{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T05:33:09Z","timestamp":1793079189363,"version":"4.5.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","award":["Vannevar Bush Faculty Fellowship"],"award-info":[{"award-number":["Vannevar Bush Faculty Fellowship"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-21-2-0104"],"award-info":[{"award-number":["W911NF-21-2-0104"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Automatically estimating animal poses from videos is important for studying animal behavior. Existing methods do not perform reliably, partly because they rely on high-quality training data, and existing such datasets are small. It is challenging and expensive to create such data, due to the large variations in animal morphology and the difficulty of frame-wise video annotation in general. In this paper, we introduce an animal pose labeling pipeline that leverages test-time optimization of a point tracker, providing temporally-consistent annotations at low cost. Given a video, we fine-tune a lightweight appearance embedding inside a pre-trained general-purpose point tracker on a sparse set of annotated frames. These annotations can be obtained from human labelers or off-the-shelf pose detectors. The fine-tuned model is then applied to the rest of the frames for automatic labeling. Our method achieves state-of-the-art performance at a reasonable annotation cost. We believe our pipeline offers a valuable tool for the automatic quantification of animal behavior. Visit our project webpage at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/zhuoyang-pan.github.io\/animal-labeling\" ext-link-type=\"uri\">https:\/\/zhuoyang-pan.github.io\/animal-labeling<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1007\/s11263-026-02976-z","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T19:03:28Z","timestamp":1790190208000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PosePAL: Efficient Animal Pose Labeling Using Point Trackers"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5425-0302","authenticated-orcid":false,"given":"Zhuoyang","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boxiao","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guandao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam W.","family":"Harley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonidas","family":"Guibas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"2976_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., & Gehler, P. (2014). 2d human pose estimation: New benchmark and state of the art analysis. Proceedings of the IEEE Conference on computer vision and pattern recognition (pp. 3686\u20133693)","DOI":"10.1109\/CVPR.2014.471"},{"key":"2976_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Iqbal, U., & Insafutdinov, E. (2018). Posetrack: A benchmark for human pose estimation and tracking. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5167\u20135176)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"2976_CR3","doi-asserted-by":"crossref","unstructured":"Biggs, B., Roddick, T., & Fitzgibbon, A. (2018). Creatures great and SMAL: Recovering the shape and motion of animals from video. ACCV.","DOI":"10.1007\/978-3-030-20873-8_1"},{"key":"2976_CR4","doi-asserted-by":"crossref","unstructured":"Cao, J., Tang, H., & Fang, H. S. (2019). Cross-domain adaptation for animal pose estimation. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9498\u20139507)","DOI":"10.1109\/ICCV.2019.00959"},{"key":"2976_CR5","unstructured":"Cao, Z., Martinez, H., & Simon, G. T. (2019). Openpose: Realtime multi-person 2d pose estimation using part affinity fields. IEEE Transactions on Pattern Analysis and Machine Intelligence,"},{"key":"2976_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Z., Gao, H., Mangalam, K., et\u00a0al. (2020). Long-term human motion prediction with scene context. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16, Springer, (pp 387\u2013404).","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"2976_CR7","doi-asserted-by":"publisher","first-page":"13610","DOI":"10.52202\/068431-0989","volume":"35","author":"C Doersch","year":"2022","unstructured":"Doersch, C., Gupta, A., Markeeva, L., et al. (2022). TAP-VID: A benchmark for tracking any point in a video. Advances in Neural Information Processing Systems, 35, 13610\u201313626.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2976_CR8","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., & Rajasegaran, J. (2023). Humans in 4d: Reconstructing and tracking humans with transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 14783\u201314794)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"2976_CR9","doi-asserted-by":"crossref","unstructured":"G\u00fcnel, S., Rhodin, H., & Morales, D. (2019). Deepfly3d, a deep learning-based approach for 3d limb and appendage tracking in tethered adult drosophila. Elife, 8, Article e48571.","DOI":"10.7554\/eLife.48571"},{"key":"2976_CR10","doi-asserted-by":"crossref","unstructured":"Harley, A. W., Fang, Z., & Fragkiadaki, K. (2022). Particle video revisited: Tracking through occlusions using point trajectories. European Conference on Computer Vision (pp. 59\u201375). Springer.","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"2976_CR11","doi-asserted-by":"crossref","unstructured":"Karaev, N., Makarov, I., Wang, J., et\u00a0al. (2024a). Cotracker3: Simpler and better point tracking by pseudo-labelling real videos. In: arXiv:2410.11831.","DOI":"10.1109\/ICCV51701.2025.00568"},{"key":"2976_CR12","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., et\u00a0al. (2024b). Cotracker: It is better to track together. In ECCV.","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"2976_CR13","doi-asserted-by":"crossref","unstructured":"Labuguen, R., Matsumoto, J., Negrete, S. B., et\u00a0al. (2021). Macaquepose: a novel \u201cin the wild\u201d macaque monkey pose dataset for markerless motion capture. Frontiers in behavioral neuroscience,14, Article 581154.","DOI":"10.3389\/fnbeh.2020.581154"},{"issue":"4","key":"2976_CR14","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1038\/s41592-022-01443-0","volume":"19","author":"J Lauer","year":"2022","unstructured":"Lauer, J., Zhou, M., Ye, S., et al. (2022). Multi-animal