Body 2D Keypoint

---

Body7 Dataset

Rtmo + Rtmo on Body7

RTMO

@misc{lu2023rtmo,
      title={{RTMO}: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation},
      author={Peng Lu and Tao Jiang and Yining Li and Xiangtai Li and Kai Chen and Wenming Yang},
      year={2023},
      eprint={2312.07526},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

AI Challenger (ArXiv'2017)

@article{wu2017ai,
  title={Ai challenger: A large-scale dataset for going deeper in image understanding},
  author={Wu, Jiahong and Zheng, He and Zhao, Bo and Li, Yixin and Yan, Baoming and Liang, Rui and Wang, Wenjia and Zhou, Shipei and Lin, Guosen and Fu, Yanwei and others},
  journal={arXiv preprint arXiv:1711.06475},
  year={2017}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

CrowdPose (CVPR'2019)

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

JHMDB (ICCV'2013)

@inproceedings{Jhuang:ICCV:2013,
  title = {Towards understanding action recognition},
  author = {H. Jhuang and J. Gall and S. Zuffi and C. Schmid and M. J. Black},
  booktitle = {International Conf. on Computer Vision (ICCV)},
  month = Dec,
  pages = {3192-3199},
  year = {2013}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

PoseTrack18 (CVPR'2018)

@inproceedings{andriluka2018posetrack,
  title={Posetrack: A benchmark for human pose estimation and tracking},
  author={Andriluka, Mykhaylo and Iqbal, Umar and Insafutdinov, Eldar and Pishchulin, Leonid and Milan, Anton and Gall, Juergen and Schiele, Bernt},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={5167--5176},
  year={2018}
}

Halpe (CVPR'2020)

@inproceedings{li2020pastanet,
  title={PaStaNet: Toward Human Activity Knowledge Engine},
  author={Li, Yong-Lu and Xu, Liang and Liu, Xinpeng and Huang, Xijie and Xu, Yue and Wang, Shiyi and Fang, Hao-Shu and Ma, Ze and Chen, Mingyang and Lu, Cewu},
  booktitle={CVPR},
  year={2020}
}

Results on COCO val2017

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log	onnx
RTMO-t	640x640	0.574	0.803	0.613	0.611	0.836	ckpt	log	onnx
RTMO-s	640x640	0.686	0.879	0.744	0.723	0.908	ckpt	log	onnx
RTMO-m	640x640	0.726	0.899	0.790	0.763	0.926	ckpt	log	onnx
RTMO-l	640x640	0.748	0.911	0.813	0.786	0.939	ckpt	log	onnx

---

Crowdpose Dataset

Rtmo + Rtmo on Crowdpose

RTMO

@misc{lu2023rtmo,
      title={{RTMO}: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation},
      author={Peng Lu and Tao Jiang and Yining Li and Xiangtai Li and Kai Chen and Wenming Yang},
      year={2023},
      eprint={2312.07526},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

CrowdPose (CVPR'2019)

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

Results on COCO val2017

Arch	Input Size	AP	AP50	AP75	AP (E)	AP (M)	AP (H)	ckpt	log
RTMO-s	640x640	0.673	0.882	0.729	0.737	0.682	0.591	ckpt	log
RTMO-m	640x640	0.711	0.897	0.771	0.774	0.719	0.634	ckpt	log
RTMO-l	640x640	0.732	0.907	0.793	0.792	0.741	0.653	ckpt	log
RTMO-l*	640x640	0.838	0.947	0.893	0.888	0.847	0.772	ckpt	log

* indicates the model is trained using a combined dataset composed of AI Challenger, COCO, CrowdPose, Halpe, MPII, PoseTrack18 and sub-JHMDB.

Dekr + Hrnet on Crowdpose

DEKR (CVPR'2021)

@inproceedings{geng2021bottom,
  title={Bottom-up human pose estimation via disentangled keypoint regression},
  author={Geng, Zigang and Sun, Ke and Xiao, Bin and Zhang, Zhaoxiang and Wang, Jingdong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={14676--14686},
  year={2021}
}

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

CrowdPose (CVPR'2019)

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

Results on CrowdPose test without multi-scale test

Arch	Input Size	AP	AP50	AP75	AP (E)	AP (M)	AP (H)	ckpt	log
HRNet-w32	512x512	0.663	0.857	0.714	0.740	0.671	0.576	ckpt	log
HRNet-w48	640x640	0.679	0.869	0.731	0.753	0.688	0.593	ckpt	log

Topdown Heatmap + Cspnext + Udp on Crowdpose

RTMDet (ArXiv 2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

UDP (CVPR'2020)

@InProceedings{Huang_2020_CVPR,
  author = {Huang, Junjie and Zhu, Zheng and Guo, Feng and Huang, Guan},
  title = {The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation},
  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2020}
}

CrowdPose (CVPR'2019)

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

Results on CrowdPose test with YOLOv3 human detector

Arch	Input Size	AP	AP50	AP75	AP (E)	AP (M)	AP (H)	ckpt	log
pose_cspnext_m	256x192	0.662	0.821	0.723	0.759	0.675	0.539	ckpt	log

Topdown Heatmap + Hrnet on Crowdpose

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

CrowdPose (CVPR'2019)

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

Results on CrowdPose test with YOLOv3 human detector

Arch	Input Size	AP	AP50	AP75	AP (E)	AP (M)	AP (H)	ckpt	log
pose_hrnet_w32	256x192	0.675	0.825	0.729	0.770	0.687	0.553	ckpt	log

Topdown Heatmap + Resnet on Crowdpose

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

CrowdPose (CVPR'2019)

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

Results on CrowdPose test with YOLOv3 human detector

Arch	Input Size	AP	AP50	AP75	AP (E)	AP (M)	AP (H)	ckpt	log
pose_resnet_50	256x192	0.637	0.808	0.692	0.738	0.650	0.506	ckpt	log
pose_resnet_101	256x192	0.647	0.810	0.703	0.745	0.658	0.521	ckpt	log
pose_resnet_101	320x256	0.661	0.821	0.714	0.759	0.672	0.534	ckpt	log
pose_resnet_152	256x192	0.656	0.818	0.712	0.754	0.666	0.533	ckpt	log

Rtmpose + Rtmpose on Crowdpose

RTMPose (arXiv'2023)

@misc{https://doi.org/10.48550/arxiv.2303.07399,
  doi = {10.48550/ARXIV.2303.07399},
  url = {https://arxiv.org/abs/2303.07399},
  author = {Jiang, Tao and Lu, Peng and Zhang, Li and Ma, Ningsheng and Han, Rui and Lyu, Chengqi and Li, Yining and Chen, Kai},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}

RTMDet (arXiv'2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

CrowdPose (CVPR'2019)

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}

Results on CrowdPose test with YOLOv3 human detector

Arch	Input Size	AP	AP50	AP75	AP (E)	AP (M)	AP (H)	ckpt	log
rtmpose-m	256x192	0.706	0.841	0.765	0.799	0.719	0.582	ckpt	log

---

Coco Dataset

Rtmo + Rtmo on Coco

RTMO

@misc{lu2023rtmo,
      title={{RTMO}: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation},
      author={Peng Lu and Tao Jiang and Yining Li and Xiangtai Li and Kai Chen and Wenming Yang},
      year={2023},
      eprint={2312.07526},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
RTMO-s	640x640	0.677	0.878	0.737	0.715	0.908	ckpt	log
RTMO-m	640x640	0.709	0.890	0.778	0.747	0.920	ckpt	log
RTMO-l	640x640	0.724	0.899	0.788	0.762	0.927	ckpt	log

Integral Regression + Resnet + Debias on Coco

Debias IPR (ICCV'2021)

@inproceedings{gu2021removing,
    title={Removing the Bias of Integral Pose Regression},
    author={Gu, Kerui and Yang, Linlin and Yao, Angela},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={11067--11076},
    year={2021}
  }

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
debias-ipr_resnet_50	256x256	0.675	0.872	0.740	0.765	0.928	ckpt	log

Integral Regression + Resnet + DSNT on Coco

DSNT (2018)

@article{nibali2018numerical,
  title={Numerical Coordinate Regression with Convolutional Neural Networks},
  author={Nibali, Aiden and He, Zhen and Morgan, Stuart and Prendergast, Luke},
  journal={arXiv preprint arXiv:1801.07372},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
ipr_resnet_50_dsnt	256x256	0.674	0.870	0.744	0.764	0.928	ckpt	log

Integral Regression + Resnet + Ipr on Coco

IPR (ECCV'2018)

@inproceedings{sun2018integral,
  title={Integral human pose regression},
  author={Sun, Xiao and Xiao, Bin and Wei, Fangyin and Liang, Shuang and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={529--545},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
ipr_resnet_50	256x256	0.633	0.860	0.703	0.730	0.919	ckpt	log

Edpose + Edpose on Coco

ED-Pose (ICLR'2023)

@inproceedings{
yang2023explicit,
title={Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation},
author={Jie Yang and Ailing Zeng and Shilong Liu and Feng Li and Ruimao Zhang and Lei Zhang},
booktitle={International Conference on Learning Representations},
year={2023},
url={https://openreview.net/forum?id=s4WVupnJjmX}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017.

Arch	BackBone	AP	AP50	AP75	AR	AR50	ckpt	log
edpose_res50_coco	ResNet-50	0.716	0.897	0.783	0.793	0.943	ckpt	log

The checkpoint is converted from the official repo. The training of EDPose is not supported yet. It will be supported in the future updates.

