Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition

doi:10.1109/TPAMI.2015.2513479

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition
	Wan, Jun1,2 ; Guo, Guodong 3; Li, Stan Z.1,2 ; Jun Wan
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2016-08-01
卷号	38 期号:8 页码:1626-1639
文章类型	Article
摘要	Availability of handy RGB-D sensors has brought about a surge of gesture recognition research and applications. Among various approaches, one shot learning approach is advantageous because it requires minimum amount of data. Here, we provide a thorough review about one-shot learning gesture recognition from RGB-D data and propose a novel spatiotemporal feature extracted from RGB-D data, namely mixed features around sparse keypoints (MFSK). In the review, we analyze the challenges that we are facing, and point out some future research directions which may enlighten researchers in this field. The proposed MFSK feature is robust and invariant to scale, rotation and partial occlusions. To alleviate the insufficiency of one shot training samples, we augment the training samples by artificially synthesizing versions of various temporal scales, which is beneficial for coping with gestures performed at varying speed. We evaluate the proposed method on the Chalearn gesture dataset (CGD). The results show that our approach outperforms all currently published approaches on the challenging data of CGD, such as translated, scaled and occluded subsets. When applied to the RGB-D datasets that are not one-shot (e.g., the Cornell Activity Dataset-60 and MSR Daily Activity 3D dataset), the proposed feature also produces very promising results under leave-one-out cross validation or one-shot learning.
关键词	One-shot Learning Gesture Reco Gnition Rgb-d Data Bag Of Visual Words Model
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TPAMI.2015.2513479
关键词[WOS]	TIME ACTION RECOGNITION ; BAG
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000379926200011
引用统计	被引频次：84[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/173211/12157
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
通讯作者	Jun Wan
作者单位	1.Chinese Acad Sci, Ctr Biometr & Secur Res, Room 1411,Intelligent Bldg,95 Zhongguancun Donglu, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Room 1411,Intelligent Bldg,95 Zhongguancun Donglu, Beijing 100190, Peoples R China 3.West Virginia Univ, Dept Comp Sci & Elect Engn, Morgantown, WV 26506 USA
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	Wan, Jun,Guo, Guodong,Li, Stan Z.,et al. Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2016,38(8):1626-1639.
APA	Wan, Jun,Guo, Guodong,Li, Stan Z.,&Jun Wan.(2016).Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,38(8),1626-1639.
MLA	Wan, Jun,et al."Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 38.8(2016):1626-1639.

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
TPAMI2016_JunWan.pdf（771KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载