SERVE: Soft and Equalized Residual VEctors for image retrieval

doi:10.1016/j.neucom.2016.04.047

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

	SERVE: Soft and Equalized Residual VEctors for image retrieval
	Li, Jun 1; Xu, Chang 2; Gong, Mingming 3; Xing, Junliang4 ; Yang, Wankou 1; Sun, Changyin 1
发表期刊	NEUROCOMPUTING
	2016-09-26
卷号	207 期号:0 页码:202-212
文章类型	Article
摘要	In the last decade, a wide variety of image signatures, e.g., Bag-of-Visual-Words (BOVW), Fisher Vector (FV), and Vector of Locally Aggregated Descriptor (VLAD), have been developed for effective image retrieval. These image signatures, however, are either computationally expensive or simplified for the purpose of trading accuracy for efficiency. To simultaneously guarantee efficiency and effectiveness, we propose a novel image signature termed Soft and Equalized Residual VEctors (SERVE) which is more discriminatively formulated and maintains higher accuracy. It improves VLAD by encoding the variability in within-cluster feature points into the summation of Residual Vectors.(RV) while manifesting superiority in computational efficiency over FV. To find the latent low-dimensional manifolds underlying in the SERVE feature space, we propose to partition the original feature space into separate subspaces by random projections and employ multi-graph embedding to obtain additional performance gain. In particular, we make use of two fusion strategies for graph ensemble to generate a holistic representation. Extensive empirical studies carried out on the three retrieval-specific public benchmarks reveal that our method outperforms existing state-of-the-art methods and provides a promising paradigm for the image retrieval task. (C) 2016 Published by Elsevier B.V.
关键词	Serve Manifolds Multi-graph Embedding Graph Ensemble Image Retrieval
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2016.04.047
关键词[WOS]	OBJECT RETRIEVAL ; RELEVANCE FEEDBACK ; RE-RANKING ; REPRESENTATION ; FEATURES ; DATABASE ; VLAD
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61473086 ; Natural Science Foundation of Jiangsu Province(BK20140566 ; 61375001) ; BK20150470)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000382794500018
引用统计	被引频次：10[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/173211/12647
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.Southeast Univ, Sch Automat, Nanjing 210096, Jiangsu, Peoples R China 2.Peking Univ, Sch Elect Engn & Comp Sci, Minist Educ, Key Lab Machine Percept, Beijing 100871, Peoples R China 3.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Fac Engn & Informat Technol, Ultimo, NSW 2007, Australia 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Jun,Xu, Chang,Gong, Mingming,et al. SERVE: Soft and Equalized Residual VEctors for image retrieval[J]. NEUROCOMPUTING,2016,207(0):202-212.
APA	Li, Jun,Xu, Chang,Gong, Mingming,Xing, Junliang,Yang, Wankou,&Sun, Changyin.(2016).SERVE: Soft and Equalized Residual VEctors for image retrieval.NEUROCOMPUTING,207(0),202-212.
MLA	Li, Jun,et al."SERVE: Soft and Equalized Residual VEctors for image retrieval".NEUROCOMPUTING 207.0(2016):202-212.

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
NC16SERVE.pdf（2902KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载