Adaptive Slice Representation for Human Action Classification

doi:10.1109/TCSVT.2014.2376136

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

	Adaptive Slice Representation for Human Action Classification
	Shan, Yanhu; Zhang, Zhang; Yang, Peipei; Huang, Kaiqi; Kaiqi Huang
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2015-10-01
卷号	25 期号:10 页码:1624-1636
文章类型	Article
摘要	Common action recognition methods describe an action sequence along with its time axis, i.e., first extracting features from the x y plane, and then modeling the dynamic changes along with the time axis. Other than the ordinary x y plane-based representation, other views, e.g., xt slice-based representation, may be more efficient to distinguish different actions. In this paper, we investigate different slicing views of the spatiotemporal volume to organize action sequences and propose an efficient slice representation for human action recognition. First, a minimum average entropy principle is proposed to select the optimal slicing angle for each action sequence adaptively. This allows the foreground pixels to be distributed in the fewest slices so as to reduce more uncertainty caused by the information dispersed in different slices. Then, the obtained slice sequence is transformed into a pair of 1-D signals to describe the distribution of foreground pixels along the time axis. Finally, the mel frequency cepstrum coefficient features are calculated to describe the spectrum characteristics of the 1-D signals over time. Thus, a 3-D spatiotemporal action volume is efficiently transformed into a low-dimensional spectrum features. Extensive experiments on the 2-D human action data sets (the UIUC and the WEIZ-MANN) as well as the Microsoft Research (MSR) Action3-D depth data set demonstrate the effectiveness of the slice-based representation, where the recognition performance can reach to the state-of-the-art level with high efficiency.
关键词	Action Recognition Adaptive Slice Mel Frequency Cepstrum Coefficient (Mfcc) Minimum Average Entropy (Minae)
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCSVT.2014.2376136
关键词[WOS]	ACTION RECOGNITION ; BEHAVIOR ANALYSIS ; MOTION ; DESCRIPTORS ; TRACKING ; DENSE
收录类别	SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000362358300006
引用统计	被引频次：8[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/173211/10037
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
通讯作者	Kaiqi Huang
作者单位	Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, 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	Shan, Yanhu,Zhang, Zhang,Yang, Peipei,et al. Adaptive Slice Representation for Human Action Classification[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2015,25(10):1624-1636.
APA	Shan, Yanhu,Zhang, Zhang,Yang, Peipei,Huang, Kaiqi,&Kaiqi Huang.(2015).Adaptive Slice Representation for Human Action Classification.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,25(10),1624-1636.
MLA	Shan, Yanhu,et al."Adaptive Slice Representation for Human Action Classification".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 25.10(2015):1624-1636.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
06967815.pdf（2720KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载