Knowledge Commons of Institute of Automation,CAS
Multi-Feature Max-Margin Hierarchical Bayesian Model for Action Recognition | |
Shuang Yang![]() ![]() ![]() | |
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 | 无 |
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 | 多模态人工智能系统全国重点实验室_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 |
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。
修改评论