The above config follows Pure Python style. Please install mmengine>=0.8.2 to use this config.

Topdown Regression + Mobilenetv2 + Rle on Coco

DeepPose (CVPR'2014)

@inproceedings{toshev2014deeppose,
  title={Deeppose: Human pose estimation via deep neural networks},
  author={Toshev, Alexander and Szegedy, Christian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1653--1660},
  year={2014}
}

RLE (ICCV'2021)

@inproceedings{li2021human,
  title={Human pose regression with residual log-likelihood estimation},
  author={Li, Jiefeng and Bian, Siyuan and Zeng, Ailing and Wang, Can and Pang, Bo and Liu, Wentao and Lu, Cewu},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={11025--11034},
  year={2021}
}

MobilenetV2 (CVPR'2018)

@inproceedings{sandler2018mobilenetv2,
  title={Mobilenetv2: Inverted residuals and linear bottlenecks},
  author={Sandler, Mark and Howard, Andrew and Zhu, Menglong and Zhmoginov, Andrey and Chen, Liang-Chieh},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={4510--4520},
  year={2018}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
deeppose_mobilenetv2_rle_pretrained	256x192	0.593	0.836	0.660	0.644	0.877	ckpt	log

Topdown Regression + Resnet on Coco

DeepPose (CVPR'2014)

@inproceedings{toshev2014deeppose,
  title={Deeppose: Human pose estimation via deep neural networks},
  author={Toshev, Alexander and Szegedy, Christian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1653--1660},
  year={2014}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
deeppose_resnet_50	256x192	0.541	0.824	0.601	0.649	0.893	ckpt	log
deeppose_resnet_101	256x192	0.562	0.831	0.629	0.670	0.900	ckpt	log
deeppose_resnet_152	256x192	0.584	0.842	0.659	0.688	0.907	ckpt	log

Topdown Regression + Resnet + Rle on Coco

DeepPose (CVPR'2014)

@inproceedings{toshev2014deeppose,
  title={Deeppose: Human pose estimation via deep neural networks},
  author={Toshev, Alexander and Szegedy, Christian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1653--1660},
  year={2014}
}

RLE (ICCV'2021)

@inproceedings{li2021human,
  title={Human pose regression with residual log-likelihood estimation},
  author={Li, Jiefeng and Bian, Siyuan and Zeng, Ailing and Wang, Can and Pang, Bo and Liu, Wentao and Lu, Cewu},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={11025--11034},
  year={2021}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
deeppose_resnet_50_rle	256x192	0.706	0.888	0.776	0.753	0.924	ckpt	log
deeppose_resnet_50_rle_pretrained	256x192	0.719	0.891	0.788	0.764	0.925	ckpt	log
deeppose_resnet_101_rle	256x192	0.722	0.894	0.794	0.768	0.930	ckpt	log
deeppose_resnet_152_rle	256x192	0.731	0.897	0.805	0.777	0.933	ckpt	log
deeppose_resnet_152_rle	384x288	0.749	0.901	0.815	0.793	0.935	ckpt	log

Dekr + Hrnet on Coco

DEKR (CVPR'2021)

@inproceedings{geng2021bottom,
  title={Bottom-up human pose estimation via disentangled keypoint regression},
  author={Geng, Zigang and Sun, Ke and Xiao, Bin and Zhang, Zhaoxiang and Wang, Jingdong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={14676--14686},
  year={2021}
}

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 without multi-scale test

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
HRNet-w32	512x512	0.686	0.868	0.750	0.735	0.898	ckpt	log
HRNet-w48	640x640	0.714	0.883	0.777	0.762	0.915	ckpt	log

Yoloxpose + Yoloxpose on Coco

YOLO-Pose (CVPRW'2022)

@inproceedings{maji2022yolo,
  title={Yolo-pose: Enhancing yolo for multi person pose estimation using object keypoint similarity loss},
  author={Maji, Debapriya and Nagori, Soyeb and Mathew, Manu and Poddar, Deepak},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={2637--2646},
  year={2022}
}

YOLOX

@article{ge2021yolox,
  title={Yolox: Exceeding yolo series in 2021},
  author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
  journal={arXiv preprint arXiv:2107.08430},
  year={2021}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
yoloxpose_tiny	416x416	0.526	0.793	0.556	0.571	0.833	ckpt	log
yoloxpose_s	640x640	0.641	0.872	0.702	0.682	0.902	ckpt	log
yoloxpose_m	640x640	0.695	0.899	0.766	0.733	0.926	ckpt	log
yoloxpose_l	640x640	0.712	0.901	0.782	0.749	0.926	ckpt	log

Simcc + Vipnas on Coco

SimCC (ECCV'2022)

@misc{https://doi.org/10.48550/arxiv.2107.03332,
  title={SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation},
  author={Li, Yanjie and Yang, Sen and Liu, Peidong and Zhang, Shoukui and Wang, Yunxiao and Wang, Zhicheng and Yang, Wankou and Xia, Shu-Tao},
  year={2021}
}

ViPNAS (CVPR'2021)

@article{xu2021vipnas,
  title={ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search},
  author={Xu, Lumin and Guan, Yingda and Jin, Sheng and Liu, Wentao and Qian, Chen and Luo, Ping and Ouyang, Wanli and Wang, Xiaogang},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  year={2021}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
simcc_S-ViPNAS-MobileNetV3	256x192	0.695	0.883	0.772	0.755	0.927	ckpt	log

Simcc + Mobilenetv2 on Coco

SimCC (ECCV'2022)

@misc{https://doi.org/10.48550/arxiv.2107.03332,
  title={SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation},
  author={Li, Yanjie and Yang, Sen and Liu, Peidong and Zhang, Shoukui and Wang, Yunxiao and Wang, Zhicheng and Yang, Wankou and Xia, Shu-Tao},
  year={2021}
}

MobilenetV2 (CVPR'2018)

@inproceedings{sandler2018mobilenetv2,
  title={Mobilenetv2: Inverted residuals and linear bottlenecks},
  author={Sandler, Mark and Howard, Andrew and Zhu, Menglong and Zhmoginov, Andrey and Chen, Liang-Chieh},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={4510--4520},
  year={2018}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
simcc_mobilenetv2_wo_deconv	256x192	0.620	0.855	0.697	0.678	0.902	ckpt	log

Simcc + Resnet on Coco

SimCC (ECCV'2022)

@misc{https://doi.org/10.48550/arxiv.2107.03332,
  title={SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation},
  author={Li, Yanjie and Yang, Sen and Liu, Peidong and Zhang, Shoukui and Wang, Yunxiao and Wang, Zhicheng and Yang, Wankou and Xia, Shu-Tao},
  year={2021}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
simcc_resnet_50	256x192	0.721	0.897	0.798	0.781	0.937	ckpt	log
simcc_resnet_50	384x288	0.735	0.899	0.800	0.790	0.939	ckpt	log

Topdown Heatmap + Hrnet + Aic on Coco

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

AI Challenger (ArXiv'2017)

@article{wu2017ai,
  title={Ai challenger: A large-scale dataset for going deeper in image understanding},
  author={Wu, Jiahong and Zheng, He and Zhao, Bo and Li, Yixin and Yan, Baoming and Liang, Rui and Wang, Wenjia and Zhou, Shipei and Lin, Guosen and Fu, Yanwei and others},
  journal={arXiv preprint arXiv:1711.06475},
  year={2017}
}

MMPose supports training model with combined datasets. coco-aic-merge and coco-aic-combine are two examples.

• coco-aic-merge leverages AIC data with partial keypoints as auxiliary data to train a COCO model

• coco-aic-combine constructs a combined dataset whose keypoints are the union of COCO and AIC keypoints to train a model that predicts keypoints of both datasets.

Evaluation results on COCO val2017 of models trained with solely COCO dataset and combined dataset as shown below. These models are evaluated with detector having human AP of 56.4 on COCO val2017 dataset.

Train Set	Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
coco	pose_hrnet_w32	256x192	0.749	0.906	0.821	0.804	0.945	ckpt	log
coco-aic-merge	pose_hrnet_w32	256x192	0.756	0.907	0.828	0.809	0.944	ckpt	log
coco-aic-combine	pose_hrnet_w32	256x192	0.755	0.904	0.825	0.807	0.942	ckpt	log

Topdown Heatmap + Hourglass on Coco

Hourglass (ECCV'2016)

@inproceedings{newell2016stacked,
  title={Stacked hourglass networks for human pose estimation},
  author={Newell, Alejandro and Yang, Kaiyu and Deng, Jia},
  booktitle={European conference on computer vision},
  pages={483--499},
  year={2016},
  organization={Springer}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hourglass_52	256x256	0.726	0.896	0.799	0.780	0.934	ckpt	log
pose_hourglass_52	384x384	0.746	0.900	0.812	0.797	0.939	ckpt	log

Topdown Heatmap + Hrformer on Coco

HRFormer (NIPS'2021)

@article{yuan2021hrformer,
  title={HRFormer: High-Resolution Vision Transformer for Dense Predict},
  author={Yuan, Yuhui and Fu, Rao and Huang, Lang and Lin, Weihong and Zhang, Chao and Chen, Xilin and Wang, Jingdong},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  year={2021}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrformer_small	256x192	0.738	0.904	0.812	0.793	0.941	ckpt	log
pose_hrformer_small	384x288	0.757	0.905	0.824	0.807	0.941	ckpt	log
pose_hrformer_base	256x192	0.754	0.906	0.827	0.807	0.943	ckpt	log
pose_hrformer_base	384x288	0.774	0.909	0.842	0.823	0.945	ckpt	log

