{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:31:26Z","timestamp":1778081486694,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2024581"],"award-info":[{"award-number":["2024581"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["OD011092"],"award-info":[{"award-number":["OD011092"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["OD011132"],"award-info":[{"award-number":["OD011132"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["R01-NS120182"],"award-info":[{"award-number":["R01-NS120182"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["K99-MH083883"],"award-info":[{"award-number":["K99-MH083883"]}],"id":[{"id":"10.13039\/100000065","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":[[2023,1]]},"DOI":"10.1007\/s11263-022-01698-2","type":"journal-article","created":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T08:02:10Z","timestamp":1665907330000},"page":"243-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["OpenMonkeyChallenge: Dataset and Benchmark Challenges for Pose Estimation of Non-human Primates"],"prefix":"10.1007","volume":"131","author":[{"given":"Yuan","family":"Yao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2144-1986","authenticated-orcid":false,"given":"Praneet","family":"Bala","sequence":"additional","affiliation":[]},{"given":"Abhiraj","family":"Mohan","sequence":"additional","affiliation":[]},{"given":"Eliza","family":"Bliss-Moreau","sequence":"additional","affiliation":[]},{"given":"Kristine","family":"Coleman","sequence":"additional","affiliation":[]},{"given":"Sienna M.","family":"Freeman","sequence":"additional","affiliation":[]},{"given":"Christopher J.","family":"Machado","sequence":"additional","affiliation":[]},{"given":"Jessica","family":"Raper","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Zimmermann","sequence":"additional","affiliation":[]},{"given":"Benjamin Y.","family":"Hayden","sequence":"additional","affiliation":[]},{"given":"Hyun Soo","family":"Park","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,16]]},"reference":[{"key":"1698_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., & Schiele, B. (2014). 2D human pose estimation: New benchmark and state of the art analysis. In Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2014.471"},{"key":"1698_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Iqbal, U., Milan, A., Insafutdinov, E., Pishchulin, L., Gall, J., & Schiele, B. (2018). Posetrack: A benchmark for human pose estimation and tracking. In Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2018.00542"},{"key":"1698_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.\u00a0L., & Parikh, D. (2015). VQA: Visual question answering. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2015.279"},{"key":"1698_CR4","doi-asserted-by":"crossref","unstructured":"Bala, P., Eisenreich, B., Yoo, S.\u00a0B., Hayden, B., Park, H., & Zimmermann, J. (2020). Automated markerless pose estimation in freely moving macaques with openmonkeystudio. Nature Communications.","DOI":"10.1101\/2020.01.31.928861"},{"key":"1698_CR5","doi-asserted-by":"crossref","unstructured":"Belagiannis, V., & Zisserman, A. (2017). Recurrent human pose estimation. In International Conference on Automatic Face & Gesture Recognition.","DOI":"10.1109\/FG.2017.64"},{"key":"1698_CR6","doi-asserted-by":"crossref","unstructured":"Bliss-Moreau, E., Machado, C.\u00a0J., & Amaral, D.\u00a0G. (2013). Macaque cardiac physiology is sensitive to the valence of passively viewed sensory stimuli. PLoS One.","DOI":"10.1371\/journal.pone.0071170"},{"key":"1698_CR7","unstructured":"Cao, Z., Martinez, G.\u00a0H., Simon, T., Wei, S.-E., & Sheikh, Y.\u00a0A. (2019). Openpose: Realtime multi-person 2d pose estimation using part affinity fields. IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"1698_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.\u00a0S., & Zhang, L. (2020). Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"1698_CR9","unstructured":"de Bem, R., Arnab, A., Golodetz, S., Sapienza, M., & Torr, P. H.\u00a0S. (2018). Deep fully-connected part-based models for human pose estimation. In Asian conference on machine learning."},{"key":"1698_CR10","doi-asserted-by":"crossref","unstructured":"Dunn, T., Marshall, J., Severson, K., Aldarondo, D., Hildebrand, D., Chettih, S., Wang, W., Gellis, A., Carlson, D., Aronov, D., Freiwald, W., Wang, F., & Olveczky, B. (2021). Geometric deep learning enables 3D kinematic profiling across species and environments. Nature Methods.","DOI":"10.1038\/s41592-021-01106-6"},{"key":"1698_CR11","doi-asserted-by":"crossref","unstructured":"Eichner, M., & Ferrari, V. (2010). We are family: Joint pose estimation of multiple persons. In European Conference on Computer Vision.","DOI":"10.1007\/978-3-642-15549-9_17"},{"key":"1698_CR12","doi-asserted-by":"crossref","unstructured":"Fang, H.-S., Xie, S., Tai, Y.-W., & Lu, C. (2017). RMPE: Regional multi-person pose estimation. