Title | ||
---|---|---|
Image representation of pose-transition feature for 3D skeleton-based action recognition |
Abstract | ||
---|---|---|
•An efficient 3D skeleton-based action recognition using Deep CNNs.•A novel encoding technique to transform pose-transition feature to image.•Fine-tuning an action recognition model with the generated data of action images.•Outstanding recognition accuracy on different challenging 3D action dataset.•Outperformance of accuracy with other deep learning-based approaches. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.ins.2019.10.047 | Information Sciences |
Keywords | Field | DocType |
Pose-transition feature to image (PoT2I) encoding technique,Depth camera,Human action recognition,Deep convolutional neural networks | Pattern recognition,Convolutional neural network,Image representation,Action recognition,RGB color model,Artificial intelligence,Machine learning,Mathematics,Encoding (memory),Color image | Journal |
Volume | ISSN | Citations |
513 | 0020-0255 | 6 |
PageRank | References | Authors |
0.49 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thien Huynh-The | 1 | 94 | 21.54 |
Cam-Hao Hua | 2 | 45 | 11.22 |
Trung-Thanh Ngo | 3 | 6 | 0.49 |
Dong-Seong Kim | 4 | 64 | 28.80 |