TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization

doi:10.1007/s11633-022-1333-4

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization
	Xiao-Yu Zhang 1; Hai-Chao Shi 1; Chang-Sheng Li 2; Li-Xin Duan 3
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2022
卷号	19 期号:3 页码:227-246
摘要	Action recognition and localization in untrimmed videos is important for many applications and have attracted a lot of attention. Since full supervision with frame-level annotation places an overwhelming burden on manual labeling effort, learning with weak video-level supervision becomes a potential solution. In this paper, we propose a novel weakly supervised framework to recognize actions and locate the corresponding frames in untrimmed videos simultaneously. Considering that there are abundant trimmed videos publicly available and well-segmented with semantic descriptions, the instructive knowledge learned on trimmed videos can be fully leveraged to analyze untrimmed videos. We present an effective knowledge transfer strategy based on inter-class semantic relevance. We also take advantage of the self-attention mechanism to obtain a compact video representation, such that the influence of background frames can be effectively eliminated. A learning architecture is designed with twin networks for trimmed and untrimmed videos, to facilitate transferable self-attentive representation learning. Extensive experiments are conducted on three untrimmed benchmark datasets (i.e., THUMOS14, ActivityNet1.3, and MEXaction2), and the experimental results clearly corroborate the efficacy of our method. It is especially encouraging to see that the proposed weakly supervised method even achieves comparable results to some fully supervised methods.
关键词	Knowledge transfer weakly supervised learning self-attention mechanism representation learning action localization
DOI	10.1007/s11633-022-1333-4
引用统计	被引频次：5[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/173211/55943
专题	学术期刊_Machine Intelligence Research
作者单位	1.Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China 2.School of Computer Science, Beijing Institute of Technology, Beijing 100081, China 3.School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
推荐引用方式 GB/T 7714	Xiao-Yu Zhang,Hai-Chao Shi,Chang-Sheng Li,et al. TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization[J]. Machine Intelligence Research,2022,19(3):227-246.
APA	Xiao-Yu Zhang,Hai-Chao Shi,Chang-Sheng Li,&Li-Xin Duan.(2022).TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization.Machine Intelligence Research,19(3),227-246.
MLA	Xiao-Yu Zhang,et al."TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization".Machine Intelligence Research 19.3(2022):227-246.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-01-022.pdf（3616KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载