{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:43:02Z","timestamp":1778082182303,"version":"3.51.4"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T00:00:00Z","timestamp":1637020800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T00:00:00Z","timestamp":1637020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002790","name":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["PGSD3-532647-2019"],"award-info":[{"award-number":["PGSD3-532647-2019"]}],"id":[{"id":"10.13039\/501100002790","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s11263-021-01529-w","type":"journal-article","created":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T05:02:27Z","timestamp":1637038947000},"page":"111-135","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose"],"prefix":"10.1007","volume":"130","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0749-064X","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0906-6589","authenticated-orcid":false,"given":"Jennifer J.","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8921-8564","authenticated-orcid":false,"given":"Long","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaping","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9206-1908","authenticated-orcid":false,"given":"Liangzhe","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0570-8967","authenticated-orcid":false,"given":"Florian","family":"Schroff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hartwig","family":"Adam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,16]]},"reference":[{"key":"1529_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., & Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. https:\/\/www.tensorflow.org\/. Software available from tensorflow.org"},{"key":"1529_CR2","doi-asserted-by":"crossref","unstructured":"Akhter, I., & Black, M. J. (2015). Pose-conditioned joint angle limits for 3D human pose reconstruction. In CVPR.","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"1529_CR3","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., & Schiele, B. (2014). 2D human pose estimation: New benchmark and state of the art analysis. In CVPR.","DOI":"10.1109\/CVPR.2014.471"},{"key":"1529_CR4","unstructured":"Bojchevski, A., & G\u00fcnnemann, S. (2018). Deep Gaussian embedding of graphs: Unsupervised inductive learning via ranking. In ICLR."},{"key":"1529_CR5","doi-asserted-by":"crossref","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., & Shah, R. (1994) . Signature verification using a \u201csiamese\u201d time delay neural network. In NeurIPS.","DOI":"10.1142\/9789812797926_0003"},{"issue":"3","key":"1529_CR6","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1109\/TCYB.2017.2756840","volume":"48","author":"C Cao","year":"2017","unstructured":"Cao, C., Zhang, Y., Zhang, C., & Lu, H. (2017). Body joint guided 3-D deep convolutional descriptors for action recognition. IEEE Transactions on Cybernetics, 48(3), 1095\u20131108.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"1529_CR7","doi-asserted-by":"crossref","unstructured":"Chen, C. H., & Ramanan, D. (2017). 3D human pose estimation = 2D pose estimation + matching. In CVPR.","DOI":"10.1109\/CVPR.2017.610"},{"key":"1529_CR8","doi-asserted-by":"crossref","unstructured":"Chen, C. H., Tyagi, A., Agrawal, A., Drover, D., Stojanov, S., & Rehg, J. M. (2019). Unsupervised 3D pose estimation with geometric self-supervision. In CVPR.","DOI":"10.1109\/CVPR.2019.00586"},{"key":"1529_CR9","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In ICML."},{"key":"1529_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., & Sun, J. (2018). Cascaded pyramid network for multi-person pose estimation. In CVPR.","DOI":"10.1109\/CVPR.2018.00742"},{"key":"1529_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., & Tan, R. T. (2020). 