Adaptive learning codebook for action recognition

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Adaptive learning codebook for action recognition
	Kong, Yu 1,2; Zhang, Xiaoqin 2; Hu, Weiming2 ; Jia, Yunde 1
发表期刊	PATTERN RECOGNITION LETTERS
	2011-06-01
卷号	32 期号:8 页码:1178-1186
文章类型	Article
摘要	Learning a compact and yet discriminative codebook is an important procedure for local feature-based action recognition. A common procedure involves two independent phases: reducing the dimensionality of local features and then performing clustering. Since the two phases are disconnected, dimensionality reduction does not necessarily capture the dimensions that are greatly helpful for codebook creation. What's more, some dimensionality reduction techniques such as the principal component analysis do not take class separability into account and thus may not help build an effective codebook. In this paper, we propose the weighted adaptive metric learning (WAML) which integrates the two independent phases into a unified optimization framework. This framework enables to select indispensable and crucial dimensions for building a discriminative codebook. The dimensionality reduction phase in the WAML is optimized for class separability and adaptively adjusts the distance metric to improve the separability of data. In addition, the video word weighting is smoothly incorporated into the WAML to accurately generate video words. Experimental results demonstrate that our approach builds a highly discriminative codebook and achieves comparable results to other state-of-the-art approaches. (C) 2011 Elsevier B.V. All rights reserved.
关键词	Action Recognition Visual Codebook Metric Learning
WOS标题词	Science & Technology ; Technology
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:000290745100011
引用统计	被引频次：19[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/173211/3245
专题	多模态人工智能系统全国重点实验室_视频内容安全
作者单位	1.Beijing Inst Technol, Sch Comp Sci, Beijing Lab Intelligent Informat Technol, Beijing 100081, Peoples R China 2.Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
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	Kong, Yu,Zhang, Xiaoqin,Hu, Weiming,et al. Adaptive learning codebook for action recognition[J]. PATTERN RECOGNITION LETTERS,2011,32(8):1178-1186.
APA	Kong, Yu,Zhang, Xiaoqin,Hu, Weiming,&Jia, Yunde.(2011).Adaptive learning codebook for action recognition.PATTERN RECOGNITION LETTERS,32(8),1178-1186.
MLA	Kong, Yu,et al."Adaptive learning codebook for action recognition".PATTERN RECOGNITION LETTERS 32.8(2011):1178-1186.