Animal 2D Keypoint¶

Zebra Dataset¶

Topdown Heatmap + Resnet on Zebra¶

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}
}

Grévy’s Zebra (Elife'2019)

@article{graving2019deepposekit,
  title={DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning},
  author={Graving, Jacob M and Chae, Daniel and Naik, Hemal and Li, Liang and Koger, Benjamin and Costelloe, Blair R and Couzin, Iain D},
  journal={Elife},
  volume={8},
  pages={e47994},
  year={2019},
  publisher={eLife Sciences Publications Limited}
}

Results on Grévy’s Zebra test set

Arch	Input Size	PCK@0.2	AUC	EPE	ckpt	log
pose_resnet_50	160x160	1.000	0.914	1.87	ckpt	log
pose_resnet_101	160x160	1.000	0.915	1.83	ckpt	log
pose_resnet_152	160x160	1.000	0.921	1.67	ckpt	log

Ap10k Dataset¶

Topdown Heatmap + Resnet on Ap10k¶

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}
}

AP-10K (NeurIPS'2021)

@misc{yu2021ap10k,
      title={AP-10K: A Benchmark for Animal Pose Estimation in the Wild},
      author={Hang Yu and Yufei Xu and Jing Zhang and Wei Zhao and Ziyu Guan and Dacheng Tao},
      year={2021},
      eprint={2108.12617},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Results on AP-10K validation set

Arch	Input Size	AP	AP⁵⁰	AP⁷⁵	AP^M	AP^L	ckpt	log
pose_resnet_50	256x256	0.680	0.926	0.738	0.552	0.687	ckpt	log
pose_resnet_101	256x256	0.681	0.921	0.751	0.545	0.690	ckpt	log

Topdown Heatmap + Cspnext + Udp on Ap10k¶

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}
}

AP-10K (NeurIPS'2021)

@misc{yu2021ap10k,
      title={AP-10K: A Benchmark for Animal Pose Estimation in the Wild},
      author={Hang Yu and Yufei Xu and Jing Zhang and Wei Zhao and Ziyu Guan and Dacheng Tao},
      year={2021},
      eprint={2108.12617},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Results on AP-10K validation set

Arch	Input Size	AP	AP⁵⁰	AP⁷⁵	AP^M	AP^L	ckpt	log
pose_cspnext_m	256x256	0.703	0.944	0.776	0.513	0.710	ckpt	log

Topdown Heatmap + Hrnet on Ap10k¶

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}
}

AP-10K (NeurIPS'2021)

@misc{yu2021ap10k,
      title={AP-10K: A Benchmark for Animal Pose Estimation in the Wild},
      author={Hang Yu and Yufei Xu and Jing Zhang and Wei Zhao and Ziyu Guan and Dacheng Tao},
      year={2021},
      eprint={2108.12617},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Results on AP-10K validation set

Arch	Input Size	AP	AP⁵⁰	AP⁷⁵	AP^M	AP^L	ckpt	log
pose_hrnet_w32	256x256	0.722	0.935	0.789	0.557	0.729	ckpt	log
pose_hrnet_w48	256x256	0.728	0.936	0.802	0.577	0.735	ckpt	log

Rtmpose + Rtmpose on Ap10k¶

AP-10K (NeurIPS'2021)

@misc{yu2021ap10k,
      title={AP-10K: A Benchmark for Animal Pose Estimation in the Wild},
      author={Hang Yu and Yufei Xu and Jing Zhang and Wei Zhao and Ziyu Guan and Dacheng Tao},
      year={2021},
      eprint={2108.12617},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Results on AP-10K validation set

Arch	Input Size	AP	AP⁵⁰	AP⁷⁵	AP^M	AP^L	ckpt	log
rtmpose-m	256x256	0.722	0.939	0.788	0.569	0.728	ckpt	log

Animalpose Dataset¶

Topdown Heatmap + Resnet on Animalpose¶

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}
}

Animal-Pose (ICCV'2019)

@InProceedings{Cao_2019_ICCV,
    author = {Cao, Jinkun and Tang, Hongyang and Fang, Hao-Shu and Shen, Xiaoyong and Lu, Cewu and Tai, Yu-Wing},
    title = {Cross-Domain Adaptation for Animal Pose Estimation},
    booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
    month = {October},
    year = {2019}
}

Results on AnimalPose validation set (1117 instances)

Arch	Input Size	AP	AP⁵⁰	AP⁷⁵	AR	AR⁵⁰	ckpt	log
pose_resnet_50	256x256	0.691	0.947	0.770	0.736	0.955	ckpt	log
pose_resnet_101	256x256	0.696	0.948	0.774	0.736	0.951	ckpt	log
pose_resnet_152	256x256	0.704	0.938	0.786	0.748	0.946	ckpt	log

Topdown Heatmap + Hrnet on Animalpose¶

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}
}

Animal-Pose (ICCV'2019)

@InProceedings{Cao_2019_ICCV,
    author = {Cao, Jinkun and Tang, Hongyang and Fang, Hao-Shu and Shen, Xiaoyong and Lu, Cewu and Tai, Yu-Wing},
    title = {Cross-Domain Adaptation for Animal Pose Estimation},
    booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
    month = {October},
    year = {2019}
}

Results on AnimalPose validation set (1117 instances)

Arch	Input Size	AP	AP⁵⁰	AP⁷⁵	AR	AR⁵⁰	ckpt	log
pose_hrnet_w32	256x256	0.740	0.959	0.833	0.780	0.965	ckpt	log
pose_hrnet_w48	256x256	0.738	0.958	0.831	0.778	0.962	ckpt	log

Locust Dataset¶

Topdown Heatmap + Resnet on Locust¶

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}
}

Desert Locust (Elife'2019)

@article{graving2019deepposekit,
  title={DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning},
  author={Graving, Jacob M and Chae, Daniel and Naik, Hemal and Li, Liang and Koger, Benjamin and Costelloe, Blair R and Couzin, Iain D},
  journal={Elife},
  volume={8},
  pages={e47994},
  year={2019},
  publisher={eLife Sciences Publications Limited}
}

Results on Desert Locust test set

Arch	Input Size	PCK@0.2	AUC	EPE	ckpt	log
pose_resnet_50	160x160	1.000	0.900	2.27	ckpt	log
pose_resnet_101	160x160	1.000	0.907	2.03	ckpt	log
pose_resnet_152	160x160	1.000	0.925	1.49	ckpt	log

Ak Dataset¶

Topdown Heatmap + Hrnet + Animalkingdom on Ak¶

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}
}

AnimalKingdom (CVPR'2022)

@InProceedings{
    Ng_2022_CVPR,
    author    = {Ng, Xun Long and Ong, Kian Eng and Zheng, Qichen and Ni, Yun and Yeo, Si Yong and Liu, Jun},
    title     = {Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {19023-19034}
 }

Results on AnimalKingdom validation set

Arch	Input Size	PCK(0.05)	Official Repo	Paper	ckpt	log
P1_hrnet_w32	256x256	0.6323	0.6342	0.6606	ckpt	log
P2_hrnet_w32	256x256	0.3741	0.3726	0.393	ckpt	log
P3_mammals_hrnet_w32	256x256	0.571	0.5719	0.6159	ckpt	log
P3_amphibians_hrnet_w32	256x256	0.5358	0.5432	0.5674	ckpt	log
P3_reptiles_hrnet_w32	256x256	0.51	0.5	0.5606	ckpt	log
P3_birds_hrnet_w32	256x256	0.7671	0.7636	0.7735	ckpt	log
P3_fishes_hrnet_w32	256x256	0.6406	0.636	0.6825	ckpt	log