Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
| A Hierarchical Model Based on Latent Dirichlet Allocation for Action Recognition | |
Shuang Yang ; Chunfeng Yuan; Weiming Hu; Xinmiao Ding
| |
| 2014 | |
| Conference Name | 2014 22nd International Conference on Pattern Recognition |
| Source Publication | International Conference on Pattern Recognition (ICPR) |
| Pages | 2613-2618 |
| Conference Date | 2014 |
| Conference Place | USA |
| Abstract | Inspired by the recent success of hierarchical representation, we propose a new hierarchical variant of latent Dirichlet allocation (h-LDA) for action recognition. The model consists of an appearance group and a motion group, and we introduce a new hierarchical structure including two-layer topics in each group to learn the spatial temporal patterns (STPs) of human actions. The basic idea is that the two-layer topics are used to model the global STPs and the local STPs of the actions respectively. Two groups of discrete words are generated from two complementary kinds of features for each group. Each topic learned in these two groups is used to describe a particular aspect of the actions. Specifically, the mid-level topics are learned to describe the local STPs by including the geometric structure information in the lower-level words. The top-level topics are learned from the mid-level topics and are the mixture distribution of the local STPs, which makes the top-level topics appropriate to represent the global STPs. In addition, we give the learning and inference process by Gibbs sampling with reasonable assumptions. Finally, each sample is discriminatively represented as the probabilistic distribution over the global STPs learned by the proposed h-LDA. Experimental results on two datasets demonstrate the effectiveness of our approach for action recognition. |
| Keyword | 无 |
| Indexed By | EI |
| Document Type | 会议论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/4553 |
| Collection | 模式识别国家重点实验室_视频内容安全 |
| Corresponding Author | Weiming Hu |
| Recommended Citation GB/T 7714 | Shuang Yang,Chunfeng Yuan,Weiming Hu,et al. A Hierarchical Model Based on Latent Dirichlet Allocation for Action Recognition[C],2014:2613-2618. |
| 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-SA | View Download | ||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment