{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T15:59:41Z","timestamp":1775577581163,"version":"3.50.1"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585440","type":"print"},{"value":"9783030585457","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58545-7_12","type":"book-chapter","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T10:04:51Z","timestamp":1604484291000},"page":"196-214","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":179,"title":["Whole-Body Human Pose Estimation in the Wild"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5736-7434","authenticated-orcid":false,"given":"Sheng","family":"Jin","sequence":"first","affiliation":[]},{"given":"Lumin","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Can","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,5]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Alp G\u00fcler, R., Neverova, N., Kokkinos, I.: DensePose: dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"12_CR3","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"12_CR4","doi-asserted-by":"publisher","first-page":"2930","DOI":"10.1109\/TPAMI.2013.23","volume":"35","author":"PN Belhumeur","year":"2013","unstructured":"Belhumeur, P.N., Jacobs, D.W., Kriegman, D.J., Kumar, N.: Localizing parts of faces using a consensus of exemplars. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2930\u20132940 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Burgos-Artizzu, X.P., Perona, P., Doll\u00e1r, P.: Robust face landmark estimation under occlusion. In: Proceedings of the 2013 IEEE International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.191"},{"key":"12_CR6","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s11263-013-0667-3","volume":"107","author":"X Cao","year":"2014","unstructured":"Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. Int. J. Comput. Vis. 107, 177\u2013190 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1812.08008 (2018)","DOI":"10.1109\/CVPR.2017.143"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"12_CR9","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"12_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: Proceedings of the IEEE International Conference on Computer Vision, pp. 9479\u20139488 (2019)","DOI":"10.1109\/ICCV.2019.00957"},{"key":"12_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1007\/978-3-642-15549-9_17","volume-title":"Computer Vision \u2013 ECCV 2010","author":"M Eichner","year":"2010","unstructured":"Eichner, M., Ferrari, V.: We are family: joint pose estimation of multiple persons. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 228\u2013242. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_17"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: RMPE: regional multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"12_CR13","unstructured":"Gomez-Donoso, F., Orts-Escolano, S., Cazorla, M.: Large-scale multiview 3D hand pose dataset. arXiv preprint arXiv:1707.03742 (2017)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-pie. In: Image and Vision Computing (2010)","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"12_CR15","unstructured":"Guan, H., Chang, J.S., Chen, L., Feris, R.S., Turk, M.: Multi-view appearance-based 3D hand pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (2006)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. arXiv preprint arXiv:1703.06870 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR17","unstructured":"Hidalgo, G., et al.: Single-network whole-body pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Honari, S., Yosinski, J., Vincent, P., Pal, C.: Recombinator networks: learning coarse-to-fine feature aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.619"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Insafutdinov, E., et al.: ArtTrack: articulated multi-person tracking in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.142"},{"key":"12_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Milan, A., Gall, J.: Pose-track: joint multi-person pose estimation and tracking. arXiv preprint arXiv:1611.07727 (2016)","DOI":"10.1109\/CVPR.2017.495"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Jin, S., Liu, W., Ouyang, W., Qian, C.: Multi-person articulated tracking with spatial and temporal embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00581"},{"key":"12_CR23","unstructured":"Jin, S., et al.: Towards multi-person pose tracking: bottom-up and top-down methods. In: IEEE International Conference on Computer Vision Workshop (2017)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Joo, H., Simon, T., Sheikh, Y.: Total capture: a 3D deformation model for tracking faces, hands, and bodies. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00868"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Koestinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: IEEE International Conference on Computer Vision Workshop (2011)","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Kowalski, M., Naruniec, J., Trzcinski, T.: Deep alignment network: a convolutional neural network for robust face alignment. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (2017)","DOI":"10.1109\/CVPRW.2017.254"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"12_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-642-33712-3_49","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V Le","year":"2012","unstructured":"Le, V., Brandt, J., Lin, Z., Bourdev, L., Huang, T.S.: Interactive facial feature localization. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 679\u2013692. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_49"},{"key":"12_CR29","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10863\u201310872 (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"12_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":"12_CR31","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, J., Li, C., Qian, C., Chu, X., Hu, X.: A cascaded inception of inception network with attention modulated feature fusion for human pose estimation. In: The Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12334"},{"key":"12_CR32","unstructured":"Messer, K., Matas, J., Kittler, J., Luettin, J., Maitre, G.: XM2VTSDB: the extended M2VTS database. In: Second International Conference on Audio and Video-Based Biometric Person Authentication (1999)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: Ganerated hands for real-time 3D hand tracking from monocular RGB. