{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T09:58:28Z","timestamp":1782554308075,"version":"3.54.5"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200670","type":"print"},{"value":"9783031200687","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20068-7_23","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:06:38Z","timestamp":1668067598000},"page":"398-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Pose for\u00a0Everything: Towards Category-Agnostic Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2125-2760","authenticated-orcid":false,"given":"Lumin","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5736-7434","authenticated-orcid":false,"given":"Sheng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-6332","authenticated-orcid":false,"given":"Wang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6587-9878","authenticated-orcid":false,"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-5563","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9163-2761","authenticated-orcid":false,"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8402-7504","authenticated-orcid":false,"given":"Xiaogang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"23_CR3","unstructured":"Bulat, A., Tzimiropoulos, G.: How far are we from solving the 2D & 3D face alignment problem? In: International Conference on Computer Vision (2017)"},{"key":"23_CR4","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: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00959"},{"key":"23_CR5","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":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: HigherHRNet: scale-aware representation learning for bottom-up human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"23_CR9","unstructured":"Contributors, M.: OpenMMlab pose estimation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmpose (2020)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Duan, H., Lin, K.Y., Jin, S., Liu, W., Qian, C., Ouyang, W.: TRB: a novel triplet representation for understanding 2D human body. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00957"},{"key":"23_CR11","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wang, X., Tang, X., Luo, P.: DeepFashion2: a versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00548"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Graving, J.M., et al.: DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning. Elife 8, e47994 (2019)","DOI":"10.7554\/eLife.47994"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.328"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.396"},{"issue":"6","key":"23_CR17","doi-asserted-by":"publisher","first-page":"2836","DOI":"10.1109\/TIP.2019.2891124","volume":"28","author":"S Jiang","year":"2019","unstructured":"Jiang, S., Liang, S., Chen, C., Zhu, Y., Li, X.: Class agnostic image common object detection. IEEE Trans. Image Process. 28(6), 2836\u20132846 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Jin, S., Liu, W., Ouyang, W., Qian, C.: Multi-person articulated tracking with spatial and temporal embeddings. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00581"},{"key":"23_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/978-3-030-58571-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., et al.: Differentiable hierarchical graph grouping for multi-person pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 718\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_42"},{"key":"23_CR20","unstructured":"Jin, S., et al.: Towards multi-person pose tracking: bottom-up and top-down methods. In: International Conference on Computer Vision Workshop (2017)"},{"key":"23_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-030-58545-7_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., et al.: Whole-body human pose estimation in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 196\u2013214. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_12"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Khan, M.H., et al.: AnimalWeb: a large-scale hierarchical dataset of annotated animal faces. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00697"},{"key":"23_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representions (2015)"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Kostinger, M., Wohlhart, P., Roth, P., Bischof, H.: Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: International Conference on Computer Vision Workshop (2011)","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"23_CR25","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":"23_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Bian, S., Zeng, A., Wang, C., Pang, B., Liu, W., Lu, C.: Human pose regression with residual log-likelihood estimation. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.S., Lu, C.: CrowdPose: efficient crowded scenes pose estimation and a new benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"23_CR28","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. In: ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3413569"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: TokenPose: learning keypoint tokens for human pose estimation. arXiv preprint arXiv:2104.03516 (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"23_CR30","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., et al.: 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"},{"key":"23_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1007\/978-3-030-20893-6_42","volume-title":"Computer Vision \u2013 ACCV 2018","author":"E Lu","year":"2019","unstructured":"Lu, E., Xie, W., Zisserman, A.: Class-agnostic counting. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 669\u2013684. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_42"},{"key":"23_CR32","unstructured":"Lu, J., Gong, P., Ye, J., Zhang, C.: Learning from very few samples: a survey. arXiv preprint arXiv:2009.02653 (2020)"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Mao, W., Ge, Y., Shen, C., Tian, Z., Wang, X., Wang, Z.: TFPose: direct human pose estimation with transformers. arXiv preprint arXiv:2103.15320 (2021)","DOI":"10.1007\/978-3-031-20068-7_5"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Mathis, A., et al.: Pretraining boosts out-of-domain robustness for pose estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2021)","DOI":"10.1109\/WACV48630.2021.00190"},{"key":"23_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-030-58565-5_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Moon","year":"2020","unstructured":"Moon, G., Yu, S.-I., Wen, H., Shiratori, T., Lee, K.M.: InterHand2.6M: a dataset and baseline for 3D interacting hand pose estimation from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 548\u2013564. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_33"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: Ganerated hands for real-time 3D hand tracking from monocular RGB. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Mueller, F., Mehta, D., Sotnychenko, O., Sridhar, S., Casas, D., Theobalt, C.: Real-time hand tracking under occlusion from an egocentric RGB-D sensor. