{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:00:40Z","timestamp":1770346840087,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":85,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609710","type":"print"},{"value":"9789819609727","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0972-7_16","type":"book-chapter","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T08:08:21Z","timestamp":1733731701000},"page":"268-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Dessie: Disentanglement for\u00a0Articulated 3D Horse Shape and\u00a0Pose Estimation from\u00a0Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7627-0125","authenticated-orcid":false,"given":"Ci","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6679-4021","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9486-9238","authenticated-orcid":false,"given":"Zehang","family":"Weng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5769-3958","authenticated-orcid":false,"given":"Elin","family":"Hernlund","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1358-0828","authenticated-orcid":false,"given":"Silvia","family":"Zuffi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5750-9655","authenticated-orcid":false,"given":"Hedvig","family":"Kjellstr\u00f6m","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"16_CR1","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: Deep vit features as dense visual descriptors. ECCVW What is Motion For? (2022)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Badger, M., Wang, Y., Modh, A., Perkes, A., Kolotouros, N., Pfrommer, B.G., Schmidt, M.F., Daniilidis, K.: 3d bird reconstruction: a dataset, model, and shape recovery from a single view. In: European Conference on Computer Vision. pp. 1\u201317 (2020)","DOI":"10.1007\/978-3-030-58523-5_1"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Biggs, B., Boyne, O., Charles, J., Fitzgibbon, A., Cipolla, R.: Who left the dogs out? 3D animal reconstruction with expectation maximization in the loop. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58621-8_12"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Biggs, B., Roddick, T., Fitzgibbon, A., Cipolla, R.: Creatures great and smal: Recovering the shape and motion of animals from video. In: Computer Vision\u2013ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2\u20136, 2018, Revised Selected Papers, Part V 14. pp. 3\u201319. Springer (2019)","DOI":"10.1007\/978-3-030-20873-8_1"},{"key":"16_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"16_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/3-540-47967-8_8","volume-title":"Computer Vision \u2014 ECCV 2002","author":"E Borenstein","year":"2002","unstructured":"Borenstein, E., Ullman, S.: Class-Specific, Top-Down Segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 109\u2013122. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-47967-8_8"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Cao, J., Tang, H., Fang, H.S., Shen, X., Lu, C., Tai, Y.W.: Cross-domain adaptation for animal pose estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 9498\u20139507 (2019)","DOI":"10.1109\/ICCV.2019.00959"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"1","key":"16_CR9","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1109\/TPAMI.2012.68","volume":"35","author":"TJ Cashman","year":"2012","unstructured":"Cashman, T.J., Fitzgibbon, A.W.: What shape are dolphins? building 3d morphable models from 2d images. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 232\u2013244 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International conference on machine learning. pp. 1597\u20131607. PMLR (2020)"},{"key":"16_CR11","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: Interpretable representation learning by information maximizing generative adversarial nets. Advances in neural information processing systems 29 (2016)"},{"key":"16_CR12","unstructured":"Council, A.H.: Economic impact study (2023), https:\/\/horsecouncil.org\/economic-impact-study\/"},{"key":"16_CR13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"16_CR14","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: A retrospective. Int. J. Comput. Vision 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"16_CR15","first-page":"5","volume":"4","author":"S Geman","year":"1987","unstructured":"Geman, S.: Statistical methods for tomographic image reconstruction. Bull. Int. Stat. Inst 4, 5\u201321 (1987)","journal-title":"Bull. Int. Stat. Inst"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa*, A., Malik*, J.: Humans in 4D: Reconstructing and tracking humans with transformers. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Hao, S., Han, K., Wong, K.Y.K.: Learning attention as disentangler for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01470"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR21","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., Lerchner, A.: beta-vae: Learning basic visual concepts with a constrained variational framework. In: International conference on learning representations (2016)"},{"key":"16_CR22","unstructured":"Hu, X., Li, X., Busam, B., Zhou, Y., Leonardis, A., Yuan, S.: Disentangling 3d attributes from a single 2d image: Human pose, shape and garment. The British Machine Vision Conference (2022)"},{"key":"16_CR23","unstructured":"IBISWorld: Horse & other equine production in the us - market size, industry analysis, trends and forecasts (2023), https:\/\/www.ibisworld.com\/united-states\/market-research-reports\/horse-other-equine-production-industry\/#ExternalEnvironment"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Jakab, T., Li, R., Wu, S., Rupprecht, C., Vedaldi, A.: Farm3D: Learning articulated 3d animals by distilling 2d diffusion. In: 2024 International Conference on 3D Vision (3DV). IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00051"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3d human dynamics from video. In: Computer Vision and Pattern Regognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00576"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Kearney, S., Li, W., Parsons, M., Kim, K.I., Cosker, D.: Rgbd-dog: Predicting canine pose from rgbd sensors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8336\u20138345 (2020)","DOI":"10.1109\/CVPR42600.2020.00836"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Keller, M., Arora, V., Dakri, A., Chandhok, S., Machann, J., Fritsche, A., Black, M.J., Pujades, S.: HIT: Estimating internal human implicit tissues from the body surface. In: Proceedings IEEE\/CVF Conf.\u00a0on Computer Vision and Pattern Recognition (CVPR) (Jun 2024)","DOI":"10.1109\/CVPR52733.2024.00334"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Keller, M., Werling, K., Shin, S., Delp, S., Pujades, S., Liu, C.K., Black, M.J.: From skin to skeleton: Towards biomechanically accurate 3d digital humans. In: ACM ToG, Proc.\u00a0SIGGRAPH Asia (Dec 2023)","DOI":"10.1145\/3618381"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.P., Hilliges, O., Black, M.J.: Pare: Part attention regressor for 3d human body estimation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 11107\u201311117. IEEE Computer Society, Los Alamitos, CA, USA (oct 2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: Video inference for human body pose and shape estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5253\u20135263 (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Jayaraman, D., Daniilidis, K.: Probabilistic modeling for human mesh recovery. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 11585\u201311594. IEEE Computer Society, Los Alamitos, CA, USA (oct 2021)","DOI":"10.1109\/ICCV48922.2021.01140"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3d human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Kotovenko, D., Sanakoyeu, A., Lang, S., Ommer, B.: Content and style disentanglement for artistic style transfer. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 4422\u20134431 (2019)","DOI":"10.1109\/ICCV.2019.00452"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Kulkarni, N., Gupta, A., Fouhey, D.F., Tulsiani, S.: Articulation-aware canonical surface mapping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 452\u2013461 (2020)","DOI":"10.1109\/CVPR42600.2020.00053"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V.: Unite the people: Closing the loop between 3d and 2d human representations. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4704\u20134713. IEEE Computer Society, Los Alamitos, CA, USA (jul 2017)","DOI":"10.1109\/CVPR.2017.500"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Li, C., Lee, G.H.: From synthetic to real: Unsupervised domain adaptation for animal pose estimation. CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00153"},{"key":"16_CR38","unstructured":"Li, C., Ghorbani, N., Broom\u00e9, S., Rashid, M., Black, M.J., Hernlund, E., Kjellstr\u00f6m, H., Zuffi, S.: hsmal: Detailed horse shape and pose reconstruction for motion pattern recognition. arXiv preprint arXiv:2106.10102 (2021)"},{"issue":"1","key":"16_CR39","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., Polikovsky, S., Holmberg, M., Ghorbani, N., Black, M.J., Kjellstr\u00f6m, H., Zuffi, S., Hernlund, E.: The poses for equine research dataset (pferd). Scientific Data 11(1), 497 (2024)","journal-title":"Scientific Data"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3382\u20133392. IEEE Computer Society, Los Alamitos, CA, USA (jun 2021)","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Li, J., Bian, S., Liu, Q., Tang, J., Wang, F., Lu, C.: Niki: Neural inverse kinematics with invertible neural networks for 3d human pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12933\u201312942 (2023)","DOI":"10.1109\/CVPR52729.2023.01243"},{"key":"16_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-030-58568-6_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., Liu, S., Kim, K., De Mello, S., Jampani, V., Yang, M.-H., Kautz, J.: Self-supervised Single-View 3D Reconstruction via Semantic Consistency. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 677\u2013693. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_40"},{"key":"16_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1007\/978-3-031-20065-6_34","volume-title":"Computer Vision - ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., Liu, J., Zhang, Z., Xu, S., Yan, Y.: Cliff: Carrying location information in full frames into human pose and shape estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 590\u2013606. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_34"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Li, Z., Litvak, D., Li, R., Zhang, Y., Jakab, T., Rupprecht, C., Wu, S., Vedaldi, A., Wu, J.: Learning the 3d fauna of the web. