Dense Trajectories and Motion Boundary Descriptors for Action Recognition

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Dense Trajectories and Motion Boundary Descriptors for Action Recognition
	Wang, Heng 1; Klaeser, Alexander 2; Schmid, Cordelia 2; Liu, Cheng-Lin1
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2013-05-01
卷号	103 期号:1 页码:60-79
文章类型	Article
摘要	This paper introduces a video representation based on dense trajectories and motion boundary descriptors. Trajectories capture the local motion information of the video. A dense representation guarantees a good coverage of foreground motion as well as of the surrounding context. A state-of-the-art optical flow algorithm enables a robust and efficient extraction of dense trajectories. As descriptors we extract features aligned with the trajectories to characterize shape (point coordinates), appearance (histograms of oriented gradients) and motion (histograms of optical flow). Additionally, we introduce a descriptor based on motion boundary histograms (MBH) which rely on differential optical flow. The MBH descriptor shows to consistently outperform other state-of-the-art descriptors, in particular on real-world videos that contain a significant amount of camera motion. We evaluate our video representation in the context of action classification on nine datasets, namely KTH, YouTube, Hollywood2, UCF sports, IXMAS, UIUC, Olympic Sports, UCF50 and HMDB51. On all datasets our approach outperforms current state-of-the-art results.
关键词	Action Recognition Dense Trajectories Motion Boundary Histograms
WOS标题词	Science & Technology ; Technology
关键词[WOS]	OBJECT TRAJECTORIES ; FEATURES ; VIDEO ; CLASSIFICATION ; TEXTURE ; SCALE
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000318413500003
引用统计	被引频次：1163[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/173211/3075
专题	多模态人工智能系统全国重点实验室_模式分析与学习
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.INRIA Grenoble Rhone Alpes, LEAR Team, F-38330 Montbonnot St Martin, France
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang, Heng,Klaeser, Alexander,Schmid, Cordelia,et al. Dense Trajectories and Motion Boundary Descriptors for Action Recognition[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2013,103(1):60-79.
APA	Wang, Heng,Klaeser, Alexander,Schmid, Cordelia,&Liu, Cheng-Lin.(2013).Dense Trajectories and Motion Boundary Descriptors for Action Recognition.INTERNATIONAL JOURNAL OF COMPUTER VISION,103(1),60-79.
MLA	Wang, Heng,et al."Dense Trajectories and Motion Boundary Descriptors for Action Recognition".INTERNATIONAL JOURNAL OF COMPUTER VISION 103.1(2013):60-79.