Qinghui Li, Aihua Li, Tao Wang, Zhigao Cui. Double-Stream Convolutional Networks with Sequential Optical Flow Image for Action Recognition[J]. Acta Optica Sinica, 2018, 38(6): 0615002
- Acta Optica Sinica
- Vol. 38, Issue 6, 0615002 (2018)
Fig. 1. (a) Original video frames; (b) optical flow images; (c) sequential optical flow images
Fig. 2. Double-stream network framework fusing appearance information and motion information
Fig. 3. Results of different subsequence lengths
|
Table 1. Recognition accuracy of HMDB51%
|
Table 2. Recognition accuracy of UCF101%
|
Table 3. Recognition accuracy of different convolutional networks%
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 4. TOP10 categories of accuracy improvement%
| ||||||||||||||||||||||||||||||
Table 5. Comparison of recognition accuracy for different methods%
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20