Real-Time Action Recognition With Deeply Transferred Motion Vector CNNs.
文献类型：期刊论文
| 作者 | Zhang, Bowen; Wang, Limin; Wang, Zhe; Qiao, Yu; Wang, Hanli |
| 刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
 |
| 出版日期 | 2018 |
| 文献子类 | 期刊论文 |
| 英文摘要 | The two-stream CNNs prove very successful for video-based action recognition. However, the classical two-stream CNNs are time costly, mainly due to the bottleneck of calculating optical flows (OFs). In this paper, we propose a two-stream-based real-time action recognition approach by using motion vector(MV) to replace OF. MVs are encoded in video stream and can be extracted directly without extra calculation. However, directly training CNN with MVs degrades accuracy severely due to the noise and the lack of fine details in MVs. In order to relieve this problem, we propose four training strategies which leverage the knowledge learned from OF CNN to enhance the accuracy of MV CNN. Our insight is that MV and OF share inherent similar structures which allow us to transfer knowledge from one domain to another. To fully utilize the knowledge learned in OF domain, we develop deeply transferred MV CNN. Experimental results on various datasets show the effectiveness of our training strategies. Our approach is significantly faster than OF based approaches and achieves processing speed of 390.7 frames per second, surpassing real-time requirement. We release our model and code to facilitate further research. |
| URL标识 | 查看原文 |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/13468]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 推荐引用方式 GB/T 7714 | Zhang, Bowen,Wang, Limin,Wang, Zhe,et al. Real-Time Action Recognition With Deeply Transferred Motion Vector CNNs.[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018. |
| APA | Zhang, Bowen,Wang, Limin,Wang, Zhe,Qiao, Yu,&Wang, Hanli.(2018).Real-Time Action Recognition With Deeply Transferred Motion Vector CNNs..IEEE TRANSACTIONS ON IMAGE PROCESSING. |
| MLA | Zhang, Bowen,et al."Real-Time Action Recognition With Deeply Transferred Motion Vector CNNs.".IEEE TRANSACTIONS ON IMAGE PROCESSING (2018). |
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。