Enhancing Video Event Recognition Using Automatically Constructed Semantic-Visual Knowledge Base

doi:10.1109/TMM.2015.2449660

	Enhancing Video Event Recognition Using Automatically Constructed Semantic-Visual Knowledge Base
	Zhang, Xishan 1,2; Yang, Yang 3; Zhang, Yongdong 1; Luan, Huanbo 5; Li, Jintao 1; Zhang, Hanwang 4; Chua, Tat-Seng 4
	2015-09-01
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	17 期号:9 页码:1562-1575
摘要	The task of recognizing events from video has attracted a lot of attention in recent years. However, due to the complex nature of user-defined events, the use of purely audio-visual content analysis without domain knowledge has been found to be grossly inadequate. In this paper, we propose to construct a semantic-visual knowledge base to encode the rich event-centric concepts and their relationships from the well-established lexical databases, including FrameNet, as well as the concept-specific visual knowledge from ImageNet. Based on this semantic-visual knowledge bases, we design an effective system for video event recognition. Specifically, in order to narrow the semantic gap between the high-level complex events and low-level visual representations, we utilize the event-centric semantic concepts encoded in the knowledge base as the intermediate-level event representation, which offers both human-perceivable and machine-interpretable semantic clues for event recognition. In addition, in order to leverage the abundant ImageNet images, we propose a robust transfer learning model to learn the noise-resistant concept classifiers for videos. Extensive experiments on various real-world video datasets demonstrate the superiority of our proposed system as compared to the state-of-the-art approaches.
关键词	Concept detection event recognition knowledge base
DOI	10.1109/TMM.2015.2449660
收录类别	SCI
语种	英语
资助项目	National High Technology and Research Development Program of China under the 863 Program[2014AA015202] ; National Natural Science Foundation of China[61303075]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000359583000016
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：29[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/2XEOYT63/9448
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Xishan
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 611731, Peoples R China 4.Natl Univ Singapore, Sch Comp, Singapore 117417, Singapore 5.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Xishan,Yang, Yang,Zhang, Yongdong,et al. Enhancing Video Event Recognition Using Automatically Constructed Semantic-Visual Knowledge Base[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2015,17(9):1562-1575.
APA	Zhang, Xishan.,Yang, Yang.,Zhang, Yongdong.,Luan, Huanbo.,Li, Jintao.,...&Chua, Tat-Seng.(2015).Enhancing Video Event Recognition Using Automatically Constructed Semantic-Visual Knowledge Base.IEEE TRANSACTIONS ON MULTIMEDIA,17(9),1562-1575.
MLA	Zhang, Xishan,et al."Enhancing Video Event Recognition Using Automatically Constructed Semantic-Visual Knowledge Base".IEEE TRANSACTIONS ON MULTIMEDIA 17.9(2015):1562-1575.