{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:52:58Z","timestamp":1780923178344,"version":"3.54.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915741","type":"print"},{"value":"9783031915758","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-91575-8_12","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T17:57:29Z","timestamp":1748195849000},"page":"189-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Depth-Based Privileged Information for\u00a0Boosting 3D Human Pose Estimation on\u00a0RGB"],"prefix":"10.1007","author":[{"given":"Alessandro","family":"Simoni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Marchetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guido","family":"Borghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Becattini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Davoli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Garattoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianpiero","family":"Francesca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Seidenari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Vezzani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Alehdaghi, M., Josi, A., Cruz, R.M., Granger, E.: Visible-infrared person re-identification using privileged intermediate information. In: European Conference on Computer Vision, pp. 720\u2013737. Springer (2022)","DOI":"10.1007\/978-3-031-25072-9_48"},{"key":"12_CR2","unstructured":"Borghi, G., Pini, S., Grazioli, F., Vezzani, R., Cucchiara, R., et\u00a0al.: Face verification from depth using privileged information. In: Proceedings of the British Machine Vision Conference, p.\u00a0303 (2018)"},{"issue":"15","key":"12_CR3","doi-asserted-by":"publisher","first-page":"3361","DOI":"10.3390\/s19153361","volume":"19","author":"G Borghi","year":"2019","unstructured":"Borghi, G., Pini, S., Vezzani, R., Cucchiara, R.: Driver face verification with depth maps. Sensors 19(15), 3361 (2019)","journal-title":"Sensors"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C.H., Ramanan, D.: 3D human pose estimation= 2D pose estimation+ matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7035\u20137043 (2017)","DOI":"10.1109\/CVPR.2017.610"},{"key":"12_CR5","unstructured":"Chen, D., Zhou, B., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning by cheating. In: Conference on Robot Learning, pp. 66\u201375. PMLR (2020)"},{"key":"12_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Sharma, A., Jain, A.: Learning 3D human pose from structure and motion. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 668\u2013683 (2018)","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Fabbri, M., Lanzi, F., Calderara, S., Alletto, S., Cucchiara, R.: Compressed volumetric heatmaps for multi-person 3D pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7204\u20137213 (2020)","DOI":"10.1109\/CVPR42600.2020.00723"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hoffman, J., Gupta, S., Darrell, T.: Learning with side information through modality hallucination. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 826\u2013834 (2016)","DOI":"10.1109\/CVPR.2016.96"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Hossain, M.R.I., Little, J.J.: Exploiting temporal information for 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 68\u201384 (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"12_CR12","unstructured":"Kim, D., Ka, W., Ahn, P., Joo, D., Chun, S., Kim, J.: Global-local path networks for monocular depth estimation with vertical CutDepth. arXiv preprint arXiv:2201.07436 (2022)"},{"key":"12_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Lee, K., Lee, I., Lee, S.: Propagating LSTM: 3D pose estimation based on joint interdependency. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 119\u2013135 (2018)","DOI":"10.1007\/978-3-030-01234-2_8"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Lee, S., et al.: Human pose estimation in extremely low-light conditions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 704\u2013714 (2023)","DOI":"10.1109\/CVPR52729.2023.00075"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Lin, H.Y., Chen, T.W.: Augmented reality with human body interaction based on monocular 3D pose estimation. In: International Conference on Advanced Concepts for Intelligent Vision Systems, pp. 321\u2013331. Springer (2010)","DOI":"10.1007\/978-3-642-17688-3_31"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Luvizon, D.C., Picard, D., Tabia, H.: 2D\/3D pose estimation and action recognition using multitask deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5137\u20135146 (2018)","DOI":"10.1109\/CVPR.2018.00539"},{"key":"12_CR18","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"issue":"9","key":"12_CR19","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1002\/esp.3332","volume":"38","author":"KD Mankoff","year":"2013","unstructured":"Mankoff, K.D., Russo, T.A.: The kinect: a low-cost, high-resolution, short-range 3D camera. Earth Surf. Proc. Land. 38(9), 926\u2013936 (2013)","journal-title":"Earth Surf. Proc. Land."},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506\u2013516. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"issue":"4","key":"12_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. (tog) 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph. (tog)"},{"issue":"1","key":"12_CR23","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Moreno-Noguer, F.: 3D human pose estimation from a single image via distance matrix regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2823\u20132832 (2017)","DOI":"10.1109\/CVPR.2017.170"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Nibali, A., He, Z., Morgan, S., Prendergast, L.: 3D human pose estimation with 2D marginal heatmaps. