3d Convolutional Neural Network With Multi-Model Framework For Action Recognition
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)(2017)
摘要
In this paper, we propose an efficient and effective action recognition framework by combining multiple feature models from dynamic image, optical flow and raw frame, with 3D convolutional neural network (CNN). Dynamic image preserves the long-term temporal information, while optical flow captures short-term temporal information, and raw frame represents the appearance information. Experiments demonstrate that dynamic image provides complementary information to raw frame feature and optical flow feature. Furthermore, with the approximate rank pooling, the computation of dynamic images is about 360 times faster than optical flow, and the dynamic image requires far less memory than optical flow and raw frame.
更多查看译文
关键词
Action Recognition, 3D Convolutional Neural Network, Video Classification
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络