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.256"},{"key":"1698_CR13","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.\u00a0A., Neverova, N., & Kokkinos, I. (2018). Densepose: Dense human pose estimation in the wild. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00762"},{"key":"1698_CR14","doi-asserted-by":"crossref","unstructured":"G\u00fcnel, S., Rhodin, H., Morales, D., Campagnolo, J., Ramdya, P., & Fua, P. (2019). Deepfly3d, a deep learning-based approach for 3d limb and appendage tracking in tethered, adult drosophila. eLife.","DOI":"10.7554\/eLife.48571.033"},{"key":"1698_CR15","doi-asserted-by":"crossref","unstructured":"Hayden, B.\u00a0Y., Park, H.\u00a0S., & Zimmermann, J. (2021). Automated pose estimation in primates. American Journal of Primatology.","DOI":"10.31234\/osf.io\/36e7h"},{"key":"1698_CR16","doi-asserted-by":"crossref","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., & Schiele, B. (2016). Deepercut: A deeper, stronger, and faster multi-person pose estimation model. In European conference on computer vision.","DOI":"10.1007\/978-3-319-46466-4_3"},{"key":"1698_CR17","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Milan, A., & Gall, J. (2017). Posetrack: Joint multi-person pose estimation and tracking. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.495"},{"key":"1698_CR18","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., & Malkov, Y. (2019). Learnable triangulation of human pose. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00781"},{"key":"1698_CR19","doi-asserted-by":"crossref","unstructured":"Jakab, T., Gupta, A., Bilen, H., & Vedaldi, A. (2020). Self-supervised learning of interpretable keypoints from unlabelled videos. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00881"},{"key":"1698_CR20","doi-asserted-by":"crossref","unstructured":"Karashchuk, P., Rupp, K., Dickinson, E., Sanders, E., Azim, E., Brunton, B., & Tuthill, J. (2020). Anipose: A toolkit for robust markerless 3D pose estimation. In BioRxiv.","DOI":"10.1101\/2020.05.26.117325"},{"key":"1698_CR21","doi-asserted-by":"crossref","unstructured":"Knaebe, B., Weiss, C., Zimmermann, J., & Hayden, B. (2022). The promise of behavioral tracking systems for advancing primate animal welfare. Animals.","DOI":"10.3390\/ani12131648"},{"key":"1698_CR22","doi-asserted-by":"crossref","unstructured":"Labuguen, R., Matsumoto, J., Negrete, S., Nishimaru, H., Nishijo, H., Takada, M., Go, Y., Inoue, K.-I., & Shibata, T. (2021). Macaquepose: A novel \u201cin the wild\u201d macaque monkey pose dataset for markerless motion capture. Frontiers in Behavioral Neuroscience.","DOI":"10.1101\/2020.07.30.229989"},{"key":"1698_CR23","doi-asserted-by":"crossref","unstructured":"Li, S., Li, J., Tang, H., Qian, R., & Lin, W. (2020). ATRW: A benchmark for amur tiger re-identification in the wild. In ACM International Conference on Multimedia.","DOI":"10.1145\/3394171.3413569"},{"key":"1698_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.\u00a0L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1698_CR25","unstructured":"Lin, W., Liu, H., Liu, S., Li, Y., Qian, R., Wang, T., Xu, N., Xiong, H., Qi, G.-J., & Sebe, N. (2020). Human in events: A large-scale benchmark for human-centric video analysis in complex events. arXiv preprintarXiv:2005.04490."},{"key":"1698_CR26","doi-asserted-by":"crossref","unstructured":"Ludwig, K., Scherer, S., Einfalt, M., & Lienhart, R. (2021). Self-supervised learning for human pose estimation in sports. In IEEE International Conference on Multimedia Expo Workshops.","DOI":"10.1109\/ICMEW53276.2021.9456000"},{"key":"1698_CR27","doi-asserted-by":"crossref","unstructured":"Machado, C.\u00a0J., Bliss-Moreau, E., Platt, M.\u00a0L., & Amaral, D.\u00a0G. (2011). Social and nonsocial content differentially modulates visual attention and autonomic arousal in rhesus macaques. PLoS One.","DOI":"10.1371\/journal.pone.0026598"},{"key":"1698_CR28","doi-asserted-by":"crossref","unstructured":"Mathis, A., Mamidanna, P., Cury, K.\u00a0M., Abe, T., Murthy, V.\u00a0N., Mathis, M.\u00a0W., & Bethge, M. (2018). Deeplabcut: Markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience.","DOI":"10.1038\/s41593-018-0209-y"},{"key":"1698_CR29","doi-asserted-by":"crossref","unstructured":"Mathis, M.\u00a0W., & Mathis, A. (2020). Deep learning tools for the measurement of animal behavior in neuroscience. Current Opinion in Neurobiology.","DOI":"10.1016\/j.conb.2019.10.008"},{"key":"1698_CR30","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., & Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv.","DOI":"10.21105\/joss.00861"},{"key":"1698_CR31","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., & Deng, J. (2016). Stacked hourglass networks for human pose estimation. In European conference on computer vision.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1698_CR32","doi-asserted-by":"crossref","unstructured":"Ng, X.\u00a0L., Ong, K.\u00a0E., Zheng, Q., Ni, Y., Yeo, S.