Real-Time Action Recognition with Deeply-Transferred Motion Vector CNNs.
IEEE Transactions on Image Processing(2018)
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...
更多查看译文
关键词
Optical imaging,Feature extraction,Real-time systems,Machine learning,Streaming media,Image recognition,Training
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络