CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Multi-Feature Max-Margin Hierarchical Bayesian Model for Action Recognition
Shuang Yang; Chunfeng Yuan; Baoxin Wu; Weiming Hu; Fangshi Wang
2015
Conference NameIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Source PublicationIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference Date2015.06.07-2015.06.12
Conference Place波士顿
AbstractIn this paper, a multi-feature max-margin hierarchical
Bayesian model (M3HBM) is proposed for action recognition.
Different from existing methods which separate representation
and classification into two steps, M3HBM jointly
learns a high-level representation by combining a hierarchical
generative model (HGM) and discriminative maxmargin
classifiers in a unified Bayesian framework. Specifically,
HGM is proposed to represent actions by distributions
over latent spatial temporal patterns (STPs) which
are learned from multiple feature modalities and shared among
different classes. For recognition, we employ Gibbs
classifiers to minimize the expected loss function based on
the max-margin principle and use the classifiers as regularization
terms of M3HBM to perform Bayeisan estimation
for classifier parameters together with the learning of STPs.
In addition, multi-task learning is applied to learn the
model from multiple feature modalities for different classes.
For test videos, we obtain the representations by the
inference process and perform action recognition by the
learned Gibbs classifiers. For the learning and inference
process, we derive an efficient Gibbs sampling algorithm
to solve the proposed M3HBM. Extensive experiments on
several datasets demonstrate both the representation power
and the classification capability of our approach for action
recognition.
Keyword
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10840
Collection模式识别国家重点实验室_视频内容安全
Corresponding AuthorWeiming Hu
Recommended Citation
GB/T 7714
Shuang Yang,Chunfeng Yuan,Baoxin Wu,et al. Multi-Feature Max-Margin Hierarchical Bayesian Model for Action Recognition[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
Yang_Multi-Feature_M(716KB)会议论文 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
[Shuang Yang]'s Articles
[Chunfeng Yuan]'s Articles
[Baoxin Wu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shuang Yang]'s Articles
[Chunfeng Yuan]'s Articles
[Baoxin Wu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shuang Yang]'s Articles
[Chunfeng Yuan]'s Articles
[Baoxin Wu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Yang_Multi-Feature_Max-Margin_Hierarchical_2015_CVPR_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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