pose estimation, identification and tracking with deeplabcut. Nature Methods, 19(4), 496\u2013504.","journal-title":"Nature Methods"},{"issue":"1","key":"2976_CR15","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1038\/s41597-024-03312-1","volume":"11","author":"C Li","year":"2024","unstructured":"Li, C., Mellbin, Y., Krogager, J., et al. (2024). The poses for equine research dataset (pferd). Scientific Data, 11(1), 497.","journal-title":"Scientific Data"},{"key":"2976_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Li, J., Tang, H., et\u00a0al. (2020). ATRW: A benchmark for amur tiger re-identification in the wild. In International Conference on Multimedia.","DOI":"10.1145\/3394171.3413569"},{"key":"2976_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., et\u00a0al. (2014). Microsoft coco: Common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, Springer, (pp 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2976_CR18","doi-asserted-by":"crossref","unstructured":"Mathis, A., Mamidanna, P., Cury, K. M., et al. (2018). Deeplabcut: markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience,21(9), 1281\u20131289.","DOI":"10.1038\/s41593-018-0209-y"},{"key":"2976_CR19","doi-asserted-by":"crossref","unstructured":"Mathis, A., Biasi, T., & Schneider, S. (2021). Pretraining boosts out-of-domain robustness for pose estimation. Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 1859\u20131868)","DOI":"10.1109\/WACV48630.2021.00190"},{"key":"2976_CR20","doi-asserted-by":"crossref","unstructured":"Naik, H., Chan, A. H. H., Yang, J., et\u00a0al. (2023). 3d-pop - an automated annotation approach to facilitate markerless 2d-3d tracking of freely moving birds with marker-based motion capture. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (pp 21274\u201321284).","DOI":"10.1109\/CVPR52729.2023.02038"},{"issue":"7","key":"2976_CR21","doi-asserted-by":"publisher","first-page":"2152","DOI":"10.1038\/s41596-019-0176-0","volume":"14","author":"T Nath","year":"2019","unstructured":"Nath, T., Mathis, A., Chen, A. C., et al. (2019). Using deeplabcut for 3d markerless pose estimation across species and behaviors. Nature Protocols, 14(7), 2152\u20132176.","journal-title":"Nature Protocols"},{"key":"2976_CR22","doi-asserted-by":"crossref","unstructured":"Ng, X. L., Ong, K. E., & Zheng, Q. (2022). Animal kingdom: A large and diverse dataset for animal behavior understanding. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19023\u201319034).","DOI":"10.1109\/CVPR52688.2022.01844"},{"issue":"1","key":"2976_CR23","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1038\/s41592-018-0234-5","volume":"16","author":"TD Pereira","year":"2019","unstructured":"Pereira, T. D., Aldarondo, D. E., Willmore, L., et al. (2019). Fast animal pose estimation using deep neural networks. Nature Methods, 16(1), 117\u2013125.","journal-title":"Nature Methods"},{"issue":"1","key":"2976_CR24","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1038\/s41592-018-0234-5","volume":"16","author":"TD Pereira","year":"2019","unstructured":"Pereira, T. D., Aldarondo, D. E., Willmore, L., et al. (2019). Fast animal pose estimation using deep neural networks. Nature Methods, 16(1), 117\u2013125.","journal-title":"Nature Methods"},{"key":"2976_CR25","unstructured":"Pont-Tuset, J., Perazzi, F., & Caelles, S. (2017). The 2017 davis challenge on video object segmentation arXiv:1704.00675."},{"key":"2976_CR26","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Singer, A., & Bagon, S. (2025). Dino-tracker: Taming dino for self-supervised point tracking in a single video. European Conference on Computer Vision (pp. 367\u2013385). Springer.","DOI":"10.1007\/978-3-031-73347-5_21"},{"key":"2976_CR27","unstructured":"Wu, J., Zheng, H., & Zhao, B. (2017). Ai challenger: A large-scale dataset for going deeper in image understanding arXiv:1711.06475."},{"key":"2976_CR28","doi-asserted-by":"publisher","first-page":"38571","DOI":"10.52202\/068431-2795","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., et al. (2022). Vitpose: Simple vision transformer baselines for human pose estimation. Advances in Neural Information Processing Systems, 35, 38571\u201338584.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2976_CR29","doi-asserted-by":"publisher","first-page":"17301","DOI":"10.52202\/068431-1258","volume":"35","author":"Y Yang","year":"2022","unstructured":"Yang, Y., Yang, J., Xu, Y., et al. (2022). Apt-36k: A large-scale benchmark for animal pose estimation and tracking. Advances in Neural Information Processing Systems, 35, 17301\u201317313.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2976_CR30","unstructured":"Yang, Y., Deng, Y., & Xu, Y. (2023). APTv2: Benchmarking animal pose estimation and tracking with a large-scale dataset and beyond arXiv:2312.15612."},{"issue":"1","key":"2976_CR31","doi-asserted-by":"publisher","first-page":"5165","DOI":"10.1038\/s41467-024-48792-2","volume":"15","author":"S Ye","year":"2024","unstructured":"Ye, S., Filippova, A., Lauer, J., et al. (2024). Superanimal pretrained pose estimation models for behavioral analysis. Nature Communications, 15(1), 5165.","journal-title":"Nature Communications"},{"key":"2976_CR32","unstructured":"Yu, H., Xu, Y., & Zhang, J. (2021). Ap-10k: A benchmark for animal pose estimation in the wild arXiv:2108.12617."},{"key":"2976_CR33","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Harley, A. W., & Shen, B. (2023). Pointodyssey: A large-scale synthetic dataset for long-term point tracking. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 19855\u201319865)","DOI":"10.1109\/ICCV51070.2023.01818"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02976-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02976-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02976-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T04:59:42Z","timestamp":1793077182000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02976-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":33,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["2976"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02976-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"assertion":[{"value":"2 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"447"}}