Predicting Salient Face in Multiple-face Videos

doi:10.1109/CVPR.2017.343

	Predicting Salient Face in Multiple-face Videos
	Liu, Yufan 1; Zhang, Songyang1,2 ; Xu, Mai 1; He, Xuming2
	2017
会议录名称	30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
ISSN	1063-6919
卷号	2017-January
页码	3224-3232
发表状态	已发表
DOI	10.1109/CVPR.2017.343
摘要	Although the recent success of convolutional neural network (CNN) advances state-of-the-art saliency prediction in static images, few work has addressed the problem of predicting attention in videos. On the other hand, we nd that the attention of different subjects consistently focuses on a single face in each frame of videos involving multiple faces. Therefore, we propose in this paper a novel deep learning (DL) based method to predict salient face in multiple-face videos, which is capable of learning features and transition of salient faces across video frames. In particular, we rst learn a CNN for each frame to locate salient face. Taking CNN features as input, we develop a multiple-stream long short-term memory (M-LSTM) network to predict the temporal transition of salient faces in video sequences. To evaluate our DL-based method, we build a new eye-tracking database of multiple-face videos. The experimental results show that our method outperforms the prior state-of-the-art methods in predicting visual attention on faces in multipleface videos.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Honolulu, HI, United states
会议日期	21-26 July 2017
URL	查看原文
收录类别	CPCI ; EI
语种	英语
资助项目	Fok Ying-Tong education foundation[151061]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000418371403032
出版者	IEEE
EI入藏号	20181304947391
EI主题词	Behavioral research ; Computer vision ; Deep learning ; Eye tracking ; Forecasting ; Neural networks ; Pattern recognition
EI分类号	Computer Applications:723.5 ; Social Sciences:971
WOS关键词	MODEL
原始文献类型	Proceedings Paper
来源库	IEEE
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/16321
专题	信息科学与技术学院信息科学与技术学院_PI研究组_何旭明组信息科学与技术学院_硕士生信息科学与技术学院_博士生
通讯作者	Xu, Mai
作者单位	1.Beihang Univ, Beijing, Peoples R China 2.ShanghaiTech Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Liu, Yufan,Zhang, Songyang,Xu, Mai,et al. Predicting Salient Face in Multiple-face Videos[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:3224-3232.