CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Fusing Features and Local Features with Context-Aware Kernels for Action Recognition
Yuan, Chunfeng1; Wu, Baoxin1; Li, Xi2; Hu, Weiming1; Maybank, Stephen3; Wang, Fangshi4
2016-06-01
发表期刊INTERNATIONAL JOURNAL OF COMPUTER VISION
卷号118期号:2页码:151-171
文章类型Article
摘要The performance of action recognition in video sequences depends significantly on the representation of actions and the similarity measurement between the representations. In this paper, we combine two kinds of features extracted from the spatio-temporal interest points with context-aware kernels for action recognition. For the action representation, local cuboid features extracted around interest points are very popular using a Bag of Visual Words (BOVW) model. Such representations, however, ignore potentially valuable information about the global spatio-temporal distribution of interest points. We propose a new global feature to capture the detailed geometrical distribution of interest points. It is calculated by using the 3D transform which is defined as an extended 3D discrete Radon transform, followed by the application of a two-directional two-dimensional principal component analysis. For the similarity measurement, we model a video set as an optimized probabilistic hypergraph and propose a context-aware kernel to measure high order relationships among videos. The context-aware kernel is more robust to the noise and outliers in the data than the traditional context-free kernel which just considers the pairwise relationships between videos. The hyperedges of the hypergraph are constructed based on a learnt Mahalanobis distance metric. Any disturbing information from other classes is excluded from each hyperedge. Finally, a multiple kernel learning algorithm is designed by integrating the norm regularization into a linear SVM classifier to fuse the feature and the BOVW representation for action recognition. Experimental results on several datasets demonstrate the effectiveness of the proposed approach for action recognition.
关键词Action Recognition Spatio-temporal Interest Points 3d r Transform Hypergraph Context-aware Kernel
WOS标题词Science & Technology ; Technology
DOI10.1007/s11263-015-0867-0
关键词[WOS]TIME INTEREST POINTS ; FACE REPRESENTATION ; VISUAL RECOGNITION ; 2-DIMENSIONAL PCA ; CLASSIFICATION ; SVM
收录类别SCI
语种英语
项目资助者973 basic research program of China(2014CB349303) ; Natural Science Foundation of China(61472421 ; CAS Center for Excellence in Brain Science and Intelligence Technology ; Guangdong Natural Science Foundation(S2012020011081) ; 61472420 ; 61303086 ; 61202327)
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000377477400004
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/10838
专题模式识别国家重点实验室_视频内容安全
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
2.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou, Zhejiang, Peoples R China
3.Birkbeck Coll, Dept Comp Sci & Informat Syst, London, England
4.Beijing Jiaotong Univ, Sch Software Engn, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Yuan, Chunfeng,Wu, Baoxin,Li, Xi,et al. Fusing Features and Local Features with Context-Aware Kernels for Action Recognition[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2016,118(2):151-171.
APA Yuan, Chunfeng,Wu, Baoxin,Li, Xi,Hu, Weiming,Maybank, Stephen,&Wang, Fangshi.(2016).Fusing Features and Local Features with Context-Aware Kernels for Action Recognition.INTERNATIONAL JOURNAL OF COMPUTER VISION,118(2),151-171.
MLA Yuan, Chunfeng,et al."Fusing Features and Local Features with Context-Aware Kernels for Action Recognition".INTERNATIONAL JOURNAL OF COMPUTER VISION 118.2(2016):151-171.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
IJCV 2015 Features a(3979KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Yuan, Chunfeng]的文章
[Wu, Baoxin]的文章
[Li, Xi]的文章
百度学术
百度学术中相似的文章
[Yuan, Chunfeng]的文章
[Wu, Baoxin]的文章
[Li, Xi]的文章
必应学术
必应学术中相似的文章
[Yuan, Chunfeng]的文章
[Wu, Baoxin]的文章
[Li, Xi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: IJCV 2015 Features and Local Features with Context-aware Kernels for Action Recognition.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。