Skip to yearly menu bar Skip to main content


Poster

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

Pengwei Yin · Jingjing Wang · Guanzhong Zeng · Di Xie · Jiang Zhu

Strong blind review: This paper was not made available on public preprint services during the review process Strong Double Blind
[ ]
Tue 1 Oct 7:30 a.m. PDT — 9:30 a.m. PDT

Abstract:

The ability of gaze estimation models to generalize is often significantly hindered by various factors unrelated to gaze, especially when the training dataset is limited. Current strategies aim to address this challenge through different domain generalization techniques, yet they have had limited success due to the risk of overfitting when solely relying on value labels for regression. Recent progress in pre-trained vision-language models has motivated us to capitalize on the abundant semantic information available. We propose a novel approach in this paper, reframing the gaze estimation task as a vision-language alignment issue. Our proposed framework, named Language-Guided Gaze Estimation (LG-Gaze), learns continuous and geometry-sensitive features for gaze estimation benefit from the rich prior knowledges of vision-language models. Specifically, LG-Gaze aligns gaze features with continuous linguistic features through our proposed multimodal contrastive regression loss, which customizes adaptive weights for different negative samples. Furthermore, to better adapt to the labels for gaze estimation task, we propose a geometry-aware interpolation method to obtain more precise gaze embeddings. Through extensive experiments, we validate the efficacy of our framework in four different cross-domain evaluation tasks.

Live content is unavailable. Log in and register to view live content