{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:00:44Z","timestamp":1775325644678,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733369","type":"print"},{"value":"9783031733376","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73337-6_27","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:02:27Z","timestamp":1730329347000},"page":"478-494","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["SCAPE: A Simple and\u00a0Strong Category-Agnostic Pose Estimator"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1432-3461","authenticated-orcid":false,"given":"Yujia","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8517-682X","authenticated-orcid":false,"given":"Zixuan","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1510-6196","authenticated-orcid":false,"given":"Wenze","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3854-8664","authenticated-orcid":false,"given":"Hao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"27_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"27_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: CVPR, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"27_CR4","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. In: Advances in Neural Information Processing Systems, vol.\u00a028 (2015)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Dong, X., Yu, S.I., Weng, X., Wei, S.E., Yang, Y., Sheikh, Y.: Supervision-by-registration: an unsupervised approach to improve the precision of facial landmark detectors. In: CVPR, pp. 360\u2013368 (2018)","DOI":"10.1109\/CVPR.2018.00045"},{"key":"27_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale (2020). arXiv preprint arXiv:2010.11929"},{"key":"27_CR8","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126\u20131135. PMLR (2017)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: Bottom-up human pose estimation via disentangled keypoint regression. In: CVPR, pp. 14676\u201314686 (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K.M.: Cotr: correspondence transformer for matching across images. In: ICCV, pp. 6207\u20136217 (2021)","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Khan, M.H., McDonagh, J., Tzimiropoulos, G.: Synergy between face alignment and tracking via discriminative global consensus optimization. In: ICCV, pp. 3811\u20133819. IEEE (2017)","DOI":"10.1109\/ICCV.2017.409"},{"key":"27_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Labuguen, R., et al.: Macaquepose: a novel \u201cin the wild\u201d macaque monkey pose dataset for markerless motion capture. Front. Behav. Neurosci. 14, 581154 (2021)","DOI":"10.3389\/fnbeh.2020.581154"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Li, S., Li, J., Tang, H., Qian, R., Lin, W.: ATRW: a benchmark for amur tiger re-identification in the wild. arxiv 2019. arXiv preprint arXiv:1906.05586","DOI":"10.1145\/3394171.3413569"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Tokenpose: learning keypoint tokens for human pose estimation. In: ICCV, pp. 11313\u201311322 (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., et\u00a0al.: Group pose: A simple baseline for end-to-end multi-person pose estimation. In: CVPR, pp. 15029\u201315038 (2023)","DOI":"10.1109\/ICCV51070.2023.01380"},{"key":"27_CR18","unstructured":"Liu, S., et al.: Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhu, L., Yamada, M., Yang, Y.: Semantic correspondence as an optimal transport problem. In: CVPR, pp. 4463\u20134472 (2020)","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR21","unstructured":"Lyu, H., Sha, N., Qin, S., Yan, M., Xie, Y., Wang, R.: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Ma, X., Su, J., Wang, C., Ci, H., Wang, Y.: Context modeling in 3D human pose estimation: a unified perspective. In: CVPR, pp. 6238\u20136247 (2021)","DOI":"10.1109\/CVPR46437.2021.00617"},{"key":"27_CR23","unstructured":"Nakamura, A., Harada, T.: Revisiting fine-tuning for few-shot learning. arXiv preprint arXiv:1910.00216 (2019)"},{"key":"27_CR24","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":"27_CR25","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Reddy, N.D., Vo, M., Narasimhan, S.G.: Carfusion: combining point tracking and part detection for dynamic 3d reconstruction of vehicles. In: CVPR, pp. 1906\u20131915 (2018)","DOI":"10.1109\/CVPR.2018.00204"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: learning feature matching with graph neural networks. In: CVPR, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Shi, D., Wei, X., Li, L., Ren, Y., Tan, W.: End-to-end multi-person pose estimation with transformers. In: CVPR, pp. 11069\u201311078 (2022)","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Shi, M., Huang, Z., Ma, X., Hu, X., Cao, Z.: Matching is not enough: a two-stage framework for category-agnostic pose estimation. In: CVPR, pp. 7308\u20137317 (2023)","DOI":"10.1109\/CVPR52729.2023.00706"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Song, X., et al.: Apollocar3D: a large 3D car instance understanding benchmark for autonomous driving. In: CVPR, pp. 5452\u20135462 (2019)","DOI":"10.1109\/CVPR.2019.00560"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Correspondence transformers with asymmetric feature learning and matching flow super-resolution. In: CVPR, pp. 17787\u201317796 (2023)","DOI":"10.1109\/CVPR52729.2023.01706"},{"key":"27_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01231-1_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Xiao","year":"2018","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29"},{"key":"27_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/978-3-031-20068-7_23","volume-title":"ECCV 2022","author":"L Xu","year":"2022","unstructured":"Xu, L., et al.: Pose for everything: Towards category-agnostic pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 398\u2013416. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_23"},{"key":"27_CR35","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose: simple vision transformer baselines for human pose estimation (2022)"},{"key":"27_CR36","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose+: vision transformer foundation model for generic body pose estimation (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73337-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:07:51Z","timestamp":1730329671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73337-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733369","9783031733376"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73337-6_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}