Attentional Composition Networks for Long-Tailed Human Action Recognition

doi:10.1145/3603253

	Attentional Composition Networks for Long-Tailed Human Action Recognition
	Wang, Haoran 1; Wang, Yajie 1; Yu, Baosheng 2; Zhan, Yibing 3; Yuan, Chunfeng4 ; Yang, Wankou 5
发表期刊	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN	1551-6857
	2024
卷号	20 期号:1 页码:18
通讯作者	Wang, Haoran(wanghaoran@ise.neu.edu.cn)
摘要	The problem of long-tailed visual recognition has been receiving increasing research attention. However, the long-tailed distribution problem remains underexplored for video-based visual recognition. To address this issue, in this article we propose a compositional learning based solution for video-based human action recognition. Our method, named Attentional Composition Networks (ACN), first learns verb-like and prepositionlike components, then shuffles these components to generate samples for the tail classes in the feature space to augment the data for the tail classes. Specifically, during training, we represent each action video by a graph that captures the spatial-temporal relations (edges) among detected human/object instances (nodes). Then, ACN utilizes the position information to decompose each action into a set of verb and preposition representations using the edge features in the graph. After that, the verb and preposition features from different videos are combined via an attention structure to synthesize feature representations for tail classes. This way, we can enrich the data for the tail classes and consequently improve the action recognition for these classes. To evaluate the compositional human action recognition, we further contribute a new human action recognition dataset, namely NEU-Interaction (NEU-I). Experimental results on both Something-Something V2 and the proposed NEU-I demonstrate the effectiveness of the proposed method for long-tailed, few-shot, and zero-shot problems in human action recognition. Source code and the NEU-I dataset are available at https://github.com/YajieW99/ACN.
关键词	Compositional learning long tail few-shot zero-shot action recognition
DOI	10.1145/3603253
收录类别	SCI
语种	英语
资助项目	Major Science and Technology Innovation 2030 New Generation Artificial Intelligence key project[2021ZD0111700] ; Fundamental Research Funds for the Central Universities of China[N2304012] ; National Nature Science Foundation of China[61773117] ; National Nature Science Foundation of China[61972397] ; National Nature Science Foundation of China[62276061] ; National Nature Science Foundation of China[62002090]
项目资助者	Major Science and Technology Innovation 2030 New Generation Artificial Intelligence key project ; Fundamental Research Funds for the Central Universities of China ; National Nature Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:001080441800008
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：1[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/173211/52979
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Haoran
作者单位	1.Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Peoples R China 2.Univ Sydney, Sch Comp Sci, Fac Engn, Darlington, NSW 2008, Australia 3.JD Explore Acad, Beijing 100176, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 5.Southeast Univ, Sch Automat, Nanjing, Peoples R China
推荐引用方式 GB/T 7714	Wang, Haoran,Wang, Yajie,Yu, Baosheng,et al. Attentional Composition Networks for Long-Tailed Human Action Recognition[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2024,20(1):18.
APA	Wang, Haoran,Wang, Yajie,Yu, Baosheng,Zhan, Yibing,Yuan, Chunfeng,&Yang, Wankou.(2024).Attentional Composition Networks for Long-Tailed Human Action Recognition.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,20(1),18.
MLA	Wang, Haoran,et al."Attentional Composition Networks for Long-Tailed Human Action Recognition".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20.1(2024):18.