Topdown Heatmap + Hrnet on Coco

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32	256x192	0.749	0.906	0.821	0.804	0.945	ckpt	log
pose_hrnet_w32	384x288	0.761	0.908	0.826	0.811	0.944	ckpt	log
pose_hrnet_w48	256x192	0.756	0.908	0.826	0.809	0.945	ckpt	log
pose_hrnet_w48	384x288	0.767	0.911	0.832	0.817	0.947	ckpt	log

Topdown Heatmap + Vipnas on Coco

ViPNAS (CVPR'2021)

@article{xu2021vipnas,
  title={ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search},
  author={Xu, Lumin and Guan, Yingda and Jin, Sheng and Liu, Wentao and Qian, Chen and Luo, Ping and Ouyang, Wanli and Wang, Xiaogang},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  year={2021}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
S-ViPNAS-MobileNetV3	256x192	0.700	0.887	0.783	0.758	0.929	ckpt	log
S-ViPNAS-Res50	256x192	0.711	0.894	0.787	0.769	0.934	ckpt	log

Topdown Heatmap + Resnext on Coco

ResNext (CVPR'2017)

@inproceedings{xie2017aggregated,
  title={Aggregated residual transformations for deep neural networks},
  author={Xie, Saining and Girshick, Ross and Doll{\'a}r, Piotr and Tu, Zhuowen and He, Kaiming},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1492--1500},
  year={2017}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnext_50	256x192	0.715	0.897	0.791	0.771	0.935	ckpt	log
pose_resnext_50	384x288	0.724	0.899	0.794	0.777	0.936	ckpt	log
pose_resnext_101	256x192	0.726	0.900	0.801	0.781	0.939	ckpt	log
pose_resnext_101	384x288	0.744	0.903	0.815	0.794	0.939	ckpt	log
pose_resnext_152	256x192	0.730	0.903	0.808	0.785	0.940	ckpt	log
pose_resnext_152	384x288	0.742	0.904	0.810	0.794	0.940	ckpt	log

Topdown Heatmap + CPM on Coco

CPM (CVPR'2016)

@inproceedings{wei2016convolutional,
  title={Convolutional pose machines},
  author={Wei, Shih-En and Ramakrishna, Varun and Kanade, Takeo and Sheikh, Yaser},
  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
  pages={4724--4732},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
cpm	256x192	0.627	0.862	0.709	0.689	0.906	ckpt	log
cpm	384x288	0.652	0.865	0.730	0.710	0.907	ckpt	log

Topdown Heatmap + Shufflenetv2 on Coco

ShufflenetV2 (ECCV'2018)

@inproceedings{ma2018shufflenet,
  title={Shufflenet v2: Practical guidelines for efficient cnn architecture design},
  author={Ma, Ningning and Zhang, Xiangyu and Zheng, Hai-Tao and Sun, Jian},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={116--131},
  year={2018}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_shufflenetv2	256x192	0.602	0.857	0.672	0.668	0.902	ckpt	log
pose_shufflenetv2	384x288	0.638	0.866	0.707	0.699	0.910	ckpt	log

Topdown Heatmap + RSN on Coco

RSN (ECCV'2020)

@misc{cai2020learning,
    title={Learning Delicate Local Representations for Multi-Person Pose Estimation},
    author={Yuanhao Cai and Zhicheng Wang and Zhengxiong Luo and Binyi Yin and Angang Du and Haoqian Wang and Xinyu Zhou and Erjin Zhou and Xiangyu Zhang and Jian Sun},
    year={2020},
    eprint={2003.04030},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
rsn_18	256x192	0.704	0.887	0.781	0.773	0.927	ckpt	log
rsn_50	256x192	0.724	0.894	0.799	0.790	0.935	ckpt	log
2xrsn_50	256x192	0.748	0.900	0.821	0.810	0.939	ckpt	log
3xrsn_50	256x192	0.750	0.900	0.824	0.814	0.941	ckpt	log

Topdown Heatmap + Hrnet + Dark on Coco

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

DarkPose (CVPR'2020)

@inproceedings{zhang2020distribution,
  title={Distribution-aware coordinate representation for human pose estimation},
  author={Zhang, Feng and Zhu, Xiatian and Dai, Hanbin and Ye, Mao and Zhu, Ce},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={7093--7102},
  year={2020}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32_dark	256x192	0.757	0.907	0.825	0.807	0.943	ckpt	log
pose_hrnet_w32_dark	384x288	0.766	0.907	0.829	0.815	0.943	ckpt	log
pose_hrnet_w48_dark	256x192	0.764	0.907	0.831	0.814	0.942	ckpt	log
pose_hrnet_w48_dark	384x288	0.772	0.911	0.833	0.821	0.948	ckpt	log

Topdown Heatmap + Resnet + Fp16 on Coco

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

FP16 (ArXiv'2017)

@article{micikevicius2017mixed,
  title={Mixed precision training},
  author={Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and Diamos, Gregory and Elsen, Erich and Garcia, David and Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and Venkatesh, Ganesh and others},
  journal={arXiv preprint arXiv:1710.03740},
  year={2017}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnet_50_fp16	256x192	0.716	0.898	0.798	0.772	0.937	ckpt	log

Topdown Heatmap + Resnetv1d on Coco

ResNetV1D (CVPR'2019)

@inproceedings{he2019bag,
  title={Bag of tricks for image classification with convolutional neural networks},
  author={He, Tong and Zhang, Zhi and Zhang, Hang and Zhang, Zhongyue and Xie, Junyuan and Li, Mu},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={558--567},
  year={2019}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnetv1d_50	256x192	0.722	0.897	0.796	0.777	0.936	ckpt	log
pose_resnetv1d_50	384x288	0.730	0.899	0.800	0.782	0.935	ckpt	log
pose_resnetv1d_101	256x192	0.732	0.901	0.808	0.785	0.940	ckpt	log
pose_resnetv1d_101	384x288	0.748	0.906	0.817	0.798	0.941	ckpt	log
pose_resnetv1d_152	256x192	0.737	0.904	0.814	0.790	0.940	ckpt	log
pose_resnetv1d_152	384x288	0.751	0.907	0.821	0.801	0.942	ckpt	log

Topdown Heatmap + Alexnet on Coco

AlexNet (NeurIPS'2012)

@inproceedings{krizhevsky2012imagenet,
  title={Imagenet classification with deep convolutional neural networks},
  author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
  booktitle={Advances in neural information processing systems},
  pages={1097--1105},
  year={2012}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_alexnet	256x192	0.448	0.767	0.461	0.521	0.829	ckpt	log

Topdown Heatmap + Seresnet on Coco

SEResNet (CVPR'2018)

@inproceedings{hu2018squeeze,
  title={Squeeze-and-excitation networks},
  author={Hu, Jie and Shen, Li and Sun, Gang},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={7132--7141},
  year={2018}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_seresnet_50	256x192	0.729	0.903	0.807	0.784	0.941	ckpt	log
pose_seresnet_50	384x288	0.748	0.904	0.819	0.799	0.941	ckpt	log
pose_seresnet_101	256x192	0.734	0.905	0.814	0.790	0.941	ckpt	log
pose_seresnet_101	384x288	0.754	0.907	0.823	0.805	0.943	ckpt	log
pose_seresnet_152*	256x192	0.730	0.899	0.810	0.787	0.939	ckpt	log
pose_seresnet_152*	384x288	0.753	0.906	0.824	0.806	0.945	ckpt	log

Note that * means without imagenet pre-training.

Topdown Heatmap + Hrnet + Fp16 on Coco

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

FP16 (ArXiv'2017)

@article{micikevicius2017mixed,
  title={Mixed precision training},
  author={Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and Diamos, Gregory and Elsen, Erich and Garcia, David and Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and Venkatesh, Ganesh and others},
  journal={arXiv preprint arXiv:1710.03740},
  year={2017}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32_fp16	256x192	0.749	0.907	0.822	0.802	0.946	ckpt	log

Topdown Heatmap + Shufflenetv1 on Coco

ShufflenetV1 (CVPR'2018)

@inproceedings{zhang2018shufflenet,
  title={Shufflenet: An extremely efficient convolutional neural network for mobile devices},
  author={Zhang, Xiangyu and Zhou, Xinyu and Lin, Mengxiao and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={6848--6856},
  year={2018}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_shufflenetv1	256x192	0.587	0.849	0.654	0.654	0.896	ckpt	log
pose_shufflenetv1	384x288	0.626	0.862	0.696	0.687	0.903	ckpt	log

Topdown Heatmap + Swin on Coco

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

Swin (ICCV'2021)

@inproceedings{liu2021swin,
  title={Swin transformer: Hierarchical vision transformer using shifted windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={10012--10022},
  year={2021}
}

FPN (CVPR'2017)

@inproceedings{lin2017feature,
  title={Feature pyramid networks for object detection},
  author={Lin, Tsung-Yi and Doll{\'a}r, Piotr and Girshick, Ross and He, Kaiming and Hariharan, Bharath and Belongie, Serge},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={2117--2125},
  year={2017}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_swin_t	256x192	0.724	0.901	0.806	0.782	0.940	ckpt	log
pose_swin_b	256x192	0.737	0.904	0.820	0.794	0.942	ckpt	log
pose_swin_b	384x288	0.759	0.910	0.832	0.811	0.946	ckpt	log
pose_swin_l	256x192	0.743	0.906	0.821	0.798	0.943	ckpt	log
pose_swin_l	384x288	0.763	0.912	0.830	0.814	0.949	ckpt	log

