Human activity prediction using temporally-weighted generalized time warping

doi:10.1016/j.neucom.2016.11.004

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

	Human activity prediction using temporally-weighted generalized time warping
	Wang, Haoran 1; Yang, Wankou 2; Yuan, Chunfeng3 ; Ling, Haibin 4; Hu, Weiming3
发表期刊	NEUROCOMPUTING
	2017-02-15
卷号	225 期号:1 页码:139-147
文章类型	Article
摘要	Different from traditional human activity recognition, human activity prediction aims to recognize an unfinished activity, typically in absence of explicit temporal progress status. In this paper, we propose a new human activity prediction approach by extending the recently proposed generalized time warping (GTW) [20], which allows an efficient and flexible alignment of two or more multi-dimensional time series. More specifically, for each activity video, either complete or incomplete, we first decompose it into a sequence of short video segments. Then, we represent each segment by the local spatial-temporal statistics using the classical bag-of visual -words model. In this way, the comparison between a query sequence (i.e., containing an incomplete activity) and a reference sequence (i.e., containing a full activity) boils down to the problem of aligning their corresponding segment sequences. While GTW treats different portions of a sequence as equally important, our task is in favor of early portions since an incomplete activity video always aligns from the beginning of a complete one. Thus motivated, we develop a temporally-weighted GTW (TGTW) algorithm for the activity prediction problem by encouraging alignment in the early portion of an activity sequence. Finally, the similarity derived from TGTW is combined with the k-nearest neighbors algorithm for predicting the activity class of an input sequence. The proposed approach is evaluated on several publicly available datasets in comparison with state-of-the-art approaches. The experimental results and analysis clearly demonstrate the effectiveness of the proposed approach.
关键词	Activity Prediction Time Warping Alignment
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2016.11.004
关键词[WOS]	ACTION RECOGNITION ; HUMAN MOTION ; ALIGNMENT ; SEQUENCES
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61603080 ; Fundamental Research Funds for the Central Universities of China(N150403006) ; NSF of Jiangsu Province(BK20140566 ; China Postdoctoral science Foundation(2014M561586) ; 61473086 ; BK20150470) ; 61375001)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000392164400014
引用统计	被引频次：17[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/173211/14360
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.Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Peoples R China 2.Southeast Univ, Sch Automat, Nanjing 210096, Jiangsu, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 USA
推荐引用方式 GB/T 7714	Wang, Haoran,Yang, Wankou,Yuan, Chunfeng,et al. Human activity prediction using temporally-weighted generalized time warping[J]. NEUROCOMPUTING,2017,225(1):139-147.
APA	Wang, Haoran,Yang, Wankou,Yuan, Chunfeng,Ling, Haibin,&Hu, Weiming.(2017).Human activity prediction using temporally-weighted generalized time warping.NEUROCOMPUTING,225(1),139-147.
MLA	Wang, Haoran,et al."Human activity prediction using temporally-weighted generalized time warping".NEUROCOMPUTING 225.1(2017):139-147.

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
wanghaoran-Human act（1309KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载