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1477\u20131485. IEEE (2019)","DOI":"10.1109\/WACV.2019.00162"},{"key":"12_CR26","unstructured":"Oquab, M., et al.: DINOv2: Learning robust visual features without supervision (2023)"},{"key":"12_CR27","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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468 (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Pini, S., Borghi, G., Vezzani, R., Cucchiara, R.: Video synthesis from intensity and event frames. In: Image Analysis and Processing\u2013ICIAP 2019: 20th International Conference, Trento, Italy, September 9\u201313, 2019, Proceedings, Part I 20, pp. 313\u2013323. Springer (2019)","DOI":"10.1007\/978-3-030-30642-7_28"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"12_CR31","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR32","unstructured":"S\u00e1r\u00e1ndi, I., Linder, T., Arras, K.O., Leibe, B.: Synthetic occlusion augmentation with volumetric heatmaps for the 2018 ECCV PoseTrack challenge on 3D human pose estimation. arXiv preprint arXiv:1809.04987 (2018)"},{"key":"12_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2015.05.006","volume":"139","author":"H Sarbolandi","year":"2015","unstructured":"Sarbolandi, H., Lefloch, D., Kolb, A.: Kinect range sensing: structured-light versus time-of-flight kinect. Comput. Vis. Image Underst. 139, 1\u201320 (2015)","journal-title":"Comput. Vis. Image Underst."},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Sharmanska, V., Quadrianto, N., Lampert, C.H.: Learning to rank using privileged information. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 825\u2013832 (2013)","DOI":"10.1109\/ICCV.2013.107"},{"issue":"4","key":"12_CR35","doi-asserted-by":"publisher","first-page":"11569","DOI":"10.1109\/LRA.2022.3193225","volume":"7","author":"A Simoni","year":"2022","unstructured":"Simoni, A., Pini, S., Borghi, G., Vezzani, R.: Semi-perspective decoupled heatmaps for 3D robot pose estimation from depth maps. IEEE Robot. Autom. Lett. 7(4), 11569\u201311576 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"12_CR37","unstructured":"Sun, K., et al.: High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514 (2019)"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 529\u2013545 (2018)","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Tekin, B., M\u00e1rquez-Neila, P., Salzmann, M., Fua, P.: Learning to fuse 2D and 3D image cues for monocular body pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3941\u20133950 (2017)","DOI":"10.1109\/ICCV.2017.425"},{"key":"12_CR40","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"},{"issue":"5\u20136","key":"12_CR41","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","volume":"22","author":"V Vapnik","year":"2009","unstructured":"Vapnik, V., Vashist, A.: A new learning paradigm: learning using privileged information. Neural Netw. 22(5\u20136), 544\u2013557 (2009)","journal-title":"Neural Netw."},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Vapnik, V., Vashist, A., Pavlovitch, N.: Learning using hidden information (learning with teacher). In: Proceedings of the International Joint Conference on Neural Networks, pp. 3188\u20133195. IEEE (2009)","DOI":"10.1109\/IJCNN.2009.5178760"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Wu, H., Wu, X., Huang, K., Ma, H.: Human pose recognition based on openpose and application in safety detection of intelligent factory (2021)","DOI":"10.1049\/icp.2021.1294"},{"key":"12_CR44","unstructured":"Xing, E., Jordan, M., Russell, S.J., Ng, A.: Distance metric learning with application to clustering with side-information. Adv. Neural Inf. Process. Syst. 15 (2002)"},{"issue":"12","key":"12_CR45","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1109\/TNNLS.2015.2405574","volume":"26","author":"X Xu","year":"2015","unstructured":"Xu, X., Li, W., Xu, D.: Distance metric learning using privileged information for face verification and person re-identification. IEEE Trans. Neural Netw. Learn. Syst. 26(12), 3150\u20133162 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X.: 3D human pose estimation in the wild by adversarial learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5255\u20135264 (2018)","DOI":"10.1109\/CVPR.2018.00551"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, S., Stenger, B., Kim, T.K.: 3D hand pose estimation from RGB using privileged learning with depth data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00348"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Welschehold, T., Dornhege, C., Burgard, W., Brox, T.: 3D human pose estimation in RGBD images for robotic task learning. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1986\u20131992. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8462833"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91575-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:02:36Z","timestamp":1748196156000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91575-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915741","9783031915758"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91575-8_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}