Xiaomin Pei, Huijie Fan, Yandong Tang. Two-person interaction recognition based on multi-stream spatio-temporal fusion network[J]. Infrared and Laser Engineering, 2020, 49(5): 20190552
- Infrared and Laser Engineering
- Vol. 49, Issue 5, 20190552 (2020)
Fig. 1. Two person action skeletons
Fig. 2. Spatial feature learning
Fig. 3. Multi-stream spatio-temporal fusion network
Fig. 4. Multi-stream spatio-temporal fusion model classification accuracy for cross subject
Fig. 5. Multi-stream spatio-temporal fusion model classification
|
Table 1. Accuracy for human action recognition for NTU-RGBD dataset
|
Table 2. Human action recognition accuracy for SBU dataset
|
Table 3. Comparison of the network structure
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