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
会议名称IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议录名称IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议日期2015.06.07-2015.06.12
会议地点波士顿
摘要In 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.
关键词
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/10840
专题模式识别国家重点实验室_视频内容安全
通讯作者Weiming Hu
推荐引用方式
GB/T 7714
Shuang Yang,Chunfeng Yuan,Baoxin Wu,et al. Multi-Feature Max-Margin Hierarchical Bayesian Model for Action Recognition[C],2015.
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
Yang_Multi-Feature_M(716KB)会议论文 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
[Shuang Yang]的文章
[Chunfeng Yuan]的文章
[Baoxin Wu]的文章
百度学术
百度学术中相似的文章
[Shuang Yang]的文章
[Chunfeng Yuan]的文章
[Baoxin Wu]的文章
必应学术
必应学术中相似的文章
[Shuang Yang]的文章
[Chunfeng Yuan]的文章
[Baoxin Wu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Yang_Multi-Feature_Max-Margin_Hierarchical_2015_CVPR_paper.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。