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"key":"12_CR34","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: Proceedings of International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.131"},{"key":"12_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-319-16178-5_33","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"N Neverova","year":"2015","unstructured":"Neverova, N., Wolf, C., Taylor, G.W., Nebout, F.: Multi-scale deep learning for gesture detection and localization. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 474\u2013490. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16178-5_33"},{"key":"12_CR36","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. In: Advances in Neural Information Processing Systems (2017)"},{"key":"12_CR37","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":"12_CR38","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Xing, J., Yan, S.: Generative partition networks for multi-person pose estimation. arXiv preprint arXiv:1705.07422 (2017)","DOI":"10.1007\/978-3-030-01228-1_42"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Tracking the articulated motion of two strongly interacting hands. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6247885"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Chen, L.C., Gidaris, S., Tompson, J., Murphy, K.: PersonLab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. arXiv preprint arXiv:1803.08225 (2018)","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Papandreou, G., et al.: Towards accurate multi-person pose estimation in the wild. arXiv preprint arXiv:1701.01779 (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"12_CR42","unstructured":"Pech-Pacheco, J. L., Crist\u00f3bal, G., Chamorro-Martinez, J., Fern\u00e1ndez-Valdivia, J.: Diatom autofocusing in brightfield microscopy: a comparative study. In: ICPR (2000)"},{"key":"12_CR43","unstructured":"Phillips, P.J., et al.: Overview of the face recognition grand challenge. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., et al.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.533"},{"key":"12_CR45","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)"},{"key":"12_CR46","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1145\/3130800.3130883","volume":"36","author":"J Romero","year":"2017","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (ToG) 36, 245 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Ronchi, M.R., Perona, P.: Benchmarking and error diagnosis in multi-instance pose estimation. In: Proceedings of International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.48"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: IEEE International Conference on Computer Vision Workshop (2013)","DOI":"10.1109\/ICCVW.2013.59"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Sharp, T., et al.: Accurate, robust, and flexible real-time hand tracking. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (2015)","DOI":"10.1145\/2702123.2702179"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.494"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Sridhar, S., Mueller, F., Oulasvirta, A., Theobalt, C.: Fast and robust hand tracking using detection-guided optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298941"},{"key":"12_CR52","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. arXiv preprint arXiv:1902.09212 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"12_CR53","unstructured":"Sun, K., et al.: High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514 (2019)"},{"key":"12_CR54","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)","DOI":"10.1109\/CVPR.2013.446"},{"key":"12_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2629500","volume":"33","author":"J Tompson","year":"2014","unstructured":"Tompson, J., Stein, M., Lecun, Y., Perlin, K.: Real-time continuous pose recovery of human hands using convolutional networks. ACM Trans. Graph. (ToG) 33, 1\u201310 (2014)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., Snape, P., Nicolaou, M.A., Antonakos, E., Zafeiriou, S.: Mnemonic descent method: a recurrent process applied for end-to-end face alignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.453"},{"key":"12_CR57","doi-asserted-by":"crossref","unstructured":"Tzimiropoulos, G.: Project-out cascaded regression with an application to face alignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298989"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Valle, R., Buenaposada, J.M., Valdes, A., Baumela, L.: A deeply-initialized coarse-to-fine ensemble of regression trees for face alignment. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01264-9_36"},{"key":"12_CR59","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":"12_CR60","unstructured":"Wu, J., et al.: Ai challenger: a large-scale dataset for going deeper in image understanding. arXiv preprint arXiv:1711.06475 (2017)"},{"key":"12_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00227"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: posing face, body, and hands in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01122"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)","DOI":"10.1109\/CVPR.2013.75"},{"key":"12_CR65","doi-asserted-by":"crossref","unstructured":"Yuan, S., Ye, Q., Stenger, B., Jain, S., Kim, T.K.: BigHand2. 2m benchmark: hand pose dataset and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.279"},{"key":"12_CR66","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1109\/TPAMI.2015.2469286","volume":"38","author":"Z Zhang","year":"2015","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Learning deep representation for face alignment with auxiliary attributes. IEEE Trans. Pattern Anal. Mach. Intell. 38, 918\u2013930 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR67","unstructured":"Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2012)"},{"key":"12_CR68","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. arXiv preprint arXiv: 1705.01389 (2017)","DOI":"10.1109\/ICCV.2017.525"},{"key":"12_CR69","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: Proceedings of International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58545-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T01:08:00Z","timestamp":1730682480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58545-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585440","9783030585457"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58545-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"5 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}