{"url":"/task/animal-pose-estimation","name":"Animal Pose Estimation","slug":"animal-pose-estimation","description_markdown":"Animal pose estimation is the task of identifying the pose of an animal.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Using DeepLabCut for 3D markerless pose estimation across species and behaviors](http://www.mousemotorlab.org/s/NathMathis2019.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":48,"papers_with_code":36,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":19,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","slug":"animal-pose-estimation-on-ap-10k","dataset":"AP-10K","dataset_url":"/dataset/ap-10k","rows_in_archive":10,"metrics":["AP"],"first_row_in_archive_order":{"model":"ViTPose+-H","paper_title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","paper_url":"/paper/vitpose-vision-transformer-foundation-model","paper_date":"2022-12-07","arxiv_id":"2212.04246","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"vitae-transformer/vitpose","url":"https://github.com/vitae-transformer/vitpose"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/animal-pose-estimation-on-horse-10","slug":"animal-pose-estimation-on-horse-10","dataset":"Horse-10","dataset_url":"/dataset/horse-10","rows_in_archive":8,"metrics":["PCK@0.3 (OOD)","Normalized Error (OOD)"],"first_row_in_archive_order":{"model":"DeepLabCut-EfficientNet-B6","paper_title":"Pretraining boosts out-of-domain robustness for pose estimation","paper_url":"/paper/pretraining-boosts-out-of-domain-robustness","paper_date":"2019-09-24","arxiv_id":"1909.11229","code_links":[{"title":"DeepLabCut/DeepLabCut","url":"https://github.com/DeepLabCut/DeepLabCut"}],"syntology":null}},{"leaderboard":"/sota/animal-pose-estimation-on-trimouse-161","slug":"animal-pose-estimation-on-trimouse-161","dataset":"TriMouse-161","dataset_url":"/dataset/trimouse-161","rows_in_archive":7,"metrics":["mAP"],"first_row_in_archive_order":{"model":"BUCTD-CoAM-W48 (DLCRNet)","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_url":"/paper/rethinking-pose-estimation-in-crowds","paper_date":"2023-06-13","arxiv_id":"2306.07879","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/animal-pose-estimation-on-fish-100","slug":"animal-pose-estimation-on-fish-100","dataset":"Fish-100","dataset_url":"/dataset/fish-100","rows_in_archive":4,"metrics":["mAP"],"first_row_in_archive_order":{"model":"HRNet-W48 + Faster R-CNN","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_url":"/paper/rethinking-pose-estimation-in-crowds","paper_date":"2023-06-13","arxiv_id":"2306.07879","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/animal-pose-estimation-on-marmoset-8k","slug":"animal-pose-estimation-on-marmoset-8k","dataset":"Marmoset-8K","dataset_url":"/dataset/marmoset-8k","rows_in_archive":4,"metrics":["mAP"],"first_row_in_archive_order":{"model":"BUCTD-preNet-W48 (CID-W32)","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_url":"/paper/rethinking-pose-estimation-in-crowds","paper_date":"2023-06-13","arxiv_id":"2306.07879","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/animal-pose-estimation-on-stanfordextra","slug":"animal-pose-estimation-on-stanfordextra","dataset":"StanfordExtra","dataset_url":"/dataset/stanfordextra","rows_in_archive":3,"metrics":["PCK@0.1"],"first_row_in_archive_order":{"model":"8 Stacked Hourglass Network","paper_title":"SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation","paper_url":"/paper/sydog-a-synthetic-dog-dataset-for-improved-2d","paper_date":"2021-07-31","arxiv_id":"2108.00249","code_links":[],"syntology":null}},{"leaderboard":"/sota/animal-pose-estimation-on-animal-pose-dataset","slug":"animal-pose-estimation-on-animal-pose-dataset","dataset":"Animal-Pose Dataset","dataset_url":"/dataset/animal-pose-dataset","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"SuperAnimal-AnimalTokenPose","paper_title":"SuperAnimal pretrained pose estimation models for behavioral