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. 复杂系统认知与决策实验室
  5. 类脑芯片与系统研究
SAPS: Self-Attentive Pathway Search for weakly-supervised action localization with-action

文献类型：期刊论文

作者Zhang, Xiao-Yu1; Zhang, Yaru1,2; Shi, Haichao1,2; Dong, Jing3
刊名COMPUTER VISION AND IMAGE UNDERSTANDING
出版日期2021-09-01
卷号210页码:9
关键词Video understanding Action localization Representation learning Neural architecture search Background modeling
ISSN号1077-3142
DOI10.1016/j.cviu.2021.103256
通讯作者Zhang, Xiao-Yu(zhangxiaoyu@iie.ac.cn)
英文摘要Weakly supervised temporal action localization is a challenging computer vision task, which aims to derive frame-level action identifier based on video-level supervision. Attention mechanism is a widely used paradigm for action recognition and localization in most recent methods. However, existing attention-based methods mostly focus on capturing the global dependency of the frame sequence regardless of the local inter-frame distances. Moreover, during background modeling, different background contents are typically classified into one category, which inevitably jeopardizes the discriminative ability of classifiers and brings about irrelevant noise. In this paper, we present a novel self-attentive pathway search framework, namely SAPS, to address the above challenges. To achieve comprehensive representation with discriminative attention weights, we design a NAS-based attentive module with a path-level searching process, and construct a competitive attention structure revealing both local and global dependency. Furthermore, we propose the action-related background modeling for robust background-action augmentation, where knowledge derived from background can provide informative clues for action recognition. An ensemble T-CAM operation is subsequently designed to incorporate background information to further refine the temporal action localization results. Extensive experiments on two benchmark datasets (i.e., THUMOS14 and ActivityNet1.2) have clearly corroborated the efficacy of our method.
WOS关键词ACTION RECOGNITION ; OPTIMIZATION
资助项目National Natural Science Foundation of China[U2003111] ; National Natural Science Foundation of China[61871378]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000691812700004
出版者ACADEMIC PRESS INC ELSEVIER SCIENCE
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/45941]  
专题类脑芯片与系统研究
通讯作者Zhang, Xiao-Yu
作者单位1.Chinese Acad Sci, Inst Informat Engn, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Xiao-Yu,Zhang, Yaru,Shi, Haichao,et al. SAPS: Self-Attentive Pathway Search for weakly-supervised action localization with-action[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2021,210:9.
APA Zhang, Xiao-Yu,Zhang, Yaru,Shi, Haichao,&Dong, Jing.(2021).SAPS: Self-Attentive Pathway Search for weakly-supervised action localization with-action.COMPUTER VISION AND IMAGE UNDERSTANDING,210,9.
MLA Zhang, Xiao-Yu,et al."SAPS: Self-Attentive Pathway Search for weakly-supervised action localization with-action".COMPUTER VISION AND IMAGE UNDERSTANDING 210(2021):9.

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。