CASIA OpenIR  > 智能感知与计算研究中心
Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding
Zhao, Fang1; Huang, Yongzhen1,3; Wang, Liang1,3; Xiang, Tao2; Tan, Tieniu1
2016-09-01
发表期刊INTERNATIONAL JOURNAL OF COMPUTER VISION
卷号119期号:3页码:329-345
文章类型Article
摘要Analyzing unstructured group activities and events in uncontrolled web videos is a challenging task due to (1) the semantic gap between class labels and low-level visual features, (2) the demanding computational cost given high-dimensional low-level feature vectors and (3) the lack of labeled training data. These difficulties can be overcome by learning a meaningful and compact mid-level video representation. To this end, in this paper a novel supervised probabilistic graphical model termed Relevance Restricted Boltzmann Machine (ReRBM) is developed to learn a low-dimensional latent semantic representation for complex activities and events. Our model is a variant of the Restricted Boltzmann Machine (RBM) with a number of critical extensions: (1) sparse Bayesian learning is incorporated into the RBM to learn features which are relevant to video classes, i.e., discriminative; (2) binary stochastic hidden units in the RBM are replaced by rectified linear units in order to better explain complex video contents and make variational inference tractable for the proposed model; and (3) an efficient variational EM algorithm is formulated for model parameter estimation and inference. We conduct extensive experiments on two recent challenging benchmarks: the Unstructured Social Activity Attribute dataset and the Event Video dataset. The experimental results demonstrate that the relevant features learned by our model provide better semantic and discriminative description for videos than a number of alternative supervised latent variable models, and achieves state of the art performance in terms of classification accuracy and retrieval precision, particularly when only a few labeled training samples are available.
关键词Representation Learning Video Analysis Restricted Boltzmann Machine Sparse Bayesian Learning
WOS标题词Science & Technology ; Technology
DOI10.1007/s11263-016-0896-3
关键词[WOS]LATENT DIRICHLET ALLOCATION ; CLASSIFICATION ; ALGORITHM ; MODELS
收录类别SCI
语种英语
项目资助者National Basic Research Program of China(2012CB316300) ; National Natural Science Foundation of China(61525306 ; Strategic Priority Research Program of the CAS(XDB02070100) ; 61573354 ; 61135002 ; 61420106015)
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000380270000008
引用统计
被引频次:3[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/173211/12170
专题智能感知与计算研究中心
作者单位1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China
2.Queen Mary Univ London, Sch Elect Engn & Comp Sci, London, England
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Zhao, Fang,Huang, Yongzhen,Wang, Liang,et al. Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2016,119(3):329-345.
APA Zhao, Fang,Huang, Yongzhen,Wang, Liang,Xiang, Tao,&Tan, Tieniu.(2016).Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding.INTERNATIONAL JOURNAL OF COMPUTER VISION,119(3),329-345.
MLA Zhao, Fang,et al."Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding".INTERNATIONAL JOURNAL OF COMPUTER VISION 119.3(2016):329-345.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Learning Relevance R(6286KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhao, Fang]的文章
[Huang, Yongzhen]的文章
[Wang, Liang]的文章
百度学术
百度学术中相似的文章
[Zhao, Fang]的文章
[Huang, Yongzhen]的文章
[Wang, Liang]的文章
必应学术
必应学术中相似的文章
[Zhao, Fang]的文章
[Huang, Yongzhen]的文章
[Wang, Liang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Learning Relevance Restricted Boltzmann Machine for_ZhaoFang_IJCV.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。