Exploring Motion Boundary based Sampling and Spatial-Temporal Context Descriptors for Action Recognition
文献类型：会议论文
| 作者 | Peng Xiaojiang; Qiao Yu; Peng Qiang; Qi Xianbiao |
| 出版日期 | 2013 |
| 会议名称 | 2013 24th British Machine Vision Conference, BMVC 2013 |
| 会议地点 | Bristol, United kingdom |
| 英文摘要 | Feature representation is important for human action recognition. Recently, Wang et al. [25] proposed dense trajectory (DT) based features for action video representation and achieved state-of-the-art performance on several action datasets. In this paper, we improve the DT method in two folds. Firstly, we introduce a motion boundary based dense sampling strategy, which greatly reduces the number of valid trajectories while preserves the discriminative power. Secondly, we develop a set of new descriptors which describe the spatial-temporal context of motion trajectories. To evaluate the performance of the proposed methods, we conduct extensive experiments on three benchmarks including K-TH, YouTube and HMDB51. The results show that our sampling strategy significantly reduces the computational cost of point tracking without degrading performance. Meanwhile, we achieve superior performance than the state-of-the-art methods by utilizing our spatial-temporal context descriptors. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/4483]  |
| 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 | Peng Xiaojiang,Qiao Yu,Peng Qiang,et al. Exploring Motion Boundary based Sampling and Spatial-Temporal Context Descriptors for Action Recognition[C]. 见:2013 24th British Machine Vision Conference, BMVC 2013. Bristol, United kingdom. |
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。