Learning Dual-Pooling Graph Neural Networks for Few-Shot Video Classification

doi:10.1109/TMM.2020.3039329

	Learning Dual-Pooling Graph Neural Networks for Few-Shot Video Classification
	Hu, Yufan 1,2; Gao, Junyu2,3,4 ; Xu, Changsheng2,3,4
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2021
卷号	23 页码:4285-4296
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
摘要	We address the problem of few-shot video classification that learns classifiers for novel concepts from only a few examples. Most current methods ignore to explicitly consider the relations in both intra-video and inter-video domains, thus cannot take full advantage of the structural information in few-shot learning. In this paper, we propose to exploit the comprehensive intra-video and inter-video relations via Graph Neural Networks (GNNs). To improve the discriminative ability for accurately selecting the representative video content and refining video relations, a Dual-Pooling GNN (DPGNN) is constructed, which stacks customized graph pooling layers in a hierarchical fashion. Specifically, to select the most representative frames in a video, we build intra-video graphs and utilize a node pooling module to extract robust video-level features. We construct an inter-video graph by taking the video-level features as nodes. By designing an edge pooling module, the proposed method can adaptively eliminate the negative relations in the inter-video graph. Extensive experimental results show that our method consistently outperforms the state-of-the-art on two benchmarks.
关键词	Task analysis Feature extraction Training Testing Streaming media Data models Semantics Few-shot learning graph neural networks video classification
DOI	10.1109/TMM.2020.3039329
关键词[WOS]	RECOGNITION
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0100604] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[6207245561721004] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61702511] ; National Natural Science Foundation of China[61751211] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61872424] ; Key Research Program of Frontier Sciences of CAS[QYZDJSSWJSC039]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences of CAS
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000720519900029
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：19[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/173211/46477
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Xu, Changsheng
作者单位	1.Hefei Univ Technol, Hefei 230009, Peoples R China 2.Peng Cheng Lab, Shenzhen 518055, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100864, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Hu, Yufan,Gao, Junyu,Xu, Changsheng. Learning Dual-Pooling Graph Neural Networks for Few-Shot Video Classification[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021,23:4285-4296.
APA	Hu, Yufan,Gao, Junyu,&Xu, Changsheng.(2021).Learning Dual-Pooling Graph Neural Networks for Few-Shot Video Classification.IEEE TRANSACTIONS ON MULTIMEDIA,23,4285-4296.
MLA	Hu, Yufan,et al."Learning Dual-Pooling Graph Neural Networks for Few-Shot Video Classification".IEEE TRANSACTIONS ON MULTIMEDIA 23(2021):4285-4296.