Topdown Heatmap + Cspnext + Udp on Coco

RTMDet (ArXiv 2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

UDP (CVPR'2020)

@InProceedings{Huang_2020_CVPR,
  author = {Huang, Junjie and Zhu, Zheng and Guo, Feng and Huang, Guan},
  title = {The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation},
  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2020}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_cspnext_t_udp	256x192	0.665	0.874	0.723	0.723	0.917	ckpt	log
pose_cspnext_s_udp	256x192	0.697	0.886	0.776	0.753	0.929	ckpt	log
pose_cspnext_m_udp	256x192	0.732	0.896	0.806	0.785	0.937	ckpt	log
pose_cspnext_l_udp	256x192	0.750	0.904	0.822	0.800	0.941	ckpt	log
pose_cspnext_t_udp_aic_coco	256x192	0.655	0.884	0.731	0.689	0.890	ckpt	log
pose_cspnext_s_udp_aic_coco	256x192	0.700	0.905	0.783	0.733	0.918	ckpt	log
pose_cspnext_m_udp_aic_coco	256x192	0.748	0.925	0.818	0.777	0.933	ckpt	log
pose_cspnext_l_udp_aic_coco	256x192	0.772	0.936	0.839	0.799	0.943	ckpt	log

Note that, UDP also adopts the unbiased encoding/decoding algorithm of DARK.

Flip test and detector is not used in the result of aic-coco training.

Topdown Heatmap + MSPN on Coco

MSPN (ArXiv'2019)

@article{li2019rethinking,
  title={Rethinking on Multi-Stage Networks for Human Pose Estimation},
  author={Li, Wenbo and Wang, Zhicheng and Yin, Binyi and Peng, Qixiang and Du, Yuming and Xiao, Tianzi and Yu, Gang and Lu, Hongtao and Wei, Yichen and Sun, Jian},
  journal={arXiv preprint arXiv:1901.00148},
  year={2019}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
mspn_50	256x192	0.723	0.895	0.794	0.788	0.934	ckpt	log
2xmspn_50	256x192	0.754	0.903	0.826	0.816	0.942	ckpt	log
3xmspn_50	256x192	0.758	0.904	0.830	0.821	0.943	ckpt	log
4xmspn_50	256x192	0.765	0.906	0.835	0.826	0.943	ckpt	log

Topdown Heatmap + Resnest on Coco

ResNeSt (ArXiv'2020)

@article{zhang2020resnest,
  title={ResNeSt: Split-Attention Networks},
  author={Zhang, Hang and Wu, Chongruo and Zhang, Zhongyue and Zhu, Yi and Zhang, Zhi and Lin, Haibin and Sun, Yue and He, Tong and Muller, Jonas and Manmatha, R. and Li, Mu and Smola, Alexander},
  journal={arXiv preprint arXiv:2004.08955},
  year={2020}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnest_50	256x192	0.720	0.899	0.800	0.775	0.939	ckpt	log
pose_resnest_50	384x288	0.737	0.900	0.811	0.789	0.937	ckpt	log
pose_resnest_101	256x192	0.725	0.900	0.807	0.781	0.939	ckpt	log
pose_resnest_101	384x288	0.745	0.905	0.818	0.798	0.942	ckpt	log
pose_resnest_200	256x192	0.731	0.905	0.812	0.787	0.943	ckpt	log
pose_resnest_200	384x288	0.753	0.907	0.827	0.805	0.943	ckpt	log
pose_resnest_269	256x192	0.737	0.907	0.819	0.792	0.943	ckpt	log
pose_resnest_269	384x288	0.754	0.908	0.828	0.805	0.943	ckpt	log

Topdown Heatmap + Vitpose on Coco

To utilize ViTPose, you’ll need to have MMPreTrain. To install the required version, run the following command:

mim install 'mmpretrain>=1.0.0'

ViTPose (NeurIPS'2022)

@inproceedings{
  xu2022vitpose,
  title={Vi{TP}ose: Simple Vision Transformer Baselines for Human Pose Estimation},
  author={Yufei Xu and Jing Zhang and Qiming Zhang and Dacheng Tao},
  booktitle={Advances in Neural Information Processing Systems},
  year={2022},
}

COCO-WholeBody (ECCV'2020)

@inproceedings{jin2020whole,
  title={Whole-Body Human Pose Estimation in the Wild},
  author={Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  year={2020}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

With classic decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
ViTPose-S	256x192	0.739	0.903	0.816	0.792	0.942	ckpt	log
ViTPose-B	256x192	0.757	0.905	0.829	0.810	0.946	ckpt	log
ViTPose-L	256x192	0.782	0.914	0.850	0.834	0.952	ckpt	log
ViTPose-H	256x192	0.788	0.917	0.855	0.839	0.954	ckpt	log
ViTPose-H*	256x192	0.790	0.916	0.857	0.840	0.953	ckpt	-

Models with * are converted from the official repo. The config files of these models are only for validation.

With simple decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
ViTPose-S	256x192	0.736	0.900	0.811	0.790	0.940	ckpt	log
ViTPose-B	256x192	0.756	0.906	0.826	0.809	0.946	ckpt	log
ViTPose-L	256x192	0.780	0.914	0.851	0.833	0.952	ckpt	log
ViTPose-H	256x192	0.789	0.916	0.856	0.839	0.953	ckpt	log

Topdown Heatmap + Hrnet + Augmentation on Coco

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

Albumentations (Information'2020)

@article{buslaev2020albumentations,
  title={Albumentations: fast and flexible image augmentations},
  author={Buslaev, Alexander and Iglovikov, Vladimir I and Khvedchenya, Eugene and Parinov, Alex and Druzhinin, Mikhail and Kalinin, Alexandr A},
  journal={Information},
  volume={11},
  number={2},
  pages={125},
  year={2020},
  publisher={Multidisciplinary Digital Publishing Institute}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
coarsedropout	256x192	0.753	0.908	0.822	0.805	0.944	ckpt	log
gridmask	256x192	0.752	0.906	0.825	0.804	0.943	ckpt	log
photometric	256x192	0.754	0.908	0.825	0.805	0.943	ckpt	log

Topdown Heatmap + Scnet on Coco

SCNet (CVPR'2020)

@inproceedings{liu2020improving,
  title={Improving Convolutional Networks with Self-Calibrated Convolutions},
  author={Liu, Jiang-Jiang and Hou, Qibin and Cheng, Ming-Ming and Wang, Changhu and Feng, Jiashi},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={10096--10105},
  year={2020}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_scnet_50	256x192	0.728	0.899	0.807	0.784	0.938	ckpt	log
pose_scnet_50	384x288	0.751	0.906	0.818	0.802	0.942	ckpt	log
pose_scnet_101	256x192	0.733	0.902	0.811	0.789	0.940	ckpt	log
pose_scnet_101	384x288	0.752	0.906	0.823	0.804	0.943	ckpt	log

Topdown Heatmap + Mobilenetv2 on Coco

MobilenetV2 (CVPR'2018)

@inproceedings{sandler2018mobilenetv2,
  title={Mobilenetv2: Inverted residuals and linear bottlenecks},
  author={Sandler, Mark and Howard, Andrew and Zhu, Menglong and Zhmoginov, Andrey and Chen, Liang-Chieh},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={4510--4520},
  year={2018}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_mobilenetv2	256x192	0.648	0.874	0.725	0.709	0.918	ckpt	log
pose_mobilenetv2	384x288	0.677	0.882	0.746	0.734	0.920	ckpt	log

Topdown Heatmap + VGG on Coco

VGG (ICLR'2015)

@article{simonyan2014very,
  title={Very deep convolutional networks for large-scale image recognition},
  author={Simonyan, Karen and Zisserman, Andrew},
  journal={arXiv preprint arXiv:1409.1556},
  year={2014}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
vgg	256x192	0.699	0.890	0.769	0.754	0.927	ckpt	log

Topdown Heatmap + Resnet + Dark on Coco

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

DarkPose (CVPR'2020)

@inproceedings{zhang2020distribution,
  title={Distribution-aware coordinate representation for human pose estimation},
  author={Zhang, Feng and Zhu, Xiatian and Dai, Hanbin and Ye, Mao and Zhu, Ce},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={7093--7102},
  year={2020}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnet_50_dark	256x192	0.724	0.897	0.797	0.777	0.934	ckpt	log
pose_resnet_50_dark	384x288	0.735	0.902	0.801	0.786	0.938	ckpt	log
pose_resnet_101_dark	256x192	0.733	0.900	0.810	0.786	0.938	ckpt	log
pose_resnet_101_dark	384x288	0.749	0.905	0.818	0.799	0.940	ckpt	log
pose_resnet_152_dark	256x192	0.743	0.906	0.819	0.796	0.943	ckpt	log
pose_resnet_152_dark	384x288	0.755	0.907	0.825	0.805	0.943	ckpt	log

Topdown Heatmap + Litehrnet on Coco

LiteHRNet (CVPR'2021)

@inproceedings{Yulitehrnet21,
  title={Lite-HRNet: A Lightweight High-Resolution Network},
  author={Yu, Changqian and Xiao, Bin and Gao, Changxin and Yuan, Lu and Zhang, Lei and Sang, Nong and Wang, Jingdong},
  booktitle={CVPR},
  year={2021}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
LiteHRNet-18	256x192	0.642	0.867	0.719	0.705	0.911	ckpt	log
LiteHRNet-18	384x288	0.676	0.876	0.746	0.735	0.919	ckpt	log
LiteHRNet-30	256x192	0.676	0.880	0.756	0.736	0.922	ckpt	log
LiteHRNet-30	384x288	0.700	0.883	0.776	0.758	0.926	ckpt	log

Topdown Heatmap + Resnet on Coco

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnet_50	256x192	0.718	0.898	0.796	0.774	0.934	ckpt	log
pose_resnet_50	384x288	0.731	0.900	0.799	0.782	0.937	ckpt	log
pose_resnet_101	256x192	0.728	0.904	0.809	0.783	0.942	ckpt	log
pose_resnet_101	384x288	0.749	0.906	0.817	0.799	0.941	ckpt	log
pose_resnet_152	256x192	0.736	0.904	0.818	0.791	0.942	ckpt	log
pose_resnet_152	384x288	0.750	0.908	0.821	0.800	0.942	ckpt	log

The following model is equipped with a visibility prediction head and has been trained using COCO and AIC datasets.

