A Generic Framework for Video Annotation via Semi-Supervised Learning

	A Generic Framework for Video Annotation via Semi-Supervised Learning
	Zhang, Tianzhu1,2 ; Xu, Changsheng2,3 ; Zhu, Guangyu 2,4; Liu, Si 2,3; Lu, Hanqing2,3
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
	2012-08-01
卷号	14 期号:4 页码:1206-1219
文章类型	Article
摘要	Learning-based video annotation is essential for video analysis and understanding, and many various approaches have been proposed to avoid the intensive labor costs of purely manual annotation. However, there lacks a generic framework due to several difficulties, such as dependence of domain knowledge, insufficiency of training data, no precise localization and inefficacy for large-scale video dataset. In this paper, we propose a novel approach based on semi-supervised learning by means of information from the Internet for interesting event annotation in videos. Concretely, a Fast Graph-based Semi-Supervised Multiple Instance Learning (FGSSMIL) algorithm, which aims to simultaneously tackle these difficulties in a generic framework for various video domains (e. g., sports, news, and movies), is proposed to jointly explore small-scale expert labeled videos and large-scale unlabeled videos to train the models. The expert labeled videos are obtained from the analysis and alignment of well-structured video related text (e. g., movie scripts, web-casting text, close caption). The unlabeled data are obtained by querying related events from the video search engine (e. g., YouTube, Google) in order to give more distributive information for event modeling. Two critical issues of FGSSMIL are: 1) how to calculate the weight assignment for a graph construction, where the weight of an edge specifies the similarity between two data points. To tackle this problem, we propose a novel Multiple Instance Learning Induced Similarity (MILIS) measure by learning instance sensitive classifiers; 2) how to solve the algorithm efficiently for large-scale dataset through an optimization approach. To address this issue, Concave-Convex Procedure (CCCP) and nonnegative multiplicative updating rule are adopted. We perform the extensive experiments in three popular video domains: movies, sports, and news. The results compared with the state-of-the-arts are promising and demonstrate the effectiveness and efficiency of our proposed approach.
关键词	Broadcast Video Concave-convex Procedure (Cccp) Event Detection Graph Internet Multiple Instance Learning Semi-supervised Learning Web-casting Text
WOS标题词	Science & Technology ; Technology
关键词[WOS]	LINEAR NEIGHBORHOOD PROPAGATION
收录类别	SCI
语种	英语
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:000306599400008
引用统计	被引频次：46[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/173211/3351
专题	紫东太初大模型研究中心_图像与视频分析
作者单位	1.Adv Digital Sci Ctr ADSC, Singapore 138632, Singapore 2.China Singapore Inst Digital Media, Singapore 119613, Singapore 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore, Singapore
推荐引用方式 GB/T 7714	Zhang, Tianzhu,Xu, Changsheng,Zhu, Guangyu,et al. A Generic Framework for Video Annotation via Semi-Supervised Learning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2012,14(4):1206-1219.
APA	Zhang, Tianzhu,Xu, Changsheng,Zhu, Guangyu,Liu, Si,&Lu, Hanqing.(2012).A Generic Framework for Video Annotation via Semi-Supervised Learning.IEEE TRANSACTIONS ON MULTIMEDIA,14(4),1206-1219.
MLA	Zhang, Tianzhu,et al."A Generic Framework for Video Annotation via Semi-Supervised Learning".IEEE TRANSACTIONS ON MULTIMEDIA 14.4(2012):1206-1219.