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCVW.2017.82"},{"key":"23_CR38","unstructured":"Nakamura, A., Harada, T.: Revisiting fine-tuning for few-shot learning. arXiv preprint arXiv:1910.00216 (2019)"},{"key":"23_CR39","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":"23_CR40","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zhang, J., Yan, S.: Single-stage multi-person pose machines. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00705"},{"key":"23_CR41","unstructured":"Parmar, N., et al.: Image transformer. In: ICML (2018)"},{"key":"23_CR42","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., et al.: Fast animal pose estimation using deep neural networks. Nat. Methods 16, 117\u2013125 (2019)","journal-title":"Nat. Methods"},{"key":"23_CR43","unstructured":"Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: International Conference on Learning Representions (2017)"},{"key":"23_CR44","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: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00204"},{"key":"23_CR45","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.imavis.2016.01.002","volume":"47","author":"C Sagonas","year":"2016","unstructured":"Sagonas, C., Antonakos, E., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: database and results. Image Vision Comput. 47, 3\u201318 (2016)","journal-title":"Image Vision Comput."},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Shen, J., Zafeiriou, S., Chrysos, G.G., Kossaifi, J., Tzimiropoulos, G., Pantic, M.: The first facial landmark tracking in-the-wild challenge: Benchmark and results. In: International Conference on Computer Vision Workshop (2015)","DOI":"10.1109\/ICCVW.2015.132"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.494"},{"key":"23_CR48","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advance Neural Information and Processing Systems (2017)"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Song, X., et al.: ApolloCar3D: a large 3D car instance understanding benchmark for autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00560"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"23_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advance Neural Information and Processing Systems (2017)"},{"key":"23_CR54","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Advance Neural Information and Processing Systems (2016)"},{"key":"23_CR55","doi-asserted-by":"publisher","first-page":"3258","DOI":"10.1109\/TCSVT.2018.2879980","volume":"29","author":"Y Wang","year":"2018","unstructured":"Wang, Y., Peng, C., Liu, Y.: Mask-pose cascaded CNN for 2D hand pose estimation from single color image. IEEE Trans. Circ. Syst. Video Technol. 29, 3258\u20133268 (2018)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Girshick, R., Hebert, M., Hariharan, B.: Low-shot learning from imaginary data. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00760"},{"key":"23_CR57","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"23_CR58","unstructured":"Welinder, P., et al.: Caltech-UCSD Birds 200. Technical report CNS-TR-2010-001, California Institute of Technology (2010)"},{"key":"23_CR59","unstructured":"Wu, J., et al.: AI challenger: a large-scale dataset for going deeper in image understanding. arXiv preprint arXiv:1711.06475 (2017)"},{"key":"23_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/978-3-319-46466-4_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Wu","year":"2016","unstructured":"Wu, J., et al.: Single image 3D interpreter network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 365\u2013382. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_22"},{"key":"23_CR61","doi-asserted-by":"crossref","unstructured":"Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., Zhou, Q.: Look at boundary: a boundary-aware face alignment algorithm. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00227"},{"key":"23_CR62","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":"23_CR63","doi-asserted-by":"crossref","unstructured":"Xu, L., et al.: ViPNAS: efficient video pose estimation via neural architecture search. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01581"},{"key":"23_CR64","unstructured":"Yang, F.S.Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)"},{"key":"23_CR65","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: TransPose: towards explainable human pose estimation by transformer. arXiv preprint arXiv:2012.14214 (2020)"},{"key":"23_CR66","doi-asserted-by":"crossref","unstructured":"Yang, S.D., Su, H.T., Hsu, W.H., Chen, W.C.: Class-agnostic few-shot object counting. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2021)","DOI":"10.1109\/WACV48630.2021.00091"},{"key":"23_CR67","unstructured":"Yu, H., Xu, Y., Zhang, J., Zhao, W., Guan, Z., Tao, D.: AP-10k: a benchmark for animal pose estimation in the wild. arXiv preprint arXiv:2108.12617 (2021)"},{"key":"23_CR68","unstructured":"Yuan, Y., et al.: HRFormer: high-resolution transformer for dense prediction. arXiv preprint arXiv:2110.09408 (2021)"},{"key":"23_CR69","doi-asserted-by":"crossref","unstructured":"Zafeiriou, S., Trigeorgis, G., Chrysos, G., Deng, J., Shen, J.: The Menpo facial landmark localisation challenge: a step towards the solution. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (2017)","DOI":"10.1109\/CVPRW.2017.263"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: Not all tokens are equal: human-centric visual analysis via token clustering transformer. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, G., Liu, F., Yao, R., Shen, C.: CANet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5217\u20135226 (2019)","DOI":"10.1109\/CVPR.2019.00536"},{"key":"23_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, S.H., et al.: Pose2Seg: detection free human instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00098"},{"key":"23_CR73","doi-asserted-by":"crossref","unstructured":"Zhao, J., Li, J., Cheng, Y., Sim, T., Yan, S., Feng, J.: Understanding humans in crowded scenes: Deep nested adversarial learning and a new benchmark for multi-human parsing. In: ACM International Conference on Multimedia (2018)","DOI":"10.1145\/3240508.3240509"},{"key":"23_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, X., Karpur, A., Luo, L., Huang, Q.: StarMap for category-agnostic keypoint and viewpoint estimation. In: European Conference on Computer Vision, pp. 318\u2013334 (2018)","DOI":"10.1007\/978-3-030-01246-5_20"},{"key":"23_CR75","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.525"},{"key":"23_CR76","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: FreiHAND: a dataset for markerless capture of hand pose and shape from single RGB images. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20068-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T18:26:28Z","timestamp":1678559188000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20068-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200670","9783031200687"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20068-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","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":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}