{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/superanimal-quadruped","name":"SuperAnimal-Quadruped","full_name":null,"description_markdown":"# Introduction\r\nThis dataset supports Ye et al. 2024 Nature Communications. \r\n\r\nYe, S., Filippova, A., Lauer, J. et al. SuperAnimal pretrained pose estimation models for behavioral analysis. Nat Commun 15, 5165 (2024). https://doi.org/10.1038/s41467-024-48792-2\r\n\r\nPlease cite this dataset and paper if you use this resource. Please also see Ye et al. 2024 for the full DataSheet accompanying this download, including the metadata for how to use this data if you want to compare model results on benchmark tasks. Below is just a summary. Also see the dataset licensing below.\r\n\r\n# Training Data\r\nIt consists of being trained together on the following datasets:\r\n\r\nAwA-Pose Quadruped dataset, see full details at (1).\r\nAnimalPose See full details at (2).\r\nAcinoSet See full details at (3).\r\nHorse-30 Horse-30 dataset, benchmark task is called Horse-10; See full details at (4).\r\nStanfordDogs See full details at (5, 6).\r\nAP-10K See full details at (7).\r\niRodent We utilized the iNaturalist API functions for scraping observations with the taxon ID of Suborder Myomorpha (8). The functions allowed us to filter the large amount of observations down to the ones with photos under the CC BY-NC creative license. The most common types of rodents from the collected observations are Muskrat (Ondatra zibethicus), Brown Rat (Rattus norvegicus), House Mouse (Mus musculus), Black Rat (Rattus rattus), Hispid Cotton Rat (Sigmodon hispidus), Meadow Vole (Microtus pennsylvanicus), Bank Vole (Clethrionomys glareolus), Deer Mouse (Peromyscus maniculatus), White-footed Mouse (Peromyscus leucopus), Striped Field Mouse (Apodemus agrarius). We then generated segmentation masks over target animals in the data by processing the media through an algorithm we designed that uses a Mask Region Based Convolutional Neural Networks(Mask R-CNN) (9) model with a ResNet-50-FPN backbone (10), pretrained on the COCO datasets (11). The processed 443 images were then manually labeled with both pose annotations and segmentation masks. iRodent data is banked at https://zenodo.org/record/8250392. \r\nAPT-36K See full details at (12).\r\nHere is an image with a keypoint guide.\r\n\r\n#Ethical Considerations\r\n• No experimental data was collected for this model; all datasets used are cited above.\r\n\r\n#Caveats and Recommendations\r\n• Please note that each dataest was labeled by separate labs & separate individuals, therefore while we map names to a unified pose vocabulary, there will be annotator bias in keypoint placement (See Ye et al. 2024 for our Supplementary Note on annotator bias). You will also note the dataset is highly diverse across species, but collectively has more representation of domesticated animals like dogs, cats, horses, and cattle. We recommend if performance of a model trained on this data is not as good as you need it to be, first try video adaptation (see Ye et al. 2024), or fine-tune the weights with your own labeling.\r\n\r\n#License\r\nModified MIT.\r\n\r\nCopyright 2023-present by Mackenzie Mathis, Shaokai Ye, and contributors. \r\n\r\nPermission is hereby granted to you (hereafter \"LICENSEE\") a fully-paid, non-exclusive,\r\nand non-transferable license for academic, non-commercial purposes only (hereafter “LICENSE”)\r\nto use the \"DATASET\" subject to the following conditions:\r\n\r\nThe above copyright notice and this permission notice shall be included in all copies or substantial\r\nportions of the Software:\r\n\r\nThis data or resulting software may not be used to harm any animal deliberately.\r\n\r\nLICENSEE acknowledges that the DATASET is a research tool. \r\nTHE DATASET IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING \r\nBUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE DATASET OR THE USE OR OTHER DEALINGS IN THE DATASET.\r\n\r\nIf this license is not appropriate for your application, please contact Prof. Mackenzie W. Mathis \r\n(mackenzie@post.harvard.edu) for a commercial use license.\r\n\r\nPlease cite Ye et al 2024  if you use this DATASET in your work.\r\n\r\n \r\n\r\n#References\r\nPrianka Banik, Lin Li, and Xishuang Dong. A novel dataset for keypoint detection of quadruped animals from images. ArXiv, abs/2108.13958, 2021\r\n\r\nJinkun Cao, Hongyang Tang, Haoshu Fang, Xiaoyong Shen, Cewu Lu, and Yu-Wing Tai. Cross-domain adaptation for animal pose estimation. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 9497–9506, 2019.\r\n\r\nDaniel Joska, Liam Clark, Naoya Muramatsu, Ricardo Jericevich, Fred Nicolls, Alexander Mathis, Mackenzie W. Mathis, and Amir Patel. Acinoset: A 3d pose estimation dataset and baseline models for cheetahs in the wild. 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 13901–13908, 2021.\r\n\r\nAlexander Mathis, Thomas Biasi, Steffen Schneider, Mert Yuksekgonul, Byron Rogers, Matthias Bethge, and Mackenzie W Mathis. Pretraining boosts out-of-domain robustness for pose estimation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1859–1868, 2021.\r\n\r\nAditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Li Fei-Fei. Novel dataset for fine-grained image categorization. In First Workshop on Fine-Grained Visual Categorization, IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, June 2011.\r\n\r\nBenjamin Biggs, Thomas Roddick, Andrew Fitzgibbon, and Roberto Cipolla. Creatures great and smal: Recovering the shape and motion of animals from video. In Asian Conference on Computer Vision, pages 3–19. Springer, 2018.\r\nHang Yu, Yufei Xu, Jing Zhang, Wei Zhao, Ziyu Guan, and Dacheng Tao. Ap-10k: A benchmark for animal pose estimation in the wild. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), 2021.\r\n\r\niNaturalist. OGBIF Occurrence Download. https://doi.org/10.15468/dl.p7nbxt. iNaturalist, July 2020\r\n\r\nKaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.\r\n\r\nTsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection, 2016.\r\n\r\nTsung-Yi Lin, Michael Maire, Serge J. Belongie, Lubomir D. Bourdev, Ross B. Girshick, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll’ar, and C. Lawrence Zitnick. Microsoft COCO: common objects in context. CoRR, abs/1405.0312, 2014\r\n\r\nYuxiang Yang, Junjie Yang, Yufei Xu, Jing Zhang, Long Lan, and Dacheng Tao. Apt-36k: A large-scale benchmark for animal pose estimation and tracking. Advances in Neural Information Processing Systems, 35:17301–17313, 2022","description_withheld":null,"homepage":"https://zenodo.org/records/14016777","introduced_date":"2024-03-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/panoptic-animal-pose-estimators-are-zero-shot","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","first_author":"Shaokai Ye","url":null},"license":{"name":"NC","url":"https://zenodo.org/records/14016777"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Animal Pose Estimation","url":"/task/animal-pose-estimation","datasets_with_task":"/datasets/task/animal-pose-estimation"}],"languages":[],"variants":["SuperAnimal-Quadruped"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":0,"of":0,"counts":{"papers_with_a_benchmark_row":0,"with_a_code_link":0,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":0,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"71f4c594e34be596716adf6012b69c61ba1e97144d7c08ec640ad8569cd3ea1e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}