Actionness Estimation Using Hybrid Fully Convolutional Networks
文献类型：会议论文
| 作者 | Limin Wang; Yu Qiao; Xiaoou Tang; Luc Van Goo |
| 出版日期 | 2016 |
| 会议名称 | CVPR2016 |
| 会议地点 | 美国 |
| 英文摘要 | Actionness [3] was introduced to quantify the likelihood of containing a generic action instance at a specific lo- cation. Accurate and efficient estimation of actionness is important in video analysis and may benefit other rele- vant tasks such as action recognition and action detection. This paper presents a new deep architecture for actionness estimation, called hybrid fully convolutional network (H- FCN), which is composed of appearance FCN (A-FCN) and motion FCN (M-FCN). These two FCNs leverage the strong capacity of deep models to estimate actionness maps from the perspectives of static appearance and dynamic mo- tion, respectively. In addition, the fully convolutional na- ture of H-FCN allows it to efficiently process videos with arbitrary sizes. Experiments are conducted on the chal- lenging datasets of Stanford40, UCF Sports, and JHMDB to verify the effectiveness of H-FCN on actionness estima- tion, which demonstrate that our method achieves superior performance to previous ones. Moreover, we apply the esti- mated actionness maps on action proposal generation and action detection. Our actionness maps advance the current state-of-the-art performance of these tasks substantially. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/10005]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2016 |
| 推荐引用方式 GB/T 7714 | Limin Wang,Yu Qiao,Xiaoou Tang,et al. Actionness Estimation Using Hybrid Fully Convolutional Networks[C]. 见:CVPR2016. 美国. |
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。