no code implementations • 8 Mar 2024 • Pengwei Yin, Guanzhong Zeng, Jingjing Wang, Di Xie
To overcome these limitations, we propose a novel framework called CLIP-Gaze that utilizes a pre-trained vision-language model to leverage its transferable knowledge.
no code implementations • 30 Dec 2022 • Pengwei Yin, Jiawu Dai, Jingjing Wang, Di Xie, ShiLiang Pu
Gaze estimation is the fundamental basis for many visual tasks.