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnet_50	256x192	0.729	0.900	0.807	0.783	0.938	ckpt	log

Topdown Heatmap + Hrnet + Udp on Coco

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

UDP (CVPR'2020)

@InProceedings{Huang_2020_CVPR,
  author = {Huang, Junjie and Zhu, Zheng and Guo, Feng and Huang, Guan},
  title = {The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation},
  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2020}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32_udp	256x192	0.762	0.907	0.829	0.810	0.942	ckpt	log
pose_hrnet_w32_udp	384x288	0.768	0.909	0.832	0.815	0.945	ckpt	log
pose_hrnet_w48_udp	256x192	0.768	0.908	0.833	0.817	0.945	ckpt	log
pose_hrnet_w48_udp	384x288	0.773	0.911	0.836	0.821	0.946	ckpt	log
pose_hrnet_w32_udp_regress	256x192	0.759	0.907	0.827	0.813	0.943	ckpt	log

Note that, UDP also adopts the unbiased encoding/decoding algorithm of DARK.

Topdown Heatmap + PVT on Coco

PVT (ICCV'2021)

@inproceedings{wang2021pyramid,
  title={Pyramid vision transformer: A versatile backbone for dense prediction without convolutions},
  author={Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={568--578},
  year={2021}
}

PVTV2 (CVMJ'2022)

@article{wang2022pvt,
  title={PVT v2: Improved baselines with Pyramid Vision Transformer},
  author={Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling},
  journal={Computational Visual Media},
  pages={1--10},
  year={2022},
  publisher={Springer}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_pvt-s	256x192	0.714	0.896	0.794	0.773	0.936	ckpt	log
pose_pvtv2-b2	256x192	0.737	0.905	0.812	0.791	0.942	ckpt	log

Cid + Hrnet on Coco

CID (CVPR'2022)

@InProceedings{Wang_2022_CVPR,
    author    = {Wang, Dongkai and Zhang, Shiliang},
    title     = {Contextual Instance Decoupling for Robust Multi-Person Pose Estimation},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {11060-11068}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 without multi-scale test

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
CID	512x512	0.704	0.894	0.775	0.753	0.928	ckpt	log
CID	512x512	0.715	0.900	0.782	0.765	0.935	ckpt	log

Rtmpose + Rtmpose on Coco

RTMPose (arXiv'2023)

@misc{https://doi.org/10.48550/arxiv.2303.07399,
  doi = {10.48550/ARXIV.2303.07399},
  url = {https://arxiv.org/abs/2303.07399},
  author = {Jiang, Tao and Lu, Peng and Zhang, Li and Ma, Ningsheng and Han, Rui and Lyu, Chengqi and Li, Yining and Chen, Kai},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}

RTMDet (arXiv'2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
rtmpose-t	256x192	0.682	0.883	0.759	0.736	0.920	ckpt	log
rtmpose-s	256x192	0.716	0.892	0.789	0.768	0.929	ckpt	log
rtmpose-m	256x192	0.746	0.899	0.817	0.795	0.935	ckpt	log
rtmpose-l	256x192	0.758	0.906	0.826	0.806	0.942	ckpt	log
rtmpose-t-aic-coco	256x192	0.685	0.880	0.761	0.738	0.918	ckpt	log
rtmpose-s-aic-coco	256x192	0.722	0.892	0.794	0.772	0.929	ckpt	log
rtmpose-m-aic-coco	256x192	0.758	0.903	0.826	0.806	0.940	ckpt	log
rtmpose-l-aic-coco	256x192	0.765	0.906	0.835	0.813	0.942	ckpt	log
rtmpose-m-aic-coco	384x288	0.770	0.908	0.833	0.816	0.943	ckpt	log
rtmpose-l-aic-coco	384x288	0.773	0.907	0.835	0.819	0.942	ckpt	log

Associative Embedding + Hrnet on Coco

Associative Embedding (NIPS'2017)

@inproceedings{newell2017associative,
  title={Associative embedding: End-to-end learning for joint detection and grouping},
  author={Newell, Alejandro and Huang, Zhiao and Deng, Jia},
  booktitle={Advances in neural information processing systems},
  pages={2277--2287},
  year={2017}
}

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Results on COCO val2017 without multi-scale test

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
HRNet-w32	512x512	0.656	0.864	0.719	0.711	0.893	ckpt	log

---

Mpii Dataset

Topdown Regression + Resnet + Rle on Mpii

DeepPose (CVPR'2014)

@inproceedings{toshev2014deeppose,
  title={Deeppose: Human pose estimation via deep neural networks},
  author={Toshev, Alexander and Szegedy, Christian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1653--1660},
  year={2014}
}

RLE (ICCV'2021)

@inproceedings{li2021human,
  title={Human pose regression with residual log-likelihood estimation},
  author={Li, Jiefeng and Bian, Siyuan and Zeng, Ailing and Wang, Can and Pang, Bo and Liu, Wentao and Lu, Cewu},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={11025--11034},
  year={2021}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
deeppose_resnet_50_rle	256x256	0.861	0.277	ckpt	log

Topdown Regression + Resnet on Mpii

DeepPose (CVPR'2014)

@inproceedings{toshev2014deeppose,
  title={Deeppose: Human pose estimation via deep neural networks},
  author={Toshev, Alexander and Szegedy, Christian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1653--1660},
  year={2014}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
deeppose_resnet_50	256x256	0.826	0.180	ckpt	log
deeppose_resnet_101	256x256	0.841	0.200	ckpt	log
deeppose_resnet_152	256x256	0.850	0.208	ckpt	log

Topdown Heatmap + Resnext on Mpii

ResNext (CVPR'2017)

@inproceedings{xie2017aggregated,
  title={Aggregated residual transformations for deep neural networks},
  author={Xie, Saining and Girshick, Ross and Doll{\'a}r, Piotr and Tu, Zhuowen and He, Kaiming},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1492--1500},
  year={2017}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_resnext_152	256x256	0.887	0.294	ckpt	log

Topdown Heatmap + Hrnet + Dark on Mpii

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

DarkPose (CVPR'2020)

@inproceedings{zhang2020distribution,
  title={Distribution-aware coordinate representation for human pose estimation},
  author={Zhang, Feng and Zhu, Xiatian and Dai, Hanbin and Ye, Mao and Zhu, Ce},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={7093--7102},
  year={2020}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_hrnet_w32_dark	256x256	0.904	0.354	ckpt	log
pose_hrnet_w48_dark	256x256	0.905	0.360	ckpt	log

Topdown Heatmap + Resnetv1d on Mpii

ResNetV1D (CVPR'2019)

@inproceedings{he2019bag,
  title={Bag of tricks for image classification with convolutional neural networks},
  author={He, Tong and Zhang, Zhi and Zhang, Hang and Zhang, Zhongyue and Xie, Junyuan and Li, Mu},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={558--567},
  year={2019}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_resnetv1d_50	256x256	0.881	0.290	ckpt	log
pose_resnetv1d_101	256x256	0.883	0.295	ckpt	log
pose_resnetv1d_152	256x256	0.888	0.300	ckpt	log

Topdown Heatmap + Shufflenetv2 on Mpii

ShufflenetV2 (ECCV'2018)

@inproceedings{ma2018shufflenet,
  title={Shufflenet v2: Practical guidelines for efficient cnn architecture design},
  author={Ma, Ningning and Zhang, Xiangyu and Zheng, Hai-Tao and Sun, Jian},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={116--131},
  year={2018}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_shufflenetv2	256x256	0.828	0.205	ckpt	log

Topdown Heatmap + Scnet on Mpii

SCNet (CVPR'2020)

@inproceedings{liu2020improving,
  title={Improving Convolutional Networks with Self-Calibrated Convolutions},
  author={Liu, Jiang-Jiang and Hou, Qibin and Cheng, Ming-Ming and Wang, Changhu and Feng, Jiashi},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={10096--10105},
  year={2020}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_scnet_50	256x256	0.888	0.290	ckpt	log
pose_scnet_101	256x256	0.887	0.293	ckpt	log

Topdown Heatmap + Hrnet on Mpii

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_hrnet_w32	256x256	0.900	0.334	ckpt	log
pose_hrnet_w48	256x256	0.901	0.337	ckpt	log

Topdown Heatmap + Mobilenetv2 on Mpii

MobilenetV2 (CVPR'2018)