\u00a0Y., & Liu, J. (2022). Animal kingdom: A large and diverse dataset for animal behavior understanding. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"1698_CR33","doi-asserted-by":"crossref","unstructured":"Pereira, T.\u00a0D., Aldarondo, D.\u00a0E., Willmore, L., Kislin, M., Wang, S. S.\u00a0H., Murthy, M., & Shaevitz, J.\u00a0W. (2018). Fast animal pose estimation using deep neural networks. Nature Methods.","DOI":"10.1101\/331181"},{"key":"1698_CR34","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., & Schiele, B. (2016). Deepcut: Joint subset partition and labeling for multi person pose estimation. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.533"},{"key":"1698_CR35","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"1698_CR36","doi-asserted-by":"crossref","unstructured":"Ren, Z., & Lee, Y.\u00a0J. (2018). Cross-domain self-supervised multi-task feature learning using synthetic imagery. In computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00086"},{"key":"1698_CR37","doi-asserted-by":"crossref","unstructured":"Sade, D.\u00a0S. (1973). An ethogram for rhesus monkeys i. Antithetical contrasts in posture and movement. American Journal of Physical Anthropology.","DOI":"10.1002\/ajpa.1330380263"},{"key":"1698_CR38","doi-asserted-by":"crossref","unstructured":"Sapp, B., & Taskar, B. (2013). Modec: Multimodal decomposable models for human pose estimation. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.471"},{"key":"1698_CR39","doi-asserted-by":"crossref","unstructured":"Sumer, O., Dencker, T., & Ommer, B. (2017). Self-supervised learning of pose embeddings from spatiotemporal relations in videos. In International conference on computer vision.","DOI":"10.1109\/ICCV.2017.461"},{"key":"1698_CR40","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., & Wang, J. (2019). Deep high-resolution representation learning for human pose estimation. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1698_CR41","doi-asserted-by":"crossref","unstructured":"Torralba, A., & Efros, A.\u00a0A. (2011). Unbiased look at dataset bias. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"1698_CR42","doi-asserted-by":"crossref","unstructured":"Toshev, A., & Szegedy, C. (2014). Deeppose: Human pose estimation via deep neural networks. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.214"},{"key":"1698_CR43","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., & Pons-Moll, G. (2018). Recovering accurate 3D human pose in the wild using imus and a moving camera. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"1698_CR44","doi-asserted-by":"crossref","unstructured":"Wan, C., Probst, T., Gool, L.\u00a0V., & Yao, A. (2019). Self-supervised 3D hand pose estimation through training by fitting. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.01111"},{"key":"1698_CR45","doi-asserted-by":"crossref","unstructured":"Wei, S.-E., Ramakrishna, V., Kanade, T., & Sheikh, Y. (2016). Convolutional pose machines. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.511"},{"key":"1698_CR46","doi-asserted-by":"crossref","unstructured":"Wiltschko, A., Johnson, M., Iurilli, G., Peterson, R., Katon, J., Pashkovski, S., Abraira, V., Adams, R., & Datta, S. (2015). Mapping sub-second structure in mouse behavior. Neuron.","DOI":"10.1016\/j.neuron.2015.11.031"},{"key":"1698_CR47","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., & Wei, Y. (2018). Simple baselines for human pose estimation and tracking. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"1698_CR48","doi-asserted-by":"crossref","unstructured":"Yang, H., Dong, W., Carlone, L., & Koltun, V. (2021). Self-supervised geometric perception. In Computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.01412"},{"key":"1698_CR49","doi-asserted-by":"crossref","unstructured":"Yao, Y., Jafarian, Y., & Park, H.\u00a0S. (2019). Monet: Multiview semi-supervised keypoint via epipolar divergence. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2019.00084"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01698-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01698-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01698-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T08:07:33Z","timestamp":1688717253000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01698-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["1698"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01698-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,16]]},"assertion":[{"value":"24 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest. All procedures were performed in compliance with the guidelines of the IACUC of the University of Minnesota.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All procedures were performed in compliance with the guidelines of the IACUC of the University of Minnesota.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Informed consent is not relevant because there were no human subjects.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}]}}