3D human pose estimation using spatio-temporal networks with explicit occlusion training. In AAAI.","DOI":"10.1609\/aaai.v34i07.6689"},{"key":"1529_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., Yan, W., & Tan, R. T. (2019). Occlusion-aware networks for 3D human pose estimation in video. In ICCV.","DOI":"10.1109\/ICCV.2019.00081"},{"key":"1529_CR13","doi-asserted-by":"crossref","unstructured":"Chu, R., Sun, Y., Li, Y., Liu, Z., Zhang, C., & Wei, Y. (2019). Vehicle re-identification with viewpoint-aware metric learning. In ICCV.","DOI":"10.1109\/ICCV.2019.00837"},{"key":"1529_CR14","doi-asserted-by":"crossref","unstructured":"Du, W., Wang, Y., & Qiao, Y. (2017). RPAN: An end-to-end recurrent pose-attention network for action recognition in videos. In ICCV.","DOI":"10.1109\/ICCV.2017.402"},{"issue":"Jul","key":"1529_CR15","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul), 2121\u20132159.","journal-title":"Journal of Machine Learning Research"},{"key":"1529_CR16","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., & Zisserman, A. (2019). Temporal cycle-consistency learning. In CVPR.","DOI":"10.1109\/CVPR.2019.00190"},{"issue":"22","key":"1529_CR17","doi-asserted-by":"publisher","first-page":"4943","DOI":"10.3390\/s19224943","volume":"19","author":"M Garcia-Salguero","year":"2019","unstructured":"Garcia-Salguero, M., Gonzalez-Jimenez, J., & Moreno, F. A. (2019). Human 3D pose estimation with a tilting camera for social mobile robot interaction. Sensors, 19(22), 4943.","journal-title":"Sensors"},{"key":"1529_CR18","doi-asserted-by":"crossref","unstructured":"Gu, R., Wang, G., & Hwang, J. N. (2019). Efficient multi-person hierarchical 3D pose estimation for autonomous driving. In MIPR.","DOI":"10.1109\/MIPR.2019.00036"},{"key":"1529_CR19","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., & LeCun, Y. (2006). Dimensionality reduction by learning an invariant mapping. In CVPR.","DOI":"10.1109\/CVPR.2006.100"},{"key":"1529_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. In CVPR.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1529_CR21","doi-asserted-by":"crossref","unstructured":"He, X., Zhou, Y., Zhou, Z., Bai, S., & Bai, X. (2018). Triplet-center loss for multi-view 3D object retrieval. In CVPR.","DOI":"10.1109\/CVPR.2018.00208"},{"key":"1529_CR22","unstructured":"Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737."},{"key":"1529_CR23","doi-asserted-by":"crossref","unstructured":"Ho, C. H., Morgado, P., Persekian, A., Vasconcelos, N. (2019). PIEs: Pose invariant embeddings. In CVPR.","DOI":"10.1109\/CVPR.2019.01266"},{"key":"1529_CR24","doi-asserted-by":"crossref","unstructured":"Hu, W., & Zhu, S. C. (2010). Learning a probabilistic model mixing 3D and 2D primitives for view invariant object recognition. In CVPR.","DOI":"10.1109\/CVPR.2010.5539910"},{"key":"1529_CR25","unstructured":"Huang, C., Loy, C. C., & Tang, X. (2016). Local similarity-aware deep feature embedding. In NeurIPS."},{"issue":"7","key":"1529_CR26","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2013). Human3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(7), 1325\u20131339.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1529_CR27","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Garbade, M., & Gall, J. (2017). Pose for action-action for pose. In FG.","DOI":"10.1109\/FG.2017.61"},{"key":"1529_CR28","doi-asserted-by":"crossref","unstructured":"Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2018). Mining on manifolds: Metric learning without labels. In CVPR.","DOI":"10.1109\/CVPR.2018.00797"},{"key":"1529_CR29","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., & Malkov, Y. (2019). Learnable triangulation of human pose. In ICCV.","DOI":"10.1109\/ICCV.2019.00781"},{"key":"1529_CR30","doi-asserted-by":"crossref","unstructured":"Jammalamadaka, N., Zisserman, A., Eichner, M., Ferrari, V., & Jawahar, C. (2012). Video retrieval by mimicking poses. In ACM MM.","DOI":"10.1145\/2324796.2324838"},{"issue":"1","key":"1529_CR31","first-page":"13","volume":"40","author":"X Ji","year":"2009","unstructured":"Ji, X., & Liu, H. (2009). Advances in view-invariant human motion analysis: A review. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 40(1), 13\u201324.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"},{"key":"1529_CR32","doi-asserted-by":"crossref","unstructured":"Ji, X., Liu, H., Li, Y., & Brown, D. (2008). Visual-based view-invariant human motion analysis: A review. In KES.","DOI":"10.1007\/978-3-540-85563-7_93"},{"key":"1529_CR33","unstructured":"Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? In NeurIPS."},{"issue":"1\/2","key":"1529_CR34","doi-asserted-by":"publisher","first-page":"81","DOI":"10.2307\/2332226","volume":"30","author":"MG Kendall","year":"1938","unstructured":"Kendall, M. G. (1938). A new measure of rank correlation. Biometrika, 30(1\/2), 81\u201393.","journal-title":"Biometrika"},{"key":"1529_CR35","unstructured":"Kingma, D. P., & Welling, M. (2014). Auto-encoding variational Bayes. In ICLR."},{"key":"1529_CR36","unstructured":"Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In ICLR."},{"key":"1529_CR37","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagoz, S., & Akbas, E. (2019). Self-supervised learning of 3D human pose using multi-view geometry. In CVPR.","DOI":"10.1109\/CVPR.2019.00117"},{"key":"1529_CR38","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Huang, F. J., & Bottou, L., et\u00a0al. (2004). Learning methods for generic object recognition with invariance to pose and lighting. In CVPR.","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"1529_CR39","unstructured":"Li, J., Wong, Y., Zhao, Q., & Kankanhalli, M. (2018). Unsupervised learning of view-invariant action representations. In NeurIPS."},{"key":"1529_CR40","doi-asserted-by":"crossref","unstructured":"Li, S., Ke, L., Pratama, K., Tai, Y. W., Tang, C. K., & Cheng, K. T. (2020). Cascaded deep monocular 3D human pose estimation with evolutionary training data. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00621"},{"key":"1529_CR41","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1529_CR42","doi-asserted-by":"publisher","first-page":"70061","DOI":"10.1109\/ACCESS.2018.2880231","volume":"6","author":"J Liu","year":"2018","unstructured":"Liu, J., Akhtar, N., & Ajmal, M. (2018). Viewpoint invariant action recognition using RGB-D videos. IEEE Access, 6, 70061\u201370071.","journal-title":"IEEE Access"},{"key":"1529_CR43","doi-asserted-by":"crossref","unstructured":"Liu, M., Yuan, J. (2018). Recognizing human actions as the evolution of pose estimation maps. In CVPR.","DOI":"10.1109\/CVPR.2018.00127"},{"key":"1529_CR44","doi-asserted-by":"crossref","unstructured":"Luvizon, D. C., Tabia, H., & Picard, D. (2020). Multi-task deep learning for real-time 3D human pose estimation and action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2020.2976014"},{"key":"1529_CR45","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., & Pons-Moll, G. (2018). Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In ECCV.","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"1529_CR46","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J. (2017). A simple yet effective baseline for 3D human pose estimation. In ICCV.","DOI":"10.1109\/ICCV.2017.288"},{"key":"1529_CR47","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., & Theobalt, C. (2017). Monocular 3D human pose estimation in the wild using improved CNN supervision. In 3DV.","DOI":"10.1109\/3DV.2017.00064"},{"key":"1529_CR48","doi-asserted-by":"crossref","unstructured":"Misra, I., Zitnick, C. L., & Hebert, M. (2016). Shuffle and learn: Unsupervised learning using temporal order verification. In ECCV.","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"1529_CR49","unstructured":"Mori, G., Pantofaru, C., Kothari, N., Leung, T., Toderici, G., Toshev, A., Yang, W. (2015). Pose embeddings: A deep architecture for learning to match human poses. arXiv preprint arXiv:1507.00302"},{"key":"1529_CR50","doi-asserted-by":"crossref","unstructured":"Nie, B. X., Xiong, C., & Zhu, S. C. (2015). Joint action recognition and pose estimation from video. In CVPR.","DOI":"10.1109\/CVPR.2015.7298734"},{"key":"1529_CR51","unstructured":"Oh, S.J., Murphy, K., Pan, J., Roth, J., Schroff, F., & Gallagher, A. (2019). Modeling uncertainty with hedged instance embedding. In ICLR."