Knowledge-Based Topic Model for Multi-Modal Social Event Analysis

doi:10.1109/TMM.2019.2951194

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Knowledge-Based Topic Model for Multi-Modal Social Event Analysis
	Xue, Feng 1,4; Hong, Richang 1,4; He, Xiangnan 3; Wang, Jianwei 2; Qian, Shengsheng 5; Xu, Changsheng 5
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2020-08-01
卷号	22 期号:8 页码:2098-2110
关键词	Analytical models Knowledge based systems Social networking (online) Data mining Data models Internet Knowledge engineering Knowledge embedding multi-modal topic coherence event classification
ISSN号	1520-9210
DOI	10.1109/TMM.2019.2951194
通讯作者	Hong, Richang(hongrc.hfut@gmail.com)
英文摘要	With the accumulation of data on the Internet and progress in representation learning techniques, knowledge priors learned from a large-scale knowledge base has been increasingly used in probabilistic topic models. However, it is challenging to learn interpretable topics and a discriminative event representation based on multi-modal information. To address these issues, we propose a knowledge priors- and max-margin-based topic model for multi-modal social event analysis, called the KGE-MMSLDA, in which feature representation and knowledge priors are jointly learned. Our model has three main advantages over current methods: (1) It integrates additional knowledge from external knowledge base into a unified topic model in which the max-margin classifier, and multi-modal information are exploited to increase the number of event descriptions obtained. (2) We mined knowledge priors from over 74,000 web documents. Multi-modal data with these knowledge priors are then incorporated into the topic model to increase the number of coherent topics learned. (3) A large-scale multi-modal dataset (containing 10 events, where each event contained approximately 7,000 Flickr pages) was collected and has been released publicly for event topic mining and classification research. In comparative experiments, the proposed method outperformed state-of-the-art models on topic coherence, and obtained a classification accuracy of 85.1%.
资助项目	National Key Research and Development Program of China[2017YFB0803301] ; National Natural Science Foundation of China[61772170]
WOS研究方向	Computer Science ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000553424500015
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40304]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Hong, Richang
作者单位	1.Hefei Univ Technol, Key Lab Knowledge Engn Big Data, Minist Educ, Hefei 230601, Peoples R China 2.Minglue Technol Grp, Beijing 100083, Peoples R China 3.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230031, Peoples R China 4.Hefei Univ Thchnol, Sch Comp Sci & Informat Engn, Hefei 230601, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Xue, Feng,Hong, Richang,He, Xiangnan,et al. Knowledge-Based Topic Model for Multi-Modal Social Event Analysis[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2020,22(8):2098-2110.
APA	Xue, Feng,Hong, Richang,He, Xiangnan,Wang, Jianwei,Qian, Shengsheng,&Xu, Changsheng.(2020).Knowledge-Based Topic Model for Multi-Modal Social Event Analysis.IEEE TRANSACTIONS ON MULTIMEDIA,22(8),2098-2110.
MLA	Xue, Feng,et al."Knowledge-Based Topic Model for Multi-Modal Social Event Analysis".IEEE TRANSACTIONS ON MULTIMEDIA 22.8(2020):2098-2110.