analysis","paper_url":"/paper/panoptic-animal-pose-estimators-are-zero-shot","paper_date":"2022-03-14","arxiv_id":"2203.07436","code_links":[{"title":"AlexEMG/DeepLabCut","url":"https://github.com/AlexEMG/DeepLabCut"},{"title":"DeepLabCut/DeepLabCut","url":"https://github.com/DeepLabCut/DeepLabCut"},{"title":"adaptivemotorcontrollab/modelzoo-figures","url":"https://github.com/adaptivemotorcontrollab/modelzoo-figures"}],"syntology":null}},{"leaderboard":"/sota/animal-pose-estimation-on-animal3d","slug":"animal-pose-estimation-on-animal3d","dataset":"Animal3D","dataset_url":"/dataset/animal3d","rows_in_archive":1,"metrics":["PA-MPJPE"],"first_row_in_archive_order":{"model":"PARE","paper_title":"Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape","paper_url":"/paper/animal3d-a-comprehensive-dataset-of-3d-animal","paper_date":"2023-08-22","arxiv_id":"2308.11737","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/ap-10k","name":"AP-10K","full_name":"","num_papers_in_archive":39},{"url":"/dataset/animal-kingdom","name":"Animal Kingdom","full_name":"","num_papers_in_archive":26},{"url":"/dataset/animal-pose-dataset","name":"Animal-Pose Dataset","full_name":"","num_papers_in_archive":21},{"url":"/dataset/stanfordextra","name":"StanfordExtra","full_name":"","num_papers_in_archive":12},{"url":"/dataset/animal3d","name":"Animal3D","full_name":"","num_papers_in_archive":9},{"url":"/dataset/atrw","name":"ATRW","full_name":"Amur Tiger Re-identification in the Wild","num_papers_in_archive":8},{"url":"/dataset/horse-10","name":"Horse-10","full_name":"","num_papers_in_archive":7},{"url":"/dataset/awa-pose","name":"AwA Pose","full_name":"","num_papers_in_archive":4},{"url":"/dataset/3d-pop","name":"3D-POP","full_name":"","num_papers_in_archive":3},{"url":"/dataset/superanimal-quadruped","name":"SuperAnimal-Quadruped","full_name":"","num_papers_in_archive":3},{"url":"/dataset/trimouse-161","name":"TriMouse-161","full_name":"","num_papers_in_archive":3},{"url":"/dataset/fish-100","name":"Fish-100","full_name":"","num_papers_in_archive":2},{"url":"/dataset/lote-animal","name":"LoTE-Animal","full_name":"LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding","num_papers_in_archive":2},{"url":"/dataset/marmoset-8k","name":"Marmoset-8K","full_name":"DeepLabCut multi-animal Marmoset dataset","num_papers_in_archive":2},{"url":"/dataset/mbw-zoo-dataset","name":"MBW - Zoo Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/desert-locust","name":"Desert Locust","full_name":"Desert Locust","num_papers_in_archive":1},{"url":"/dataset/macaquepose","name":"MacaquePose","full_name":"MacaquePose","num_papers_in_archive":1},{"url":"/dataset/vinegar-fly","name":"Vinegar Fly","full_name":"Vinegar Fly","num_papers_in_archive":1},{"url":"/dataset/grevys-zebra","name":"Grévy’s Zebra","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/pose-estimation","name":"Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":36,"tagged_in_all":48,"items":[{"url":"/paper/ap-10k-a-benchmark-for-animal-pose-estimation","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","date":"2021-08-28","arxiv_id":"2108.12617","repositories_listed":5,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/apt-36k-a-large-scale-benchmark-for-animal","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","date":"2022-06-12","arxiv_id":"2206.05683","repositories_listed":4,"syntology":null},{"url":"/paper/panoptic-animal-pose-estimators-are-zero-shot","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","date":"2022-03-14","arxiv_id":"2203.07436","repositories_listed":3,"syntology":null},{"url":"/paper/continuous-surface-embeddings-1","title":"Continuous Surface Embeddings","date":"2020-11-24","arxiv_id":"2011.12438","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/animal-avatars-reconstructing-animatable-3d","title":"Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos","date":"2024-03-25","arxiv_id":"2403.17103","repositories_listed":2,"syntology":null},{"url":"/paper/pose-anything-a-graph-based-approach-for","title":"A Graph-Based Approach for Category-Agnostic Pose Estimation","date":"2023-11-29","arxiv_id":"2311.17891","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/unipose-detecting-any-keypoints","title":"X-Pose: Detecting Any Keypoints","date":"2023-10-12","arxiv_id":"2310.08530","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}},{"url":"/paper/vitpose-vision-transformer-foundation-model","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","date":"2022-12-07","arxiv_id":"2212.04246","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/multi-animal-pose-estimation-identification","title":"Multi-animal pose estimation, identification and tracking with DeepLabCut","date":"2022-04-12","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/mbe-ari-a-multimodal-dataset-mapping-bi","title":"MBE-ARI: A Multimodal Dataset Mapping Bi-directional Engagement in Animal-Robot