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
Identifying the key frames: An attention-aware sampling method for action recognition

文献类型：期刊论文

作者Dong, Wenkai2,3,4; Zhang, Zhaoxiang1,2,3,4; Song, Chunfeng2,3,4; Tan, Tieniu2,3,4
刊名PATTERN RECOGNITION
出版日期2022-10-01
卷号130页码:11
ISSN号0031-3203
关键词Action recognition Deep learning Reinforcement learning Pseudo labels
DOI10.1016/j.patcog.2022.108797
通讯作者Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要Deep learning based methods have achieved remarkable progress in action recognition. Existing works mainly focus on designing novel deep architectures to learn video representations for action recognition. Most existing methods treat sampled frames equally and average all the frame-level predictions to generate video-level predictions at the testing stage. However, within a video, discriminative actions may occur sparsely in a few frames whereas most other frames are irrelevant to the ground truth which may even lead to wrong results. As a result, we think that the strategy of selecting relevant frames would be a further important key to enhance the existing deep learning based action recognition. In this paper, we propose an attention-aware sampling method for action recognition, which aims to discard the irrelevant and misleading frames and preserve the most discriminative frames. We formulate the process of mining key frames from videos as a Markov decision process and train the attention agent through deep reinforcement learning without extra labels. The agent takes features and predictions from the baseline model as inputs and generates importance scores for all frames. Moreover, our approach is extensible, which can be applied to different existing deep learning based action recognition models. We achieve very competitive action recognition performance on two widely used action recognition datasets. (c) 2022 Elsevier Ltd. All rights reserved.
WOS关键词NETWORK
资助项目Major Project for New Generation of AI[2018AAA0100400] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62006231] ; National Natural Science Foundation of China[62072457] ; National Youth Talent Support Program
WOS研究方向Computer Science ; Engineering
语种英语
出版者ELSEVIER SCI LTD
WOS记录号WOS:001027089400007
资助机构Major Project for New Generation of AI ; National Natural Science Foundation of China ; National Youth Talent Support Program
源URL[http://ir.ia.ac.cn/handle/173211/53669]  
专题多模态人工智能系统全国重点实验室
通讯作者Zhang, Zhaoxiang
作者单位1.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, HKISI, Beijing, Peoples R China
2.Chinese Acad Sci CASIA, Inst Automat, Beijing, Peoples R China
3.Univ Chinese Acad Sci UCAS, Beijing, Peoples R China
4.Natl Lab Pattern Recognit NLPR, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Dong, Wenkai,Zhang, Zhaoxiang,Song, Chunfeng,et al. Identifying the key frames: An attention-aware sampling method for action recognition[J]. PATTERN RECOGNITION,2022,130:11.
APA Dong, Wenkai,Zhang, Zhaoxiang,Song, Chunfeng,&Tan, Tieniu.(2022).Identifying the key frames: An attention-aware sampling method for action recognition.PATTERN RECOGNITION,130,11.
MLA Dong, Wenkai,et al."Identifying the key frames: An attention-aware sampling method for action recognition".PATTERN RECOGNITION 130(2022):11.

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。