},{"key":"1529_CR52","doi-asserted-by":"crossref","unstructured":"Oh Song, H., Xiang, Y., Jegelka, S., & Savarese, S. (2016). Deep metric learning via lifted structured feature embedding. In CVPR.","DOI":"10.1109\/CVPR.2016.434"},{"issue":"2\u20133","key":"1529_CR53","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.cviu.2006.08.004","volume":"104","author":"EJ Ong","year":"2006","unstructured":"Ong, E. J., Micilotta, A. S., Bowden, R., & Hilton, A. (2006). Viewpoint invariant exemplar-based 3D human tracking. Computer Vision and Image Understanding, 104(2\u20133), 178\u2013189.","journal-title":"Computer Vision and Image Understanding"},{"key":"1529_CR54","unstructured":"Oord, A. V. D., Li, Y., Vinyals, O. (2018). Representation learning with contrastive predictive coding. In NeurIPS."},{"key":"1529_CR55","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Chen, L. C., Gidaris, S., Tompson, J., Murphy, K. (2018). PersonLab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In ECCV.","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"1529_CR56","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., & Murphy, K. (2017). Towards accurate multi-person pose estimation in the wild. In CVPR.","DOI":"10.1109\/CVPR.2017.395"},{"key":"1529_CR57","doi-asserted-by":"crossref","unstructured":"Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015). Deep face recognition. In BMVC.","DOI":"10.5244\/C.29.41"},{"key":"1529_CR58","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., & Auli, M. (2019). 3D human pose estimation in video with temporal convolutions and semi-supervised training. In CVPR.","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1529_CR59","doi-asserted-by":"crossref","unstructured":"Qiu, H., Wang, C., Wang, J., Wang, N., & Zeng, W. (2019). Cross view fusion for 3D human pose estimation. In ICCV.","DOI":"10.1109\/ICCV.2019.00444"},{"key":"1529_CR60","doi-asserted-by":"crossref","unstructured":"Rao, C., & Shah, M. (2001). View-invariance in action recognition. In CVPR.","DOI":"10.1109\/CVPR.2001.990977"},{"key":"1529_CR61","unstructured":"Rayat I. H. M., & Little, J. J. (2018). Exploiting temporal information for 3D human pose estimation. In ECCV."},{"key":"1529_CR62","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Salzmann, M., & Fua, P. (2018). Unsupervised geometry-aware representation for 3D human pose estimation. In ECCV.","DOI":"10.1007\/978-3-030-01249-6_46"},{"key":"1529_CR63","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Sp\u00f6rri, J., Katircioglu, I., Constantin, V., Meyer, F., M\u00fcller, E., Salzmann, M., & Fua, P. (2018). Learning monocular 3D human pose estimation from multi-view images. In CVPR.","DOI":"10.1109\/CVPR.2018.00880"},{"key":"1529_CR64","doi-asserted-by":"crossref","unstructured":"Ronchi, M. R., Kim, J. S., & Yue, Y. (2016). A rotation invariant latent factor model for moveme discovery from static poses. In ICDM.","DOI":"10.1109\/ICDM.2016.0156"},{"key":"1529_CR65","unstructured":"S\u00e1r\u00e1ndi, I., Linder, T., Arras, K. O., & Leibe, B. (2018). Synthetic occlusion augmentation with volumetric heatmaps for the 2018 ECCV PoseTrack Challenge on 3D human pose estimation. arXiv preprint arXiv:1809.04987"},{"key":"1529_CR66","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. In CVPR.