@inproceedings{sandler2018mobilenetv2,
  title={Mobilenetv2: Inverted residuals and linear bottlenecks},
  author={Sandler, Mark and Howard, Andrew and Zhu, Menglong and Zhmoginov, Andrey and Chen, Liang-Chieh},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={4510--4520},
  year={2018}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_mobilenetv2	256x256	0.854	0.234	ckpt	log

Topdown Heatmap + Shufflenetv1 on Mpii

ShufflenetV1 (CVPR'2018)

@inproceedings{zhang2018shufflenet,
  title={Shufflenet: An extremely efficient convolutional neural network for mobile devices},
  author={Zhang, Xiangyu and Zhou, Xinyu and Lin, Mengxiao and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={6848--6856},
  year={2018}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_shufflenetv1	256x256	0.824	0.195	ckpt	log

Topdown Heatmap + CPM on Mpii

CPM (CVPR'2016)

@inproceedings{wei2016convolutional,
  title={Convolutional pose machines},
  author={Wei, Shih-En and Ramakrishna, Varun and Kanade, Takeo and Sheikh, Yaser},
  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
  pages={4724--4732},
  year={2016}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
cpm	368x368	0.876	0.285	ckpt	log

Topdown Heatmap + Resnet on Mpii

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_resnet_50	256x256	0.882	0.286	ckpt	log
pose_resnet_101	256x256	0.888	0.290	ckpt	log
pose_resnet_152	256x256	0.889	0.303	ckpt	log

Topdown Heatmap + Cspnext + Udp on Mpii

RTMDet (arXiv'2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

UDP (CVPR'2020)

@InProceedings{Huang_2020_CVPR,
  author = {Huang, Junjie and Zhu, Zheng and Guo, Feng and Huang, Guan},
  title = {The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation},
  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2020}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_hrnet_w32	256x256	0.902	0.303	ckpt	log

Topdown Heatmap + Seresnet on Mpii

SEResNet (CVPR'2018)

@inproceedings{hu2018squeeze,
  title={Squeeze-and-excitation networks},
  author={Hu, Jie and Shen, Li and Sun, Gang},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={7132--7141},
  year={2018}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_seresnet_50	256x256	0.884	0.292	ckpt	log
pose_seresnet_101	256x256	0.884	0.295	ckpt	log
pose_seresnet_152*	256x256	0.884	0.287	ckpt	log

Note that * means without imagenet pre-training.

Topdown Heatmap + Litehrnet on Mpii

LiteHRNet (CVPR'2021)

@inproceedings{Yulitehrnet21,
  title={Lite-HRNet: A Lightweight High-Resolution Network},
  author={Yu, Changqian and Xiao, Bin and Gao, Changxin and Yuan, Lu and Zhang, Lei and Sang, Nong and Wang, Jingdong},
  booktitle={CVPR},
  year={2021}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
LiteHRNet-18	256x256	0.859	0.260	ckpt	log
LiteHRNet-30	256x256	0.869	0.271	ckpt	log

Topdown Heatmap + Hourglass on Mpii

Hourglass (ECCV'2016)

@inproceedings{newell2016stacked,
  title={Stacked hourglass networks for human pose estimation},
  author={Newell, Alejandro and Yang, Kaiyu and Deng, Jia},
  booktitle={European conference on computer vision},
  pages={483--499},
  year={2016},
  organization={Springer}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean	Mean@0.1	ckpt	log
pose_hourglass_52	256x256	0.889	0.317	ckpt	log
pose_hourglass_52	384x384	0.894	0.367	ckpt	log

Rtmpose + Rtmpose on Mpii

RTMPose (arXiv'2023)

@misc{https://doi.org/10.48550/arxiv.2303.07399,
  doi = {10.48550/ARXIV.2303.07399},
  url = {https://arxiv.org/abs/2303.07399},
  author = {Jiang, Tao and Lu, Peng and Zhang, Li and Ma, Ningsheng and Han, Rui and Lyu, Chengqi and Li, Yining and Chen, Kai},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}

MPII (CVPR'2014)

@inproceedings{andriluka14cvpr,
  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2014},
  month = {June}
}

Results on MPII val set

Arch	Input Size	Mean / w. flip	Mean@0.1	ckpt	log
rtmpose-m	256x256	0.907	0.348	ckpt	log

---

Exlpose Dataset

Topdown Heatmap + Hrnet on Exlpose

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

ExLPose (2023)

@inproceedings{ExLPose_2023_CVPR,
 title={Human Pose Estimation in Extremely Low-Light Conditions},
 author={Sohyun Lee, Jaesung Rim, Boseung Jeong, Geonu Kim, ByungJu Woo, Haechan Lee, Sunghyun Cho, Suha Kwak},
 booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
 year={2023}
}

Results on ExLPose-LLA val set with ground-truth bounding boxes

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32	256x192	0.401	0.64	0.40	0.452	0.693	ckpt	log

---

Aic Dataset

Topdown Heatmap + Hrnet on Aic

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

AI Challenger (ArXiv'2017)

@article{wu2017ai,
  title={Ai challenger: A large-scale dataset for going deeper in image understanding},
  author={Wu, Jiahong and Zheng, He and Zhao, Bo and Li, Yixin and Yan, Baoming and Liang, Rui and Wang, Wenjia and Zhou, Shipei and Lin, Guosen and Fu, Yanwei and others},
  journal={arXiv preprint arXiv:1711.06475},
  year={2017}
}

Results on AIC val set with ground-truth bounding boxes

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32	256x192	0.323	0.761	0.218	0.366	0.789	ckpt	log

Topdown Heatmap + Resnet on Aic

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

AI Challenger (ArXiv'2017)

@article{wu2017ai,
  title={Ai challenger: A large-scale dataset for going deeper in image understanding},
  author={Wu, Jiahong and Zheng, He and Zhao, Bo and Li, Yixin and Yan, Baoming and Liang, Rui and Wang, Wenjia and Zhou, Shipei and Lin, Guosen and Fu, Yanwei and others},
  journal={arXiv preprint arXiv:1711.06475},
  year={2017}
}

Results on AIC val set with ground-truth bounding boxes

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_resnet_101	256x192	0.294	0.736	0.172	0.337	0.762	ckpt	log

---

JHMDB Dataset

Topdown Heatmap + Resnet on JHMDB

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

JHMDB (ICCV'2013)

@inproceedings{Jhuang:ICCV:2013,
  title = {Towards understanding action recognition},
  author = {H. Jhuang and J. Gall and S. Zuffi and C. Schmid and M. J. Black},
  booktitle = {International Conf. on Computer Vision (ICCV)},
  month = Dec,
  pages = {3192-3199},
  year = {2013}
}

Results on Sub-JHMDB dataset

The models are pre-trained on MPII dataset only. NO test-time augmentation (multi-scale /rotation testing) is used.

• Normalized by Person Size

Split	Arch	Input Size	Head	Sho	Elb	Wri	Hip	Knee	Ank	Mean	ckpt	log
Sub1	pose_resnet_50	256x256	99.1	98.0	93.8	91.3	99.4	96.5	92.8	96.1	ckpt	log
Sub2	pose_resnet_50	256x256	99.3	97.1	90.6	87.0	98.9	96.3	94.1	95.0	ckpt	log
Sub3	pose_resnet_50	256x256	99.0	97.9	94.0	91.6	99.7	98.0	94.7	96.7	ckpt	log
Average	pose_resnet_50	256x256	99.2	97.7	92.8	90.0	99.3	96.9	93.9	96.0	-	-
Sub1	pose_resnet_50 (2 Deconv.)	256x256	99.1	98.5	94.6	92.0	99.4	94.6	92.5	96.1	ckpt	log
Sub2	pose_resnet_50 (2 Deconv.)	256x256	99.3	97.8	91.0	87.0	99.1	96.5	93.8	95.2	ckpt	log
Sub3	pose_resnet_50 (2 Deconv.)	256x256	98.8	98.4	94.3	92.1	99.8	97.5	93.8	96.7	ckpt	log
Average	pose_resnet_50 (2 Deconv.)	256x256	99.1	98.2	93.3	90.4	99.4	96.2	93.4	96.0	-	-

• Normalized by Torso Size

Split	Arch	Input Size	Head	Sho	Elb	Wri	Hip	Knee	Ank	Mean	ckpt	log
Sub1	pose_resnet_50	256x256	93.3	83.2	74.4	72.7	85.0	81.2	78.9	81.9	ckpt	log
Sub2	pose_resnet_50	256x256	94.1	74.9	64.5	62.5	77.9	71.9	78.6	75.5	ckpt	log
Sub3	pose_resnet_50	256x256	97.0	82.2	74.9	70.7	84.7	83.7	84.2	82.9	ckpt	log
Average	pose_resnet_50	256x256	94.8	80.1	71.3	68.6	82.5	78.9	80.6	80.1	-	-
Sub1	pose_resnet_50 (2 Deconv.)	256x256	92.4	80.6	73.2	70.5	82.3	75.4	75.0	79.2	ckpt	log
Sub2	pose_resnet_50 (2 Deconv.)	256x256	93.4	73.6	63.8	60.5	75.1	68.4	75.5	73.7	ckpt	log
Sub3	pose_resnet_50 (2 Deconv.)	256x256	96.1	81.2	72.6	67.9	83.6	80.9	81.5	81.2	ckpt	log
Average	pose_resnet_50 (2 Deconv.)	256x256	94.0	78.5	69.9	66.3	80.3	74.9	77.3	78.0	-	-

Topdown Heatmap + CPM on JHMDB

CPM (CVPR'2016)

@inproceedings{wei2016convolutional,
  title={Convolutional pose machines},
  author={Wei, Shih-En and Ramakrishna, Varun and Kanade, Takeo and Sheikh, Yaser},
  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
  pages={4724--4732},
  year={2016}
}

JHMDB (ICCV'2013)

@inproceedings{Jhuang:ICCV:2013,
  title = {Towards understanding action recognition},
  author = {H. Jhuang and J. Gall and S. Zuffi and C. Schmid and M. J. Black},
  booktitle = {International Conf. on Computer Vision (ICCV)},
  month = Dec,
  pages = {3192-3199},
  year = {2013}
}

Results on Sub-JHMDB dataset

The models are pre-trained on MPII dataset only. NO test-time augmentation (multi-scale /rotation testing) is used.

