CUHK&SIAT Submission for THUMOS15 Action Recognition Challenge
文献类型：会议论文
| 作者 | limin wang; zhe wang; yuanjun xiong; yu qiao |
| 出版日期 | 2015 |
| 会议名称 | CVPR 2015 workshop |
| 会议地点 | 美国波士顿 |
| 英文摘要 | This paper presents the method of our submission for THUMOS15 action recognition challenge. We propose a new action recognition system by exploiting very deep two- stream ConvNets and Fisher vector representation of iDT features. Specifically, we utilize those successful very deep architectures in images such as GoogLeNet and VGGNet to design the two-stream ConvNets. From our experiments, we see that deeper architectures obtain higher performance for spatial nets. However, for temporal net, deeper archi- tectures could not yield better recognition accuracy. We an- alyze that the UCF101 dataset is relatively very small and it is very hard to train such deep networks on the current ac- tion datasets. Compared with traditional iDT features, our implemented two-stream ConvNets significantly outperfor- m them. We further combine the recognition scores of both two-stream ConvNets and iDT features, and achieve 68% mAP value on the validation dataset of THUMOS15. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6712]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2015 |
| 推荐引用方式 GB/T 7714 | limin wang,zhe wang,yuanjun xiong,et al. CUHK&SIAT Submission for THUMOS15 Action Recognition Challenge[C]. 见:CVPR 2015 workshop. 美国波士顿. |
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。