mmpose/configs/wholebody_2d_keypoint/topdown_heatmap/coco-wholebody/resnet_coco-wholebody.md

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}
}

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-WholeBody v1.0 val with detector having human AP of 56.4 on COCO val2017 dataset

Arch	Input Size	Body AP	Body AR	Foot AP	Foot AR	Face AP	Face AR	Hand AP	Hand AR	Whole AP	Whole AR	ckpt	log
pose_resnet_50	256x192	0.652	0.738	0.615	0.749	0.606	0.715	0.460	0.584	0.521	0.633	ckpt	log
pose_resnet_50	384x288	0.666	0.747	0.634	0.763	0.731	0.811	0.536	0.646	0.574	0.670	ckpt	log
pose_resnet_101	256x192	0.669	0.753	0.637	0.766	0.611	0.722	0.463	0.589	0.531	0.645	ckpt	log
pose_resnet_101	384x288	0.692	0.770	0.680	0.799	0.746	0.820	0.548	0.657	0.597	0.693	ckpt	log
pose_resnet_152	256x192	0.682	0.764	0.661	0.787	0.623	0.728	0.481	0.607	0.548	0.661	ckpt	log
pose_resnet_152	384x288	0.704	0.780	0.693	0.813	0.751	0.824	0.559	0.666	0.610	0.705	ckpt	log