• Normalized by Person Size

Split	Arch	Input Size	Head	Sho	Elb	Wri	Hip	Knee	Ank	Mean	ckpt	log
Sub1	cpm	368x368	96.1	91.9	81.0	78.9	96.6	90.8	87.3	89.5	ckpt	log
Sub2	cpm	368x368	98.1	93.6	77.1	70.9	94.0	89.1	84.7	87.4	ckpt	log
Sub3	cpm	368x368	97.9	94.9	87.3	84.0	98.6	94.4	86.2	92.4	ckpt	log
Average	cpm	368x368	97.4	93.5	81.5	77.9	96.4	91.4	86.1	89.8	-	-

• Normalized by Torso Size

Split	Arch	Input Size	Head	Sho	Elb	Wri	Hip	Knee	Ank	Mean	ckpt	log
Sub1	cpm	368x368	89.0	63.0	54.0	54.9	68.2	63.1	61.2	66.0	ckpt	log
Sub2	cpm	368x368	90.3	57.9	46.8	44.3	60.8	58.2	62.4	61.1	ckpt	log
Sub3	cpm	368x368	91.0	72.6	59.9	54.0	73.2	68.5	65.8	70.3	ckpt	log
Average	cpm	368x368	90.1	64.5	53.6	51.1	67.4	63.3	63.1	65.7	-	-

---

Humanart Dataset

Topdown Heatmap + Hrnet on Humanart

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Human-Art (CVPR'2023)

@inproceedings{ju2023humanart,
    title={Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes},
    author={Ju, Xuan and Zeng, Ailing and Jianan, Wang and Qiang, Xu and Lei, Zhang},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
    year={2023}}

Results on Human-Art validation dataset with detector having human AP of 56.2 on Human-Art validation dataset

With classic decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32-coco	256x192	0.252	0.397	0.255	0.321	0.485	ckpt	log
pose_hrnet_w32-humanart-coco	256x192	0.399	0.545	0.420	0.466	0.613	ckpt	log
pose_hrnet_w48-coco	256x192	0.271	0.413	0.277	0.339	0.499	ckpt	log
pose_hrnet_w48-humanart-coco	256x192	0.417	0.553	0.442	0.481	0.617	ckpt	log

Results on Human-Art validation dataset with ground-truth bounding-box

With classic decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32-coco	256x192	0.533	0.771	0.562	0.574	0.792	ckpt	log
pose_hrnet_w32-humanart-coco	256x192	0.754	0.906	0.812	0.783	0.916	ckpt	log
pose_hrnet_w48-coco	256x192	0.557	0.782	0.593	0.595	0.804	ckpt	log
pose_hrnet_w48-humanart-coco	256x192	0.769	0.906	0.825	0.796	0.919	ckpt	log

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

With classic decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32-coco	256x192	0.749	0.906	0.821	0.804	0.945	ckpt	log
pose_hrnet_w32-humanart-coco	256x192	0.741	0.902	0.814	0.795	0.941	ckpt	log
pose_hrnet_w48-coco	256x192	0.756	0.908	0.826	0.809	0.945	ckpt	log
pose_hrnet_w48-humanart-coco	256x192	0.751	0.905	0.822	0.805	0.943	ckpt	log

Topdown Heatmap + Vitpose on Humanart

To utilize ViTPose, you’ll need to have MMPreTrain. To install the required version, run the following command:

mim install 'mmpretrain>=1.0.0'

ViTPose (NeurIPS'2022)

@inproceedings{
  xu2022vitpose,
  title={Vi{TP}ose: Simple Vision Transformer Baselines for Human Pose Estimation},
  author={Yufei Xu and Jing Zhang and Qiming Zhang and Dacheng Tao},
  booktitle={Advances in Neural Information Processing Systems},
  year={2022},
}

COCO-WholeBody (ECCV'2020)

@inproceedings{jin2020whole,
  title={Whole-Body Human Pose Estimation in the Wild},
  author={Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  year={2020}
}

Human-Art (CVPR'2023)

@inproceedings{ju2023humanart,
    title={Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes},
    author={Ju, Xuan and Zeng, Ailing and Jianan, Wang and Qiang, Xu and Lei, Zhang},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
    year={2023}}

Results on Human-Art validation dataset with detector having human AP of 56.2 on Human-Art validation dataset

With classic decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
ViTPose-S-coco	256x192	0.228	0.371	0.229	0.298	0.467	ckpt	log
ViTPose-S-humanart-coco	256x192	0.381	0.532	0.405	0.448	0.602	ckpt	log
ViTPose-B-coco	256x192	0.270	0.423	0.272	0.340	0.510	ckpt	log
ViTPose-B-humanart-coco	256x192	0.410	0.549	0.434	0.475	0.615	ckpt	log
ViTPose-L-coco	256x192	0.342	0.498	0.357	0.413	0.577	ckpt	log
ViTPose-L-humanart-coco	256x192	0.459	0.592	0.487	0.525	0.656	ckpt	log
ViTPose-H-coco	256x192	0.377	0.541	0.391	0.447	0.615	ckpt	log
ViTPose-H-humanart-coco	256x192	0.468	0.594	0.498	0.534	0.655	ckpt	log

Results on Human-Art validation dataset with ground-truth bounding-box

With classic decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
ViTPose-S-coco	256x192	0.507	0.758	0.531	0.551	0.780	ckpt	log
ViTPose-S-humanart-coco	256x192	0.738	0.905	0.802	0.768	0.911	ckpt	log
ViTPose-B-coco	256x192	0.555	0.782	0.590	0.599	0.809	ckpt	log
ViTPose-B-humanart-coco	256x192	0.759	0.905	0.823	0.790	0.917	ckpt	log
ViTPose-L-coco	256x192	0.637	0.838	0.689	0.677	0.859	ckpt	log
ViTPose-L-humanart-coco	256x192	0.789	0.916	0.845	0.819	0.929	ckpt	log
ViTPose-H-coco	256x192	0.665	0.860	0.715	0.701	0.871	ckpt	log
ViTPose-H-humanart-coco	256x192	0.800	0.926	0.855	0.828	0.933	ckpt	log

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

With classic decoder

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
ViTPose-S-coco	256x192	0.739	0.903	0.816	0.792	0.942	ckpt	log
ViTPose-S-humanart-coco	256x192	0.737	0.902	0.811	0.792	0.942	ckpt	log
ViTPose-B-coco	256x192	0.757	0.905	0.829	0.810	0.946	ckpt	log
ViTPose-B-humanart-coco	256x192	0.758	0.906	0.829	0.812	0.946	ckpt	log
ViTPose-L-coco	256x192	0.782	0.914	0.850	0.834	0.952	ckpt	log
ViTPose-L-humanart-coco	256x192	0.782	0.914	0.849	0.835	0.953	ckpt	log
ViTPose-H-coco	256x192	0.788	0.917	0.855	0.839	0.954	ckpt	log
ViTPose-H-humanart-coco	256x192	0.788	0.914	0.853	0.841	0.956	ckpt	log

Rtmpose + Rtmpose on Humanart

RTMPose (arXiv'2023)

@misc{https://doi.org/10.48550/arxiv.2303.07399,
  doi = {10.48550/ARXIV.2303.07399},
  url = {https://arxiv.org/abs/2303.07399},
  author = {Jiang, Tao and Lu, Peng and Zhang, Li and Ma, Ningsheng and Han, Rui and Lyu, Chengqi and Li, Yining and Chen, Kai},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}

RTMDet (arXiv'2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

Human-Art (CVPR'2023)

@inproceedings{ju2023humanart,
    title={Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes},
    author={Ju, Xuan and Zeng, Ailing and Jianan, Wang and Qiang, Xu and Lei, Zhang},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
    year={2023}}

Results on Human-Art validation dataset with detector having human AP of 56.2 on Human-Art validation dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
rtmpose-t-coco	256x192	0.161	0.283	0.154	0.221	0.373	ckpt	log
rtmpose-t-humanart-coco	256x192	0.249	0.395	0.256	0.323	0.485	ckpt	log
rtmpose-s-coco	256x192	0.199	0.328	0.198	0.261	0.418	ckpt	log
rtmpose-s-humanart-coco	256x192	0.311	0.462	0.323	0.381	0.540	ckpt	log
rtmpose-m-coco	256x192	0.239	0.372	0.243	0.302	0.455	ckpt	log
rtmpose-m-humanart-coco	256x192	0.355	0.503	0.377	0.417	0.568	ckpt	log
rtmpose-l-coco	256x192	0.260	0.393	0.267	0.323	0.472	ckpt	log
rtmpose-l-humanart-coco	256x192	0.378	0.521	0.399	0.442	0.584	ckpt	log

