STRNet: Triple-stream Spatiotemporal Relation Network for Action Recognition

doi:10.1007/s11633-021-1289-9

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

	STRNet: Triple-stream Spatiotemporal Relation Network for Action Recognition
	Zhi-Wei Xu 1,2
刊名	International Journal of Automation and Computing
	2021
卷号	18 期号:5 页码:718-730
关键词	Action recognition spatiotemporal relation multi-branch fusion long-term representation video classification
ISSN号	1476-8186
DOI	10.1007/s11633-021-1289-9
英文摘要	Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network (ARTNet) and spatiotemporal and motion network (STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network (STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches, which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45459]
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 Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China 2.Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Wuxi 214122, China 3.Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, UK
推荐引用方式 GB/T 7714	Zhi-Wei Xu. STRNet: Triple-stream Spatiotemporal Relation Network for Action Recognition[J]. International Journal of Automation and Computing,2021,18(5):718-730.
APA	Zhi-Wei Xu.(2021).STRNet: Triple-stream Spatiotemporal Relation Network for Action Recognition.International Journal of Automation and Computing,18(5),718-730.
MLA	Zhi-Wei Xu."STRNet: Triple-stream Spatiotemporal Relation Network for Action Recognition".International Journal of Automation and Computing 18.5(2021):718-730.