Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification
Ali Diba, Ali Mohammad Pazandeh, Luc Van Gool
Aug 31, 2016 (modified: Aug 31, 2016)ECCV2016 BNMW submissionreaders: everyone
Submit for proceedings:no
Abstract:The video and action classification have extremely evolved by deep neural networks specially with two stream CNN using RGB and optical flow as inputs and they present outstanding performance in terms of video analysis. One of the shortcoming of these methods is handling motion information extraction which is done out side of the CNNs and relatively time consuming also on GPUs. So proposing end-to-end methods which are exploring to learn motion representation, like 3D-CNN can achieve faster and accurate performance.
We present some novel deep CNNs using 3D architecture to model actions and motion representation in an efficient way to be accurate and also as fast as real-time. Our new networks learn distinctive models to combine deep motion features into appearance model via learning optical flow features inside the network.