Saved in:
Bibliographic Details
Main Authors: Guan, Yiran, Chen, Zhuoguang, Zeng, Wenzheng, Cao, Zhiguo, Xiao, Yang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.18131
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913180945481728
author Guan, Yiran
Chen, Zhuoguang
Zeng, Wenzheng
Cao, Zhiguo
Xiao, Yang
author_facet Guan, Yiran
Chen, Zhuoguang
Zeng, Wenzheng
Cao, Zhiguo
Xiao, Yang
contents In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), to facilitate video gaze estimation via capturing spatial-temporal interaction context among head, face, and eye in an end-to-end learning way, which has not been well concerned yet. The main advantage of MCGaze is that the tasks of clue localization of head, face, and eye can be solved jointly for gaze estimation in a one-step way, with joint optimization to seek optimal performance. During this, spatial-temporal context exchange happens among the clues on the head, face, and eye. Accordingly, the final gazes obtained by fusing features from various queries can be aware of global clues from heads and faces, and local clues from eyes simultaneously, which essentially leverages performance. Meanwhile, the one-step running way also ensures high running efficiency. Experiments on the challenging Gaze360 dataset verify the superiority of our proposition. The source code will be released at https://github.com/zgchen33/MCGaze.
format Preprint
id arxiv_https___arxiv_org_abs_2310_18131
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context
Guan, Yiran
Chen, Zhuoguang
Zeng, Wenzheng
Cao, Zhiguo
Xiao, Yang
Computer Vision and Pattern Recognition
In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), to facilitate video gaze estimation via capturing spatial-temporal interaction context among head, face, and eye in an end-to-end learning way, which has not been well concerned yet. The main advantage of MCGaze is that the tasks of clue localization of head, face, and eye can be solved jointly for gaze estimation in a one-step way, with joint optimization to seek optimal performance. During this, spatial-temporal context exchange happens among the clues on the head, face, and eye. Accordingly, the final gazes obtained by fusing features from various queries can be aware of global clues from heads and faces, and local clues from eyes simultaneously, which essentially leverages performance. Meanwhile, the one-step running way also ensures high running efficiency. Experiments on the challenging Gaze360 dataset verify the superiority of our proposition. The source code will be released at https://github.com/zgchen33/MCGaze.
title End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.18131