|
| 1 | +<!-- [ALGORITHM] --> |
| 2 | + |
| 3 | +<details> |
| 4 | +<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-030-58580-8_27">RTMPose (arXiv'2023)</a></summary> |
| 5 | + |
| 6 | +```bibtex |
| 7 | +@misc{https://doi.org/10.48550/arxiv.2303.07399, |
| 8 | + doi = {10.48550/ARXIV.2303.07399}, |
| 9 | + url = {https://arxiv.org/abs/2303.07399}, |
| 10 | + author = {Jiang, Tao and Lu, Peng and Zhang, Li and Ma, Ningsheng and Han, Rui and Lyu, Chengqi and Li, Yining and Chen, Kai}, |
| 11 | + keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences}, |
| 12 | + title = {RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose}, |
| 13 | + publisher = {arXiv}, |
| 14 | + year = {2023}, |
| 15 | + copyright = {Creative Commons Attribution 4.0 International} |
| 16 | +} |
| 17 | +
|
| 18 | +``` |
| 19 | + |
| 20 | +</details> |
| 21 | + |
| 22 | +<!-- [BACKBONE] --> |
| 23 | + |
| 24 | +<details> |
| 25 | +<summary align="right"><a href="https://arxiv.org/abs/2212.07784">RTMDet (arXiv'2022)</a></summary> |
| 26 | + |
| 27 | +```bibtex |
| 28 | +@misc{lyu2022rtmdet, |
| 29 | + title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors}, |
| 30 | + author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen}, |
| 31 | + year={2022}, |
| 32 | + eprint={2212.07784}, |
| 33 | + archivePrefix={arXiv}, |
| 34 | + primaryClass={cs.CV} |
| 35 | +} |
| 36 | +``` |
| 37 | + |
| 38 | +</details> |
| 39 | + |
| 40 | +<!-- [DATASET] --> |
| 41 | + |
| 42 | +<details> |
| 43 | +<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-319-10602-1_48">COCO (ECCV'2014)</a></summary> |
| 44 | + |
| 45 | +```bibtex |
| 46 | +@inproceedings{lin2014microsoft, |
| 47 | + title={Microsoft coco: Common objects in context}, |
| 48 | + author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence}, |
| 49 | + booktitle={European conference on computer vision}, |
| 50 | + pages={740--755}, |
| 51 | + year={2014}, |
| 52 | + organization={Springer} |
| 53 | +} |
| 54 | +``` |
| 55 | + |
| 56 | +</details> |
| 57 | + |
| 58 | +- Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset. |
| 59 | +- `*` denotes model trained on 7 public datasets: |
| 60 | + - [AI Challenger](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#aic) |
| 61 | + - [MS COCO](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#coco) |
| 62 | + - [CrowdPose](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#crowdpose) |
| 63 | + - [MPII](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#mpii) |
| 64 | + - [sub-JHMDB](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#sub-jhmdb-dataset) |
| 65 | + - [Halpe](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_wholebody_keypoint.html#halpe) |
| 66 | + - [PoseTrack18](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#posetrack18) |
| 67 | +- `Body8` denotes the addition of the [OCHuman](https://mmpose.readthedocs.io/en/latest/dataset_zoo/2d_body_keypoint.html#ochuman) dataset, in addition to the 7 datasets mentioned above, for evaluation. |
| 68 | + |
| 69 | +| Config | Input Size | AP<sup><br>(COCO) | PCK@0.1<sup><br>(Body8) | AUC<sup><br>(Body8) | EPE<sup><br>(Body8) | Params(M) | FLOPS(G) | Download | |
| 70 | +| :--------------------------------------------: | :--------: | :---------------: | :---------------------: | :-----------------: | :-----------------: | :-------: | :------: | :-----------------------------------------------: | |
| 71 | +| [RTMPose-t\*](/configs/body_2d_keypoint/rtmpose/body8/rtmpose-t_8xb256-210e_body8-256x192.py) | 256x192 | 65.9 | 91.44 | 63.18 | 19.45 | 3.34 | 0.36 | [Model](https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-t_simcc-body7_pt-body7_420e-256x192-026a1439_20230504.pth) | |
| 72 | +| [RTMPose-s\*](/configs/body_2d_keypoint/rtmpose/body8/rtmpose-s_8xb256-210e_body8-256x192.py) | 256x192 | 69.7 | 92.45 | 65.15 | 17.85 | 5.47 | 0.68 | [Model](https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-s_simcc-body7_pt-body7_420e-256x192-acd4a1ef_20230504.pth) | |
| 73 | +| [RTMPose-m\*](/configs/body_2d_keypoint/rtmpose/body8/rtmpose-m_8xb256-210e_body8-256x192.py) | 256x192 | 74.9 | 94.25 | 68.59 | 15.12 | 13.59 | 1.93 | [Model](https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth) | |
| 74 | +| [RTMPose-l\*](/configs/body_2d_keypoint/rtmpose/body8/rtmpose-l_8xb256-210e_body8-256x192.py) | 256x192 | 76.7 | 95.08 | 70.14 | 13.79 | 27.66 | 4.16 | [Model](https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-l_simcc-body7_pt-body7_420e-256x192-4dba18fc_20230504.pth) | |
| 75 | +| [RTMPose-m\*](/configs/body_2d_keypoint/rtmpose/body8/rtmpose-m_8xb256-210e_body8-384x288.py) | 384x288 | 76.6 | 94.64 | 70.38 | 13.98 | 13.72 | 4.33 | [Model](https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-384x288-65e718c4_20230504.pth) | |
| 76 | +| [RTMPose-l\*](/configs/body_2d_keypoint/rtmpose/body8/rtmpose-l_8xb256-210e_body8-384x288.py) | 384x288 | 78.3 | 95.36 | 71.58 | 13.08 | 27.79 | 9.35 | [Model](https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-l_simcc-body7_pt-body7_420e-384x288-3f5a1437_20230504.pth) | |
0 commit comments