QQ客服 官方微博 反馈留言

	Video Action Detection with Relational Dynamic-Poselets
	Limin Wang; Yu Qiao; Xiaoou Tang
	2014
会议名称	13th European Conference on Computer Vision (ECCV)
会议地点	瑞士
英文摘要	Action detection is of great importance in understanding human motion from video. Compared with action recognition, it not only recognizes action type, but also localizes its spatiotemporal extent. This paper presents a relational model for action detection, which first decomposes human action into temporal “key poses” and then further into spatial “action parts”. Specifically, we start by clustering cuboids around each human joint into dynamic-poselets using a new descrip- tor. The cuboids from the same cluster share consistent geometric and dynamic structure, and each cluster acts as a mixture of body parts. We then propose a sequential skeleton model to capture the relations among dynamic-poselets. This model unifies the tasks of learning the composites of mixture dynamic-poselets, the spatiotemporal structures of action parts, and the local model for each action part in a single frame- work. Our model not only allows to localize the action in a video stream, but also enables a detailed pose estimation of an actor. We formulate the model learning problem in a structured SVM framework and speed up model inference by dynamic programming. We conduct experiments on three challenging action detection datasets: the MSR-II dataset, the UCF Sports dataset, and the JHMDB dataset. The results show that our method achieves superior performance to the state-of-the-art methods on these datasets.
收录类别	EI
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/5514]
专题	深圳先进技术研究院_集成所
作者单位	2014
推荐引用方式 GB/T 7714	Limin Wang,Yu Qiao,Xiaoou Tang. Video Action Detection with Relational Dynamic-Poselets[C]. 见:13th European Conference on Computer Vision (ECCV). 瑞士.

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。