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"1529_CR67","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Lynch, C., Chebotar, Y., Hsu, J., Jang, E., Schaal, S., Levine, S., & Brain, G. (2018). Time-contrastive networks: Self-supervised learning from video. In ICRA.","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"1529_CR68","doi-asserted-by":"crossref","unstructured":"Sun, J. J., Zhao, J., Chen, L. C., Schroff, F., Adam, H., & Liu, T. (2020). View-invariant probabilistic embedding for human pose. In ECCV.","DOI":"10.1007\/978-3-030-58558-7_4"},{"key":"1529_CR69","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., & Wei, Y. (2018). Integral human pose regression. In ECCV.","DOI":"10.1109\/ICCV.2017.284"},{"key":"1529_CR70","doi-asserted-by":"crossref","unstructured":"Tekin, B., M\u00e1rquez-Neila, P., Salzmann, M., Fua, P. (2017). Learning to fuse 2D and 3D image cues for monocular body pose estimation. In ICCV.","DOI":"10.1109\/ICCV.2017.425"},{"key":"1529_CR71","doi-asserted-by":"crossref","unstructured":"Tome, D., Toso, M., Agapito, L., & Russell, C. (2018). Rethinking pose in 3D: Multi-stage refinement and recovery for markerless motion capture. In 3DV.","DOI":"10.1109\/3DV.2018.00061"},{"key":"1529_CR72","unstructured":"Vilnis, L., & McCallum, A. (2015). Word representations via Gaussian embedding. In ICLR."},{"key":"1529_CR73","doi-asserted-by":"crossref","unstructured":"Wang, J., Song, Y., Leung, T., Rosenberg, C., Wang, J., Philbin, J., Chen, B., & Wu, Y. (2014). Learning fine-grained image similarity with deep ranking. In CVPR.","DOI":"10.1109\/CVPR.2014.180"},{"key":"1529_CR74","doi-asserted-by":"crossref","unstructured":"Wohlhart, P., & Lepetit, V. (2015). Learning descriptors for object recognition and 3D pose estimation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"1529_CR75","doi-asserted-by":"crossref","unstructured":"Wu, C. Y., Manmatha, R., Smola, A. J., & Krahenbuhl, P. (2017). Sampling matters in deep embedding learning. In ICCV.","DOI":"10.1109\/ICCV.2017.309"},{"key":"1529_CR76","doi-asserted-by":"crossref","unstructured":"Xia, L., Chen, C. C., & Aggarwal, J. K. (2012). View invariant human action recognition using histograms of 3D joints. In CVPRW.","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"1529_CR77","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Huang, F., Liu, M., Xu, Q., & Lin, S. (2020). SRNet: Improving generalization in 3D human pose estimation with a split-and-recombine approach. In ECCV.","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"1529_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhu, M., & Derpanis, K. G. (2013). From actemes to action: A strongly-supervised representation for detailed action understanding. In ICCV.","DOI":"10.1109\/ICCV.2013.280"},{"key":"1529_CR79","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., & Metaxas, D. N. (2019). Semantic graph convolutional networks for 3D human pose regression. In CVPR.","DOI":"10.1109\/CVPR.2019.00354"},{"key":"1529_CR80","doi-asserted-by":"publisher","first-page":"4500","DOI":"10.1109\/TIP.2019.2910414","volume":"28","author":"L Zheng","year":"2019","unstructured":"Zheng, L., Huang, Y., Lu, H., & Yang, Y. (2019). Pose invariant embedding for deep person re-identification. IEEE Transactions on Image Processing, 28, 4500\u20134509.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1529_CR81","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y. (2017). Towards 3D human pose estimation in the wild: A weakly-supervised approach. In ICCV.","DOI":"10.1109\/ICCV.2017.51"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01529-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01529-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01529-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:04:19Z","timestamp":1641499459000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01529-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,16]]},"references-count":81,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["1529"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01529-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,16]]},"assertion":[{"value":"15 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}