中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
STA-CNN: Convolutional Spatial-Temporal Attention Learning for Action Recognition

文献类型：期刊论文

作者Yang, Hao1; Yuan, Chunfeng6; Zhang, Li2; Sun, Yunda1; Hu, Weiming3,4; Maybank, Stephen J.5
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2020
卷号29页码:5783-5793
ISSN号1057-7149
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
DOI10.1109/TIP.2020.2984904
通讯作者Yang, Hao(yanghao1@nuctech.com)
英文摘要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%).
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
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000529943000018
资助机构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
源URL[http://ir.ia.ac.cn/handle/173211/39383]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
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.Tsinghua Univ, Dept Engn Phys, Beijing 100084, Peoples R China
3.Chinese Acad Sci, Natl Lab Pattern Recognit, Ctr Excellence Brain Sci & Intelligence Technol, Inst Automat, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
5.Univ London, Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
6.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。