Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation

arXiv:2404.05215v1 Announce Type: new
Abstract: Gaze is an essential prompt for analyzing human behavior and attention. Recently, there has been an increasing interest in determining gaze direction from facial videos. However, video gaze estimation faces significant challenges, such as understanding the dynamic evolution of gaze in video sequences, dealing with static backgrounds, and adapting to variations in illumination. To address these challenges, we propose a simple and novel deep learning model designed to estimate gaze from videos, incorporating a specialized …

arxiv attention cs.cv gaussian processes personalized processes temporal type video