Believe It or Not, We Know What You Are Looking At!

doi:10.1007/978-3-030-20893-6_3

	Believe It or Not, We Know What You Are Looking At!
	Lian, Dongze; Yu, Zehao; Gao, Shenghua
	2019
会议录名称	LECTURE NOTES IN COMPUTER SCIENCE (IF:0.402[JCR-2005],0.000[5-Year])
ISSN	0302-9743
卷号	11363
页码	35-50
发表状态	已发表
DOI	10.1007/978-3-030-20893-6_3
摘要	By borrowing the wisdom of human in gaze following, we propose a two-stage solution for gaze point prediction of the target persons in a scene. Specifically, in the first stage, both head image and its position are fed into a gaze direction pathway to predict the gaze direction, and then multi-scale gaze direction fields are generated to characterize the distribution of gaze points without considering the scene contents. In the second stage, the multi-scale gaze direction fields are concatenated with the image contents and fed into a heatmap pathway for heatmap regression. There are two merits for our two-stage solution based gaze following: (i) our solution mimics the behavior of human in gaze following, therefore it is more psychological plausible; (ii) besides using heatmap to supervise the output of our network, we can also leverage gaze direction to facilitate the training of gaze direction pathway, therefore our network can be more robustly trained. Considering that existing gaze following dataset is annotated by the third-view persons, we build a video gaze following dataset, where the ground truth is annotated by the observers in the videos. Therefore it is more reliable. The evaluation with such a dataset reflects the capacity of different methods in real scenarios better. Extensive experiments on both datasets show that our method significantly outperforms existing methods, which validates the effectiveness of our solution for gaze following.
关键词	Gaze following Saliency Multi-scale gaze direction fields
会议名称	Asian Conference on Computer Vision
收录类别	EI ; CPCI-S ; CPCI
语种	英语
资助项目	NSFC[61502304]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000492903100003
出版者	SPRINGER INTERNATIONAL PUBLISHING AG
EI入藏号	20192507061254
EI主题词	Behavioral research
EISSN	1611-3349
EI分类号	Computer Applications:723.5 ; Social Sciences:971
WOS关键词	MODEL
原始文献类型	Proceedings Paper
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29130
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_高盛华组
通讯作者	Gao, Shenghua
作者单位	School of Information Science and Technology, ShanghaiTech University, Shanghai, China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Lian, Dongze,Yu, Zehao,Gao, Shenghua. Believe It or Not, We Know What You Are Looking At![C]:SPRINGER INTERNATIONAL PUBLISHING AG,2019:35-50.