Modality-specific and hierarchical feature learning for RGB-D hand-held object recognition

doi:10.1007/s11042-016-3375-5

	Modality-specific and hierarchical feature learning for RGB-D hand-held object recognition
	Lv, Xiong 1; Liu, Xinda 2; Li, Xiangyang 1; Li, Xue 1,3; Jiang, Shuqiang 1; He, Zhiqiang 4
	2017-02-01
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
ISSN	1380-7501
卷号	76 期号:3 页码:4273-4290
摘要	Hand-held object recognition is an important research topic in image understanding and plays an essential role in human-machine interaction. With the easily available RGB-D devices, the depth information greatly promotes the performance of object segmentation and provides additional channel information. While how to extract a representative and discriminating feature from object region and efficiently take advantage of the depth information plays an important role in improving hand-held object recognition accuracy and eventual human-machine interaction experience. In this paper, we focus on a special but important area called RGB-D hand-held object recognition and propose a hierarchical feature learning framework for this task. First, our framework learns modality-specific features from RGB and depth images using CNN architectures with different network depth and learning strategies. Secondly a high-level feature learning network is implemented for a comprehensive feature representation. Different with previous works on feature learning and representation, the hierarchical learning method can sufficiently dig out the characteristics of different modal information and efficiently fuse them in a unified framework. The experimental results on HOD dataset illustrate the effectiveness of our proposed method.
关键词	Feature learning RGB-D object recogntion Multiple modalities
DOI	10.1007/s11042-016-3375-5
收录类别	SCI
语种	英语
资助项目	National Basic Research 973 Program of China[2012CB316400] ; National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61322212] ; National High Technology Research and Development 863 Program of China[2014AA015202] ; Lenovo Outstanding Young Scientists Program (LOYS)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000396051200054
出版者	SPRINGER
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/7479
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	He, Zhiqiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Ningxia Univ, Sch Math & Comp Sci, Ningxia 750021, Peoples R China 3.Shandong Univ Sci & Technol, Coll Informat Sci & Engn, Qingdao, Shandong, Peoples R China 4.Lenovo Corp Res, Beijing 100085, Peoples R China
推荐引用方式 GB/T 7714	Lv, Xiong,Liu, Xinda,Li, Xiangyang,et al. Modality-specific and hierarchical feature learning for RGB-D hand-held object recognition[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2017,76(3):4273-4290.
APA	Lv, Xiong,Liu, Xinda,Li, Xiangyang,Li, Xue,Jiang, Shuqiang,&He, Zhiqiang.(2017).Modality-specific and hierarchical feature learning for RGB-D hand-held object recognition.MULTIMEDIA TOOLS AND APPLICATIONS,76(3),4273-4290.
MLA	Lv, Xiong,et al."Modality-specific and hierarchical feature learning for RGB-D hand-held object recognition".MULTIMEDIA TOOLS AND APPLICATIONS 76.3(2017):4273-4290.