Exploring Dense Trajectory Feature and Encoding Methods for Human Interaction Recognition
文献类型：会议论文
| 作者 | Xiaojiang Peng; Xiao Wu; Qiang Peng; Xianbiao Qi; Yu Qiao; Yanhua Liu |
| 出版日期 | 2013 |
| 会议名称 | 5th International Conference on Internet Multimedia Computing and Service, ICIMCS 2013 |
| 会议地点 | Huangshan, China |
| 英文摘要 | Recently, human activity recognition has obtained increasing attention due to its wide range of potential applications. Much progress has been made to improve the performance on single actions in videos while few on collective and interactive activities. Human interaction is a more challenging task owing to multi-actors in an execution. In this paper, we utilize multi-scale dense trajectories and explore four advanced feature encoding methods on the human interaction dataset with a bag-of-features framework. Particularly, dense trajectories are described by shape, histogram of gradient orientation, histogram of flow orientation and motion boundary histogram, and all these are computed by integral images. Experimental results on the UT-Interaction dataset show that our approach outperforms state-of-the-art methods by 7-14%. Additionally, we thoroughly analyse a finding that the performance of vector quantization is on par with or even better than other sophisticated feature encoding methods by using dense trajectories in videos. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/4482]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2013 |
| 推荐引用方式 GB/T 7714 | Xiaojiang Peng,Xiao Wu,Qiang Peng,et al. Exploring Dense Trajectory Feature and Encoding Methods for Human Interaction Recognition[C]. 见:5th International Conference on Internet Multimedia Computing and Service, ICIMCS 2013. Huangshan, China. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
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。