| dmlc/gluon-cv |
5,422 |
|
15 |
46 |
about 3 years ago |
1,535 |
February 03, 2023 |
61 |
apache-2.0 |
Python |
| Gluon CV Toolkit |
| open-mmlab/mmaction2 |
4,904 |
|
0 |
1 |
over 1 year ago |
28 |
October 12, 2023 |
242 |
apache-2.0 |
Python |
| OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark |
| kenshohara/3D-ResNets-PyTorch |
2,677 |
|
0 |
0 |
about 5 years ago |
0 |
|
120 |
mit |
Python |
| 3D ResNets for Action Recognition (CVPR 2018) |
| open-mmlab/mmskeleton |
2,604 |
|
0 |
0 |
over 3 years ago |
0 |
|
193 |
apache-2.0 |
Python |
| A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis. |
| axinc-ai/ailia-models |
1,708 |
|
0 |
0 |
about 2 years ago |
0 |
|
297 |
|
Python |
| The collection of pre-trained, state-of-the-art AI models for ailia SDK |
| open-mmlab/mmaction |
1,415 |
|
0 |
0 |
over 5 years ago |
0 |
|
38 |
apache-2.0 |
Python |
| An open-source toolbox for action understanding based on PyTorch |
| openvinotoolkit/training_extensions |
1,111 |
|
0 |
1 |
about 2 years ago |
55 |
October 31, 2023 |
54 |
apache-2.0 |
Python |
| Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™ |
| MCG-NJU/VideoMAE |
864 |
|
0 |
0 |
almost 3 years ago |
0 |
|
21 |
other |
Python |
| [NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training |
| jeffreyyihuang/two-stream-action-recognition |
835 |
|
0 |
0 |
over 6 years ago |
0 |
|
30 |
mit |
Python |
| Using two stream architecture to implement a classic action recognition method on UCF101 dataset |
| kennymckormick/pyskl |
763 |
|
0 |
0 |
over 2 years ago |
0 |
|
63 |
apache-2.0 |
Python |
| A toolbox for skeleton-based action recognition. |