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00931"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Liautard, A.F.A.: Lameness of horses and diseases of the locomotory apparatus. WR Jenkins (1888)","DOI":"10.5962\/bhl.title.42824"},{"key":"16_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: Common Objects in Context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"6","key":"16_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: A skinned multi-person linear model. ACM transactions on graphics (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM transactions on graphics (TOG)"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Lorenz, D., Bereska, L., Milbich, T., Ommer, B.: Unsupervised part-based disentangling of object shape and appearance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10955\u201310964 (2019)","DOI":"10.1109\/CVPR.2019.01121"},{"key":"16_CR49","volume-title":"Artemis: Articulated neural pets with appearance and motion synthesis","author":"H Luo","year":"2022","unstructured":"Luo, H., Xu, T., Jiang, Y., Zhou, C., Qiu, Q., Zhang, Y., Yang, W., Xu, L., Yu, J.: Artemis: Articulated neural pets with appearance and motion synthesis. ACM Trans, Graph (2022)"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Luo, X., Hu, Y., Gao, Z., Guo, H., Su, Y.: Automated measurement of livestock body based on pose normalisation using statistical shape model. Biosystems Engineering (2023)","DOI":"10.1016\/j.biosystemseng.2023.01.016"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Mathis, A., Biasi, T., Schneider, S., Yuksekgonul, M., Rogers, B., Bethge, M., Mathis, M.W.: Pretraining boosts out-of-domain robustness for pose estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1859\u20131868 (2021)","DOI":"10.1109\/WACV48630.2021.00190"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Mu, J., Qiu, W., Hager, G.D., Yuille, A.L.: Learning from synthetic animals. CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01240"},{"key":"16_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked Hourglass Networks for Human Pose Estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"16_CR54","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H.V., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., Howes, R., Huang, P.Y., Xu, H., Sharma, V., Li, S.W., Galuba, W., Rabbat, M., Assran, M., Ballas, N., Synnaeve, G., Misra, I., Jegou, H., Mairal, J., Labatut, P., Joulin, A., Bojanowski, P.: Dinov2: Learning robust visual features without supervision (2023)"},{"key":"16_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1007\/978-3-030-58539-6_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"AAA Osman","year":"2020","unstructured":"Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: Sparse Trained Articulated Human Body Regressor. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 598\u2013613. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_36"},{"key":"16_CR56","doi-asserted-by":"publisher","unstructured":"Osman, A.A.A., Bolkart, T., Tzionas, D., Black, M.J.: Supr: A sparse unified part-based human representation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 568\u2013585. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_33","DOI":"10.1007\/978-3-031-20086-1_33"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3d human pose and shape from a single color image. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 459\u2013468. IEEE Computer Society, Los Alamitos, CA, USA (jun 2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A., Tzionas, D., Black, M.J.: Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"16_CR59","doi-asserted-by":"crossref","unstructured":"Qing, Z., Zhang, S., Huang, Z., Zhang, Y., Gao, C., Zhao, D., Sang, N.: Disentangling spatial and temporal learning for efficient image-to-video transfer learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01281"},{"key":"16_CR60","unstructured":"Ravi, N., Reizenstein, J., Novotny, D., Gordon, T., Lo, W.Y., Johnson, J., Gkioxari, G.: Accelerating 3d deep learning with pytorch3d. arXiv:2007.08501 (2020)"},{"key":"16_CR61","unstructured":"Research, T.M.: Equine healthcare market (2022), https:\/\/www.transparencymarketresearch.com\/equine-healthcare-market.html"},{"key":"16_CR62","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R., Cohen-Or, D.: Texture: Text-guided texturing of 3d shapes. In: ACM SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"16_CR63","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"16_CR64","doi-asserted-by":"crossref","unstructured":"R\u00fcegg, N., Tripathi, S., Schindler, K., Black, M.J., Zuffi, S.: Bite: Beyond priors for improved three-d dog pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8867\u20138876 (2023)","DOI":"10.1109\/CVPR52729.2023.00856"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"R\u00fcegg, N., Zuffi, S., Schindler, K., Black, M.J.: Barc: Learning to regress 3d dog shape from images by exploiting breed information. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3876\u20133884 (2022)","DOI":"10.1109\/CVPR52688.2022.00385"},{"key":"16_CR66","doi-asserted-by":"crossref","unstructured":"Shooter, M., Malleson, C., Hilton, A.: Digidogs: Single-view 3d pose estimation of dogs using synthetic training data. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops. pp. 80\u201389 (January 2024)","DOI":"10.1109\/WACVW60836.2024.00017"},{"key":"16_CR67","doi-asserted-by":"crossref","unstructured":"Stathopoulos, A., Pavlakos, G., Han, L., Metaxas, D.N.: Learning articulated shape with keypoint pseudo-labels from web images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13092\u201313101 (2023)","DOI":"10.1109\/CVPR52729.2023.01258"},{"key":"16_CR68","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"16_CR69","doi-asserted-by":"crossref","unstructured":"Tian, Y., Zhang, H., Liu, Y., Wang, L.: Recovering 3d human mesh from monocular images: A survey. IEEE transactions on pattern analysis and machine intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3298850"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Tschernezki, V., Laina, I., Larlus, D., Vedaldi, A.: Neural feature fusion fields: 3d distillation of self-supervised 2d image representations. In: 2022 International Conference on 3D Vision (3DV). pp. 443\u2013453. IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Bar-Tal, O., Bagon, S., Dekel, T.: Splicing vit features for semantic appearance transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10748\u201310757 (2022)","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"16_CR72","doi-asserted-by":"crossref","unstructured":"Wang, Y., Kolotouros, N., Daniilidis, K., Badger, M.: Birds of a feather: Capturing avian shape models from images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14739\u201314749 (2021)","DOI":"10.1109\/CVPR46437.2021.01450"},{"key":"16_CR73","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.: Foundationpose: Unified 6d pose estimation and tracking of novel objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17868\u201317879 (2024)","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Wu, S., Li, R., Jakab, T., Rupprecht, C., Vedaldi, A.: MagicPony: Learning articulated 3d animals in the wild. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00849"},{"key":"16_CR75","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhang, Y., Peng, J., Ma, W., Jesslen, A., Ji, P., Hu, Q., Zhang, J., Liu, Q., Wang, J., et\u00a0al.: Animal3d: A comprehensive dataset of 3d animal pose and shape. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9099\u20139109 (2023)","DOI":"10.1109\/ICCV51070.2023.00835"},{"key":"16_CR76","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose+: Vision transformer foundation model for generic body pose estimation. arXiv preprint arXiv:2212.04246 (2022)"},{"key":"16_CR77","first-page":"15296","volume":"35","author":"CH Yao","year":"2022","unstructured":"Yao, C.H., Hung, W.C., Li, Y., Rubinstein, M., Yang, M.H., Jampani, V.: Lassie: Learning articulated shapes from sparse image ensemble via 3d part discovery. Adv. Neural. Inf. Process. Syst. 35, 15296\u201315308 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR78","doi-asserted-by":"crossref","unstructured":"Yao, C.H., Hung, W.C., Li, Y., Rubinstein, M., Yang, M.H., Jampani, V.: Hi-lassie: High-fidelity articulated shape and skeleton discovery from sparse image ensemble. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4853\u20134862 (2023)","DOI":"10.1109\/CVPR52729.2023.00470"},{"key":"16_CR79","unstructured":"Yao, C.H., Raj, A., Hung, W.C., Rubinstein, M., Li, Y., Yang, M.H., Jampani, V.: Artic3d: Learning robust articulated 3d shapes from noisy web image collections. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"16_CR80","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Iqbal, U., Molchanov, P., Kitani, K., Kautz, J.: Glamr: Global occlusion-aware human mesh recovery with dynamic cameras. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 11028\u201311039. IEEE Computer Society, Los Alamitos, CA, USA (jun 2022)","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"16_CR81","doi-asserted-by":"crossref","unstructured":"Zhao, L., Wang, Y., Zhao, J., Yuan, L., Sun, J.J., Schroff, F., Adam, H., Peng, X., Metaxas, D., Liu, T.: Learning view-disentangled human pose representation by contrastive cross-view mutual information maximization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12793\u201312802 (2021)","DOI":"10.1109\/CVPR46437.2021.01260"},{"key":"16_CR82","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/978-3-030-58542-6_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Zhou","year":"2020","unstructured":"Zhou, K., Bhatnagar, B.L., Pons-Moll, G.: Unsupervised Shape and Pose Disentanglement for 3D Meshes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 341\u2013357. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_21"},{"key":"16_CR83","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Kanazawa, A., Berger-Wolf, T., Black, M.J.: Three-d safari: Learning to estimate zebra pose, shape, and texture from images\" in the wild\". In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 5359\u20135368 (2019)","DOI":"10.1109\/ICCV.2019.00546"},{"key":"16_CR84","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Kanazawa, A., Jacobs, D.W., Black, M.J.: 3d menagerie: Modeling the 3d shape and pose of animals. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 6365\u20136373 (2017)","DOI":"10.1109\/CVPR.2017.586"},{"key":"16_CR85","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Mellbin, Y., Li, C., Hoeschle, M., Kjellstr\u00f6m, H., Polikovsky, S., Hernlund, E., Black, M.J.: VAREN: Very accurate and realistic equine network. CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00514"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0972-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T09:08:12Z","timestamp":1733735292000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0972-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"ISBN":["9789819609710","9789819609727"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0972-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"10 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}