STA-CNN: Convolutional Spatial-Temporal Attention Learning for Action Recognition

doi:10.1109/TIP.2020.2984904

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	STA-CNN: Convolutional Spatial-Temporal Attention Learning for Action Recognition
	Yang, Hao 1; Yuan, Chunfeng2 ; Zhang, Li 3; Sun, Yunda 1; Hu, Weiming4,5 ; Maybank, Stephen J.6
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2020
卷号	29 页码:5783-5793
通讯作者	Yang, Hao(yanghao1@nuctech.com)
摘要	Convolutional Neural Networks have achieved excellent successes for object recognition in still images. However, the improvement of Convolutional Neural Networks over the traditional methods for recognizing actions in videos is not so significant, because the raw videos usually have much more redundant or irrelevant information than still images. In this paper, we propose a Spatial-Temporal Attentive Convolutional Neural Network (STA-CNN) which selects the discriminative temporal segments and focuses on the informative spatial regions automatically. The STA-CNN model incorporates a Temporal Attention Mechanism and a Spatial Attention Mechanism into a unified convolutional network to recognize actions in videos. The novel Temporal Attention Mechanism automatically mines the discriminative temporal segments from long and noisy videos. The Spatial Attention Mechanism firstly exploits the instantaneous motion information in optical flow features to locate the motion salient regions and it is then trained by an auxiliary classification loss with a Global Average Pooling layer to focus on the discriminative non-motion regions in the video frame. The STA-CNN model achieves the state-of-the-art performance on two of the most challenging datasets, UCF-101 (95.8%) and HMDB-51 (71.5%).
关键词	Videos Feature extraction Motion segmentation Computational modeling Image recognition Solid modeling Convolutional neural networks Temporal attention spatial attention convolutional neural network action recognition
DOI	10.1109/TIP.2020.2984904
收录类别	SCI
语种	英语
资助项目	973 Basic Research Program of China[2014CB349303] ; Natural Science Foundation of China[U1636218] ; Natural Science Foundation of China[61472420] ; Natural Science Foundation of China[61472063] ; Natural Science Foundation of China[61370185] ; Natural Science Foundation of China[61472421] ; Natural Science Foundation of China[61672519] ; Natural Science Foundation of China[2017YFB1002801] ; Natural Science Foundation of China[61100099] ; Strategic Priority Research Program of Chinese Academy of Science[XDB02070003] ; Chinese Academy of Science External Cooperation Key Project
项目资助者	973 Basic Research Program of China ; Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Science ; Chinese Academy of Science External Cooperation Key Project
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000529943000018
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：50[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/39384
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Yang, Hao
作者单位	1.Nuctech Co Ltd, R&D Ctr Artificial Intelligent, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Tsinghua Univ, Dept Engn Phys, Beijing 100084, Peoples R China 4.Chinese Acad Sci, Natl Lab Pattern Recognit, Ctr Excellence Brain Sci & Intelligence Technol, Inst Automat, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 6.Univ London, Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
推荐引用方式 GB/T 7714	Yang, Hao,Yuan, Chunfeng,Zhang, Li,et al. STA-CNN: Convolutional Spatial-Temporal Attention Learning for Action Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:5783-5793.
APA	Yang, Hao,Yuan, Chunfeng,Zhang, Li,Sun, Yunda,Hu, Weiming,&Maybank, Stephen J..(2020).STA-CNN: Convolutional Spatial-Temporal Attention Learning for Action Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,5783-5793.
MLA	Yang, Hao,et al."STA-CNN: Convolutional Spatial-Temporal Attention Learning for Action Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):5783-5793.