Learning Dual-Pooling Graph Neural Networks for Few-Shot Video Classification | |
Hu, Yufan3,4; Gao, Junyu1,2,3; Xu, Changsheng1,2,3 | |
刊名 | IEEE TRANSACTIONS ON MULTIMEDIA |
2021 | |
卷号 | 23页码:4285-4296 |
关键词 | Task analysis Feature extraction Training Testing Streaming media Data models Semantics Few-shot learning graph neural networks video classification |
ISSN号 | 1520-9210 |
DOI | 10.1109/TMM.2020.3039329 |
通讯作者 | Xu, Changsheng(csxu@nlpr.ia.ac.cn) |
英文摘要 | 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. |
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] |
WOS关键词 | RECOGNITION |
WOS研究方向 | Computer Science ; Telecommunications |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000720519900029 |
资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences of CAS |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/46476] |
专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
通讯作者 | Xu, Changsheng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100864, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China 4.Hefei Univ Technol, Hefei 230009, Peoples R China |
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. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论