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

doi:10.1016/j.patcog.2022.108797

	Identifying the key frames: An attention-aware sampling method for action recognition
	Dong, Wenkai1,2,4 ; Zhang, Zhaoxiang1,2,3,4 ; Song, Chunfeng1,2,4 ; Tan, Tieniu1,2,4
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2022-10-01
卷号	130 页码:11
通讯作者	Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
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.
关键词	Action recognition Deep learning Reinforcement learning Pseudo labels
DOI	10.1016/j.patcog.2022.108797
关键词[WOS]	NETWORK
收录类别	SCI
语种	英语
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
项目资助者	Major Project for New Generation of AI ; National Natural Science Foundation of China ; National Youth Talent Support Program
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001027089400007
出版者	ELSEVIER SCI LTD
引用统计	被引频次：7[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/173211/53670
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 CASIA, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci UCAS, Beijing, Peoples R China 3.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, HKISI, Beijing, Peoples R China 4.Natl Lab Pattern Recognit NLPR, Beijing, Peoples R China
第一作者单位	中国科学院自动化研究所; 模式识别国家重点实验室
通讯作者单位	中国科学院自动化研究所; 模式识别国家重点实验室
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.