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation

How Video Meetings Change Your Expression

Human Motion Forecasting in Dynamic Domain Shifts: A Homeostatic Continual Test-time Adaptation Framework

Towards Open Domain Text-Driven Synthesis of Multi-Person Motions

Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization

MegaScenes: Scene-Level View Synthesis at Scale

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

Idea2Img: Iterative Self-Refinement with GPT-4V for Automatic Image Design and Generation

Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

Robust-Wide: Robust Watermarking against Instruction-driven Image Editing

ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion

AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion

Towards Architecture-Agnostic Untrained Networks Priors for Image Reconstruction with Frequency Regularization

CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General INverse Problems

Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformations

Plug-and-Play Learned Proximal Trajectory for 3D Sparse-View X-Ray Computed Tomography

Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model

Spiking Wavelet Transformer

Finding a needle in a haystack: A Black-Box Approach to Invisible Watermark Detection

Noise-assisted Prompt Learning for Image Forgery Detection and Localization

Oulu Remote-photoplethysmography Physical Domain Attacks Database (ORPDAD)

Affine steerers for structured keypoint description

A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation

ZeroI2V: Zero-Cost Adaptation of Pre-Trained Transformers from Image to Video

SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow

Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localization

Two-Stage Active Learning for Efficient Temporal Action Segmentation

MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos

Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data

Text-Guided Video Masked Autoencoder

BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos

Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning

Uni3DL: A Unified Model for 3D Vision-Language Understanding

TrajPrompt: Aligning Color Trajectory with Vision-Language Representations

Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification

OmniSat: Self-Supervised Modality Fusion for Earth Observation

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

Generalizing to Unseen Domains via Text-guided Augmentation

R^2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations

Fully Authentic Visual Question Answering Dataset from Online Communities

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

Kalman-Inspired Feature Propagation for Video Face Super-Resolution

Diffusion-Guided Weakly Supervised Semantic Segmentation

Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs

Better Call SAL: Towards Learning to Segment Anything in Lidar

TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models

Plain-Det: A Plain Multi-Dataset Object Detector

PDT Uav Target Detection Dataset for Pests and Diseases Tree

FreeAugment: Data Augmentation Search Across All Degrees of Freedom

CC-SAM: Enhancing SAM with Cross-feature Attention and Context for Ultrasound Image Segmentation

Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model

MedRAT: Unpaired Medical Report Generation via Auxiliary Tasks

Learning Quantized Adaptive Conditions for Diffusion Models

BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge Distillation

FairViT: Fair Vision Transformer via Adaptive Masking

PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference

Dropout Mixture Low-Rank Adaptation for Visual Parameters-Efficient Fine-Tuning

Group Testing for Accurate and Efficient Range-Based Near Neighbor Search for Plagiarism Detection

Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration

An accurate detection is not all you need to combat label noise in web-noisy datasets

Integrating Markov Blanket Discovery into Causal Representation Learning for Domain Generalization

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay

CLEO: Continual Learning of Evolving Ontologies

Learning Representation for Multitask Learning through Self-Supervised Auxiliary Learning

CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching

Federated Learning with Local Openset Noisy Labels

Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents

Causal Subgraphs and Information Bottlenecks: Redefining OOD Robustness in Graph Neural Networks

Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks

Shedding More Light on Robust Classifiers under the lens of Energy-based Models

Inter-Class Topology Alignment for Efficient Black-Box Substitute Attacks

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

FedHide: Federated Learning by Hiding in the Neighbors