Interaction","date":"2025-04-11","arxiv_id":"2504.08646","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-prompt-distribution-learning","title":"Probabilistic Prompt Distribution Learning for Animal Pose Estimation","date":"2025-03-20","arxiv_id":"2503.16120","repositories_listed":1,"syntology":null},{"url":"/paper/consistent-multi-animal-pose-estimation-in","title":"Consistent multi-animal pose estimation in cattle using dynamic Kalman filter based tracking","date":"2025-03-13","arxiv_id":"2503.10450","repositories_listed":1,"syntology":null},{"url":"/paper/learning-structure-supporting-dependencies","title":"Learning Structure-Supporting Dependencies via Keypoint Interactive Transformer for General Mammal Pose Estimation","date":"2025-02-25","arxiv_id":"2502.18214","repositories_listed":1,"syntology":null},{"url":"/paper/edge-weight-prediction-for-category-agnostic","title":"Edge Weight Prediction For Category-Agnostic Pose Estimation","date":"2024-11-25","arxiv_id":"2411.16665","repositories_listed":1,"syntology":null},{"url":"/paper/towards-multi-modal-animal-pose-estimation-an","title":"Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis","date":"2024-10-12","arxiv_id":"2410.09312","repositories_listed":1,"syntology":null},{"url":"/paper/capex-category-agnostic-pose-estimation-from","title":"CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation","date":"2024-06-01","arxiv_id":"2406.00384","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptive-pose-estimation-via-multi","title":"Domain adaptive pose estimation via multi-level alignment","date":"2024-04-23","arxiv_id":"2404.14885","repositories_listed":1,"syntology":null},{"url":"/paper/aptv2-benchmarking-animal-pose-estimation-and","title":"APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond","date":"2023-12-25","arxiv_id":"2312.15612","repositories_listed":1,"syntology":null},{"url":"/paper/telling-left-from-right-identifying-geometry","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","date":"2023-11-28","arxiv_id":"2311.17034","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_unverified":4,"n_pointer_only":15}},{"url":"/paper/rethinking-pose-estimation-in-crowds","title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","date":"2023-06-13","arxiv_id":"2306.07879","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/spac-net-synthetic-pose-aware-animal","title":"SPAC-Net: Synthetic Pose-aware Animal ControlNet for Enhanced Pose Estimation","date":"2023-05-29","arxiv_id":"2305.17845","repositories_listed":1,"syntology":null},{"url":"/paper/scarcenet-animal-pose-estimation-with-scarce","title":"ScarceNet: Animal Pose Estimation with Scarce Annotations","date":"2023-03-27","arxiv_id":"2303.15023","repositories_listed":1,"syntology":null},{"url":"/paper/3d-pop-an-automated-annotation-approach-to","title":"3D-POP - An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture","date":"2023-03-23","arxiv_id":"2303.13174","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/prior-aware-synthetic-data-to-the-rescue","title":"Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data","date":"2022-08-30","arxiv_id":"2208.13944","repositories_listed":1,"syntology":null},{"url":"/paper/promptpose-language-prompt-helps-animal-pose","title":"CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose","date":"2022-06-23","arxiv_id":"2206.11752","repositories_listed":1,"syntology":null},{"url":"/paper/animal-kingdom-a-large-and-diverse-dataset","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","date":"2022-04-18","arxiv_id":"2204.08129","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-framework-for-domain-adaptive-pose","title":"A Unified Framework for Domain Adaptive Pose Estimation","date":"2022-04-01","arxiv_id":"2204.00172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/t-leap-occlusion-robust-pose-estimation-of","title":"T-LEAP: Occlusion-robust pose estimation of walking cows using temporal information","date":"2021-04-16","arxiv_id":"2104.08029","repositories_listed":1,"syntology":null},{"url":"/paper/from-synthetic-to-real-unsupervised-domain","title":"From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation","date":"2021-03-27","arxiv_id":"2103.14843","repositories_listed":1,"syntology":null},{"url":"/paper/acinoset-a-3d-pose-estimation-dataset-and","title":"AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild","date":"2021-03-24","arxiv_id":"2103.13282","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}