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

doi:10.1007/s11633-022-1333-4

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization
	Xiao-Yu Zhang 3
刊名	Machine Intelligence Research
	2022
卷号	19 页码:227-246
关键词	Knowledge transfer weakly supervised learning self-attention mechanism representation learning action localization
ISSN号	2731-538X
DOI	10.1007/s11633-022-1333-4
英文摘要	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.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48809]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	1.School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China 2.School of Computer Science, Beijing Institute of Technology, Beijing 100081, China 3.Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China
推荐引用方式 GB/T 7714	Xiao-Yu Zhang. TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization[J]. Machine Intelligence Research,2022,19:227-246.
APA	Xiao-Yu Zhang.(2022).TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization.Machine Intelligence Research,19,227-246.
MLA	Xiao-Yu Zhang."TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization".Machine Intelligence Research 19(2022):227-246.