Modeling Interactions between Low-Level and High-Level Features for Human Action Recognition

doi:10.1587/transinf.E96.D.2896

CASIA OpenIR > 复杂系统管理与控制国家重点实验室 > 影像分析与机器视觉

	Modeling Interactions between Low-Level and High-Level Features for Human Action Recognition
	Zhou, Wen; Wang, Chunheng; Xiao, Baihua; Zhang, Zhong; Shao, Yunxue
发表期刊	IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
	2013-12-01
卷号	E96D 期号:12 页码:2896-2899
文章类型	Article
摘要	Recognizing human action in complex scenes is a challenging problem in computer vision. Some action-unrelated concepts, such as camera position features, could significantly affect the appearance of local spatio-temporal features, and therefore the performance of low-level features based methods degrades. In this letter, we define the action-unrelated concept: the position of camera as high-level features. We observe that they can serve as a prior to local spatio-temporal features for human action recognition. We encode this prior by modeling interactions between spatio-temporal features and camera position features. We infer camera position features from local spatio-temporal features via these interactions. The parameters of this model are estimated by a new max-margin algorithm. We evaluate the proposed method on KTH, IXMAS and Youtube actions datasets. Experimental results show the effectiveness of the proposed method.
关键词	Action Recognition Camera Position Features Local Spatio-temporal Features Interactions
WOS标题词	Science & Technology ; Technology
DOI	10.1587/transinf.E96.D.2896
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000329009300048
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/3752
专题	复杂系统管理与控制国家重点实验室_影像分析与机器视觉
作者单位	Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100864, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhou, Wen,Wang, Chunheng,Xiao, Baihua,et al. Modeling Interactions between Low-Level and High-Level Features for Human Action Recognition[J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,2013,E96D(12):2896-2899.
APA	Zhou, Wen,Wang, Chunheng,Xiao, Baihua,Zhang, Zhong,&Shao, Yunxue.(2013).Modeling Interactions between Low-Level and High-Level Features for Human Action Recognition.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,E96D(12),2896-2899.
MLA	Zhou, Wen,et al."Modeling Interactions between Low-Level and High-Level Features for Human Action Recognition".IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E96D.12(2013):2896-2899.