Detecting action tubes via spatial action estimation and temporal path inference

	Detecting action tubes via spatial action estimation and temporal path inference
	Li, Nannan; Huang, Jingjia; Li, Thomas; Guo, Huiwen; Li, Ge
刊名	NEUROCOMPUTING
	2018
文献子类	期刊论文
英文摘要	In this paper, we address the problem of action detection in unconstrained video clips. Our approach starts from action detection on object proposals at each frame, then aggregates the frame-level detection results belonging to the same actor across the whole video via linking, associating, and tracking to generate action tubes that are spatially compact and temporally continuous. To achieve the target, a novel action detection model with two-stream architecture is firstly proposed, which utilizes the fused feature from both appearance and motion cues and can be trained end-to-end. Then, the association of the action paths is formulated as a maximum set coverage problem with the results of action detection as a priori. We utilize an incremental search algorithm to obtain all the action proposals at one-pass operation with great efficiency, especially while dealing with the video of long duration or with multiple action instances. Finally, a tracking-by-detection scheme is designed to further refine the generated action paths. Extensive experiments on three validation datasets, UCF-Sports, UCF-101 and J-HMDB, show that the proposed approach advances state-of-the-art action detection performance in terms of both accuracy and proposal quality. (C) 2018 Elsevier B.V. All rights reserved.
URL标识	查看原文
语种	英语
内容类型	期刊论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/13671]
专题	深圳先进技术研究院_集成所
推荐引用方式 GB/T 7714	Li, Nannan,Huang, Jingjia,Li, Thomas,et al. Detecting action tubes via spatial action estimation and temporal path inference[J]. NEUROCOMPUTING,2018.
APA	Li, Nannan,Huang, Jingjia,Li, Thomas,Guo, Huiwen,&Li, Ge.(2018).Detecting action tubes via spatial action estimation and temporal path inference.NEUROCOMPUTING.
MLA	Li, Nannan,et al."Detecting action tubes via spatial action estimation and temporal path inference".NEUROCOMPUTING (2018).