Per-Sample Multiple Kernel Approach for Visual Concept Learning

doi:10.1155/2010/461450

	Per-Sample Multiple Kernel Approach for Visual Concept Learning
	Yang, Jingjing 1,2,3; Li, Yuanning 1,2,3; Tian, Yonghong 1; Duan, Ling-Yu 1; Gao, Wen 1,2
	2010
发表期刊	EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING
ISSN	1687-5281
页码	13
摘要	Learning visual concepts from images is an important yet challenging problem in computer vision and multimedia research areas. Multiple kernel learning (MKL) methods have shown great advantages in visual concept learning. As a visual concept often exhibits great appearance variance, a canonical MKL approach may not generate satisfactory results when a uniform kernel combination is applied over the input space. In this paper, we propose a per-sample multiple kernel learning (PS-MKL) approach to take into account intraclass diversity for improving discrimination. PS-MKL determines sample-wise kernel weights according to kernel functions and training samples. Kernel weights as well as kernel-based classifiers are jointly learned. For efficient learning, PS-MKL employs a sample selection strategy. Extensive experiments are carried out over three benchmarking datasets of different characteristics including Caltech101, WikipediaMM, and Pascal VOC'07. PS-MKL has achieved encouraging performance, comparable to the state of the art, which has outperformed a canonical MKL.
DOI	10.1155/2010/461450
收录类别	SCI
语种	英语
资助项目	Chinese National Natural Science Foundation[60605020] ; Chinese National Natural Science Foundation[60973055] ; Chinese National Natural Science Foundation[60902057] ; Chinese National Natural Science Foundation[90820003] ; National Hi-Tech R and D Program (863) of China[2006AA010105] ; National Basic Research Program of China[2009CB320906]
WOS研究方向	Engineering ; Imaging Science & Photographic Technology
WOS类目	Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology
WOS记录号	WOS:000285113400001
出版者	SPRINGER
引用统计	被引频次：97[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/2XEOYT63/12285
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tian, Yonghong
作者单位	1.Peking Univ, Natl Engn Lab Video Technol, Sch EE & CS, Beijing 100871, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100080, Peoples R China 3.Chinese Acad Sci, Grad Univ, Beijing 100039, Peoples R China
推荐引用方式 GB/T 7714	Yang, Jingjing,Li, Yuanning,Tian, Yonghong,et al. Per-Sample Multiple Kernel Approach for Visual Concept Learning[J]. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING,2010:13.
APA	Yang, Jingjing,Li, Yuanning,Tian, Yonghong,Duan, Ling-Yu,&Gao, Wen.(2010).Per-Sample Multiple Kernel Approach for Visual Concept Learning.EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING,13.
MLA	Yang, Jingjing,et al."Per-Sample Multiple Kernel Approach for Visual Concept Learning".EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING (2010):13.