A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities

doi:10.1016/j.neucom.2017.08.057

	A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities
	Pang, Junbiao 1; Tao, Fei 2; Li, Liang 3; Huang, Qingming 2,3; Yin, Baocai 1,4; Tian, Qi 5
	2018-01-31
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	275 页码:478-487
摘要	To quickly grasp what interesting topics are happening on web, it is challenge to discover and describe topics from User-Generated Content (UGC) data. Describing topics by probable keywords and prototype images is an efficient human-machine interaction to help person quickly grasp a topic. However, except for the challenges from web topic detection, mining the multi-media description is a challenge task that the conventional approaches can barely handle: (1) noises from non-informative short texts or images due to less-constrained UGC; and (2) even for these informative images, the gaps between visual concepts and social ones. This paper addresses above challenges from the perspective of background similarity remove, and proposes a two-step approach to mining the multi-media description from noisy data. First, we utilize a devcovolution model to strip the similarities among non-informative words/images during web topic detection. Second, the background-removed similarities are reconstructed to identify the probable keywords and prototype images during topic description. By removing background similarities, we can generate coherent and informative multi-media description for a topic. Experiments show that the proposed method produces a high quality description on two public datasets. (C) 2017 Elsevier B.V. All rights reserved.
关键词	Topic description Poisson deconvolution User-Generated Content Topic detection Background similarity Multi-modal description
DOI	10.1016/j.neucom.2017.08.057
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[61332016] ; Natural Science Foundation of China[61672069] ; Natural Science Foundation of China[61472387] ; Natural Science Foundation of China[61620106009] ; Natural Science Foundation of China[U1636214] ; Natural Science Foundation of China[61429201] ; Natural Science Foundation of China[61650202] ; Beijing Post-Doctoral Research Foundation ; Beijing Municipal Commission of Education[KM201610005034] ; Funding Project for Academic Human Resources Development in Institutions of Higher Learning Under the Jurisdiction of Beijing Municipality (PHR) ; ARO[W911NF-15-1-0290] ; NEC Laboratory of Blippar ; NEC Laboratory of America
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000418370200047
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：7[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/2XEOYT63/6283
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Liang
作者单位	1.Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Multimedia & Intelligent Software, 100 Pingleyuan Rd, Beijing 100124, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, 19 Yuquan Rd, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, 6 Kexueyuan South Rd, Beijing 100190, Peoples R China 4.Dalian Univ Technol, 2 Linggong Rd, Dalian 116024, Peoples R China 5.Univ Texas San Antonio, Dept Comp Sci, One UTSA Circle, San Antonio, TX 78249 USA
推荐引用方式 GB/T 7714	Pang, Junbiao,Tao, Fei,Li, Liang,et al. A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities[J]. NEUROCOMPUTING,2018,275:478-487.
APA	Pang, Junbiao,Tao, Fei,Li, Liang,Huang, Qingming,Yin, Baocai,&Tian, Qi.(2018).A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities.NEUROCOMPUTING,275,478-487.
MLA	Pang, Junbiao,et al."A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities".NEUROCOMPUTING 275(2018):478-487.