CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition
Yuan, Chunfeng1; Li, Xi2; Hu, Weiming1; Ling, Haibin3; Maybank, Stephen J.4
Source PublicationIEEE TRANSACTIONS ON IMAGE PROCESSING
2014-02-01
Volume23Issue:2Pages:658-672
SubtypeArticle
AbstractIn this paper, we present a new geometric-temporal representation for visual action recognition based on local spatio-temporal features. First, we propose a modified covariance descriptor under the log-Euclidean Riemannian metric to represent the spatio-temporal cuboids detected in the video sequences. Compared with previously proposed covariance descriptors, our descriptor can be measured and clustered in Euclidian space. Second, to capture the geometric-temporal contextual information, we construct a directional pyramid co-occurrence matrix (DPCM) to describe the spatio-temporal distribution of the vector-quantized local feature descriptors extracted from a video. DPCM characterizes the co-occurrence statistics of local features as well as the spatio-temporal positional relationships among the concurrent features. These statistics provide strong descriptive power for action recognition. To use DPCM for action recognition, we propose a directional pyramid co-occurrence matching kernel to measure the similarity of videos. The proposed method achieves the state-of-the-art performance and improves on the recognition performance of the bag-of-visual-words (BOVWs) models by a large margin on six public data sets. For example, on the KTH data set, it achieves 98.78% accuracy while the BOVW approach only achieves 88.06%. On both Weizmann and UCF CIL data sets, the highest possible accuracy of 100% is achieved.
KeywordCovariance Cuboid Descriptor Log-euclidean Riemannian Metric Spatio-temporal Directional Pyramid Co-occurrence Matrix Kernel Machine Action Recognition
WOS HeadingsScience & Technology ; Technology
WOS KeywordIMAGE FEATURES ; CLASSIFICATION ; CATEGORIES ; FLOW
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000329581800014
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/3268
Collection模式识别国家重点实验室_视频内容安全
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Adelaide, Sch Comp Sci, Adelaide, SA 5005, Australia
3.Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 USA
4.Univ London Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yuan, Chunfeng,Li, Xi,Hu, Weiming,et al. Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2014,23(2):658-672.
APA Yuan, Chunfeng,Li, Xi,Hu, Weiming,Ling, Haibin,&Maybank, Stephen J..(2014).Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,23(2),658-672.
MLA Yuan, Chunfeng,et al."Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 23.2(2014):658-672.
Files in This Item: Download All
File Name/Size DocType Version Access License
06665089_TIP.pdf(3487KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yuan, Chunfeng]'s Articles
[Li, Xi]'s Articles
[Hu, Weiming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yuan, Chunfeng]'s Articles
[Li, Xi]'s Articles
[Hu, Weiming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yuan, Chunfeng]'s Articles
[Li, Xi]'s Articles
[Hu, Weiming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 06665089_TIP.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.