{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:31:03Z","timestamp":1760956263968,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319781983"},{"type":"electronic","value":"9783319781990"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-78199-0_3","type":"book-chapter","created":{"date-parts":[[2018,3,21]],"date-time":"2018-03-21T00:13:52Z","timestamp":1521591232000},"page":"34-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Structured Output Prediction and Learning for Deep Monocular 3D Human Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9356-5948","authenticated-orcid":false,"given":"Stefan","family":"Kinauer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5149-5195","authenticated-orcid":false,"given":"Riza Alp","family":"G\u00fcler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhartha","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iasonas","family":"Kokkinos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,3,22]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P.V., Schiele, B.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4929\u20134937 (2016)","DOI":"10.1109\/CVPR.2016.533"},{"key":"3_CR3","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":"3_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. arXiv preprint arXiv:1611.08050 (2016)","DOI":"10.1109\/CVPR.2017.143"},{"key":"3_CR5","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":"3_CR6","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732 (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"3_CR7","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":"3_CR8","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito, L.: Lifting from the deep: convolutional 3D pose estimation from a single image. arXiv preprint arXiv:1701.00295 (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Chen, C.H., Ramanan, D.: 3D human pose estimation = 2D pose estimation + matching. arXiv preprint arXiv:1612.06524 (2016)","DOI":"10.1109\/CVPR.2017.610"},{"key":"3_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., Sotnychenko, O., Xu, W., Theobalt, C.: Monocular 3D human pose estimation in the wild using improved CNN supervision. arXiv preprint arXiv:1611.09813v3 (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"3_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-319-48881-3_29","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"A Guler","year":"2016","unstructured":"Guler, A., et al.: Human joint angle estimation and gesture recognition for assistive robotic vision. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 415\u2013431. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_29"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3D human pose. arXiv preprint arXiv:1611.07828 (2016)","DOI":"10.1109\/CVPR.2017.139"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Burenius, M., Sullivan, J., Carlsson, S.: 3D pictorial structures for multiple view articulated pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3618\u20133625 (2013)","DOI":"10.1109\/CVPR.2013.464"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Tekin, B., M\u00e1rquez-Neila, P., Salzmann, M., Fua, P.: Fusing 2D uncertainty and 3D cues for monocular body pose estimation. arXiv preprint arXiv:1611.05708 (2016)","DOI":"10.1109\/ICCV.2017.425"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Tekin, B., Katircioglu, I., Salzmann, M., Lepetit, V., Fua, P.: Structured prediction of 3D human pose with deep neural networks. CoRR abs\/1605.05180 (2016)","DOI":"10.5244\/C.30.130"},{"key":"3_CR17","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: NIPS (2014)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Li, H., Wang, X.: End-to-end learning of deformable mixture of parts and deep convolutional neural networks for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3073\u20133082 (2016)","DOI":"10.1109\/CVPR.2016.335"},{"key":"3_CR19","unstructured":"Lee, C., Xie, S., Gallagher, P.W., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: AISTATS (2015)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"3_CR21","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, pp. 91\u201399 (2015)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Guler, R.A., Trigeorgis, G., Antonakos, E., Snape, P., Zafeiriou, S., Kokkinos, I.: DenseReg: fully convolutional dense shape regression in-the-wild. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.280"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., Murphy, K.P.: Towards accurate multi-person pose estimation in the wild. CoRR abs\/1701.01779 (2017)","DOI":"10.1109\/CVPR.2017.395"},{"issue":"1","key":"3_CR24","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. Int. J. Comput. Vis. 61(1), 55\u201379 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR25","unstructured":"Chen, X., Yuille, A.L.: Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in Neural Information Processing Systems, pp. 1736\u20131744 (2014)"},{"key":"3_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/978-3-642-15552-9_30","volume-title":"Computer Vision \u2013 ECCV 2010","author":"B Sapp","year":"2010","unstructured":"Sapp, B., Toshev, A., Taskar, B.: Cascaded models for articulated pose estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 406\u2013420. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15552-9_30"},{"key":"3_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/978-3-319-49409-8_24","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"S Kinauer","year":"2016","unstructured":"Kinauer, S., Berman, M., Kokkinos, I.: Monocular surface reconstruction using 3D deformable part models. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 296\u2013308. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_24"},{"issue":"1","key":"3_CR28","first-page":"1","volume":"3","author":"S Boyd","year":"2011","unstructured":"Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends\u00ae Mach. Learn. 3(1), 1\u2013122 (2011)","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"3_CR29","unstructured":"Martins, A.F., Smith, N.A., Aguiar, P.M., Figueiredo, M.A.: Dual decomposition with many overlapping components. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 238\u2013249. Association for Computational Linguistics (2011)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Boussaid, H., Kokkinos, I.: Fast and exact: ADMM-based discriminative shape segmentation with loopy part models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4058\u20134065 (2014)","DOI":"10.1109\/CVPR.2014.517"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Komodakis, N., Paragios, N., Tziritas, G.: MRF optimization via dual decomposition: message-passing revisited. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4408890"},{"issue":"1","key":"3_CR32","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10994-009-5108-8","volume":"77","author":"T Joachims","year":"2009","unstructured":"Joachims, T., Finley, T., Yu, C.N.J.: Cutting-plane training of structural SVMs. Mach. Learn. 77(1), 27\u201359 (2009)","journal-title":"Mach. Learn."},{"issue":"11","key":"3_CR33","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1109\/TPAMI.2015.2408347","volume":"37","author":"B Pepik","year":"2015","unstructured":"Pepik, B., Stark, M., Gehler, P.V., Schiele, B.: Multi-view and 3D deformable part models. IEEE Trans. Pattern Anal. Mach. Intell. 37(11), 2232\u20132245 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sohn, K., Villegas, R., Pan, G., Lee, H.: Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction, pp. 249\u2013258 (2015)","DOI":"10.1109\/CVPR.2015.7298621"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. arXiv preprint arXiv:1704.00159 (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Yasin, H., Iqbal, U., Kruger, B., Weber, A., Gall, J.: A dual-source approach for 3D pose estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4948\u20134956 (2016)","DOI":"10.1109\/CVPR.2016.535"},{"key":"3_CR37","unstructured":"Rogez, G., Schmid, C.: MoCap-guided data augmentation for 3D pose estimation in the wild. In: Advances in Neural Information Processing Systems, pp. 3108\u20133116 (2016)"}],"container-title":["Lecture Notes in Computer Science","Energy Minimization Methods in Computer Vision and Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78199-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,13]],"date-time":"2019-10-13T01:54:00Z","timestamp":1570931640000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78199-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319781983","9783319781990"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78199-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}