Results on Human-Art validation dataset with ground-truth bounding-box

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
rtmpose-t-coco	256x192	0.444	0.725	0.453	0.488	0.750	ckpt	log
rtmpose-t-humanart-coco	256x192	0.655	0.872	0.720	0.693	0.890	ckpt	log
rtmpose-s-coco	256x192	0.480	0.739	0.498	0.521	0.763	ckpt	log
rtmpose-s-humanart-coco	256x192	0.698	0.893	0.768	0.732	0.903	ckpt	log
rtmpose-m-coco	256x192	0.532	0.765	0.563	0.571	0.789	ckpt	log
rtmpose-m-humanart-coco	256x192	0.728	0.895	0.791	0.759	0.906	ckpt	log
rtmpose-l-coco	256x192	0.564	0.789	0.602	0.599	0.808	ckpt	log
rtmpose-l-humanart-coco	256x192	0.753	0.905	0.812	0.783	0.915	ckpt	log

Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
rtmpose-t-coco	256x192	0.682	0.883	0.759	0.736	0.920	ckpt	log
rtmpose-t-humanart-coco	256x192	0.665	0.875	0.739	0.721	0.916	ckpt	log
rtmpose-s-coco	256x192	0.716	0.892	0.789	0.768	0.929	ckpt	log
rtmpose-s-humanart-coco	256x192	0.706	0.888	0.780	0.759	0.928	ckpt	log
rtmpose-m-coco	256x192	0.746	0.899	0.817	0.795	0.935	ckpt	log
rtmpose-m-humanart-coco	256x192	0.725	0.892	0.795	0.775	0.929	ckpt	log
rtmpose-l-coco	256x192	0.758	0.906	0.826	0.806	0.942	ckpt	log
rtmpose-l-humanart-coco	256x192	0.748	0.901	0.816	0.796	0.938	ckpt	log

Results on COCO val2017 with ground-truth bounding box

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
rtmpose-t-humanart-coco	256x192	0.679	0.895	0.755	0.710	0.907	ckpt	log
rtmpose-s-humanart-coco	256x192	0.725	0.916	0.798	0.753	0.925	ckpt	log
rtmpose-m-humanart-coco	256x192	0.744	0.916	0.818	0.770	0.930	ckpt	log
rtmpose-l-humanart-coco	256x192	0.770	0.927	0.840	0.794	0.939	ckpt	log

---

Posetrack18 Dataset

Topdown Heatmap + Resnet on Posetrack18

SimpleBaseline2D (ECCV'2018)

@inproceedings{xiao2018simple,
  title={Simple baselines for human pose estimation and tracking},
  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={466--481},
  year={2018}
}

ResNet (CVPR'2016)

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

PoseTrack18 (CVPR'2018)

@inproceedings{andriluka2018posetrack,
  title={Posetrack: A benchmark for human pose estimation and tracking},
  author={Andriluka, Mykhaylo and Iqbal, Umar and Insafutdinov, Eldar and Pishchulin, Leonid and Milan, Anton and Gall, Juergen and Schiele, Bernt},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={5167--5176},
  year={2018}
}

Results on PoseTrack2018 val with ground-truth bounding boxes

Arch	Input Size	Head	Shou	Elb	Wri	Hip	Knee	Ankl	Total	ckpt	log
pose_resnet_50	256x192	86.5	87.7	82.5	75.8	80.1	78.8	74.2	81.2	ckpt	log

The models are first pre-trained on COCO dataset, and then fine-tuned on PoseTrack18.

Topdown Heatmap + Hrnet on Posetrack18

HRNet (CVPR'2019)

@inproceedings{sun2019deep,
  title={Deep high-resolution representation learning for human pose estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5693--5703},
  year={2019}
}

PoseTrack18 (CVPR'2018)

@inproceedings{andriluka2018posetrack,
  title={Posetrack: A benchmark for human pose estimation and tracking},
  author={Andriluka, Mykhaylo and Iqbal, Umar and Insafutdinov, Eldar and Pishchulin, Leonid and Milan, Anton and Gall, Juergen and Schiele, Bernt},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={5167--5176},
  year={2018}
}

Results on PoseTrack2018 val with ground-truth bounding boxes

Arch	Input Size	Head	Shou	Elb	Wri	Hip	Knee	Ankl	Total	ckpt	log
pose_hrnet_w32	256x192	86.2	89.0	84.5	79.2	82.3	82.5	78.7	83.4	ckpt	log
pose_hrnet_w32	384x288	87.1	89.0	85.1	80.2	80.6	82.8	79.6	83.7	ckpt	log
pose_hrnet_w48	256x192	88.3	90.2	86.0	81.0	80.7	83.3	80.6	84.6	ckpt	log
pose_hrnet_w48	384x288	87.8	90.0	86.2	81.3	81.0	83.4	80.9	84.6	ckpt	log

The models are first pre-trained on COCO dataset, and then fine-tuned on PoseTrack18.

Results on PoseTrack2018 val with MMDetection pre-trained Cascade R-CNN (X-101-64x4d-FPN) human detector

Arch	Input Size	Head	Shou	Elb	Wri	Hip	Knee	Ankl	Total	ckpt	log
pose_hrnet_w32	256x192	78.0	82.9	79.5	73.8	76.9	76.6	70.2	76.9	ckpt	log
pose_hrnet_w32	384x288	79.9	83.6	80.4	74.5	74.8	76.1	70.5	77.3	ckpt	log
pose_hrnet_w48	256x192	80.1	83.4	80.6	74.8	74.3	76.8	70.5	77.4	ckpt	log
pose_hrnet_w48	384x288	80.2	83.8	80.9	75.2	74.7	76.7	71.7	77.8	ckpt	log

The models are first pre-trained on COCO dataset, and then fine-tuned on PoseTrack18.

---

Body8 Dataset

Rtmpose + Rtmpose + Body8-Halpe26 on Body8

RTMPose (arXiv'2023)

@misc{https://doi.org/10.48550/arxiv.2303.07399,
  doi = {10.48550/ARXIV.2303.07399},
  url = {https://arxiv.org/abs/2303.07399},
  author = {Jiang, Tao and Lu, Peng and Zhang, Li and Ma, Ningsheng and Han, Rui and Lyu, Chengqi and Li, Yining and Chen, Kai},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}

RTMDet (arXiv'2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

AlphaPose (TPAMI'2022)

@article{alphapose,
  author = {Fang, Hao-Shu and Li, Jiefeng and Tang, Hongyang and Xu, Chao and Zhu, Haoyi and Xiu, Yuliang and Li, Yong-Lu and Lu, Cewu},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  title = {AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time},
  year = {2022}
}

• * denotes model trained on 7 public datasets:

  • AI Challenger

  • MS COCO

  • CrowdPose

  • MPII

  • sub-JHMDB

  • Halpe

  • PoseTrack18

• Body8 denotes the addition of the OCHuman dataset, in addition to the 7 datasets mentioned above, for evaluation.

Config	Input Size	PCK@0.1 (Body8)	AUC (Body8)	Params(M)	FLOPS(G)	Download
RTMPose-t*	256x192	91.89	66.35	3.51	0.37	Model
RTMPose-s*	256x192	93.01	68.62	5.70	0.70	Model
RTMPose-m*	256x192	94.75	71.91	13.93	1.95	Model
RTMPose-l*	256x192	95.37	73.19	28.11	4.19	Model
RTMPose-m*	384x288	95.15	73.56	14.06	4.37	Model
RTMPose-l*	384x288	95.56	74.38	28.24	9.40	Model
RTMPose-x*	384x288	95.74	74.82	50.00	17.29	Model

Rtmpose + Rtmpose + Body8-Coco on Body8

RTMPose (arXiv'2023)

@misc{https://doi.org/10.48550/arxiv.2303.07399,
  doi = {10.48550/ARXIV.2303.07399},
  url = {https://arxiv.org/abs/2303.07399},
  author = {Jiang, Tao and Lu, Peng and Zhang, Li and Ma, Ningsheng and Han, Rui and Lyu, Chengqi and Li, Yining and Chen, Kai},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}

RTMDet (arXiv'2022)

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

COCO (ECCV'2014)

@inproceedings{lin2014microsoft,
  title={Microsoft coco: Common objects in context},
  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},
  booktitle={European conference on computer vision},
  pages={740--755},
  year={2014},
  organization={Springer}
}

• Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset.

• * denotes model trained on 7 public datasets:

  • AI Challenger

  • MS COCO

  • CrowdPose

  • MPII

  • sub-JHMDB

  • Halpe

  • PoseTrack18

• Body8 denotes the addition of the OCHuman dataset, in addition to the 7 datasets mentioned above, for evaluation.

Config	Input Size	AP (COCO)	PCK@0.1 (Body8)	AUC (Body8)	EPE (Body8)	Params(M)	FLOPS(G)	Download
RTMPose-t*	256x192	65.9	91.44	63.18	19.45	3.34	0.36	Model
RTMPose-s*	256x192	69.7	92.45	65.15	17.85	5.47	0.68	Model
RTMPose-m*	256x192	74.9	94.25	68.59	15.12	13.59	1.93	Model
RTMPose-l*	256x192	76.7	95.08	70.14	13.79	27.66	4.16	Model
RTMPose-m*	384x288	76.6	94.64	70.38	13.98	13.72	4.33	Model
RTMPose-l*	384x288	78.3	95.36	71.58	13.08	27.79	9.35	Model