{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:07:04Z","timestamp":1788937624907,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375940","type":"print"},{"value":"9783032375957","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37595-7_8","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:35:07Z","timestamp":1788935707000},"page":"134-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DETRAM: End-to-End DEtection, Tracking and\u00a0Recovery of\u00a0HumAn Meshes"],"prefix":"10.1007","author":[{"given":"Chunggi","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seonwook","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanhua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umar","family":"Iqbal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanspeter","family":"Pfister","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Iqbal, U., Insafutdinov, E., Pishchulin, L., Milan, A., Gall, J., Schiele, B.: Posetrack: a benchmark for human pose estimation and tracking. In: CVPR, pp. 5167\u20135176 (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Baradel, F., et al.: Multi-HMR: multi-person whole-body human mesh recovery in a single shot. In: ECCV, pp. 202\u2013218. Springer (2024)","DOI":"10.1007\/978-3-031-73337-6_12"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: ICCV, pp. 941\u2013951 (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Black, M.J., Patel, P., Tesch, J., Yang, J.: BEDLAM: a synthetic dataset of bodies exhibiting detailed lifelike animated motion. In: CVPR, pp. 8726\u20138737 (2023)","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., et al.: Smpler-x: Scaling up expressive human pose and shape estimation. NeurIPS 36, 11454\u201311468 (2023)","DOI":"10.52202\/075280-0506"},{"key":"8_CR6","unstructured":"Carion, N., et\u00a0al.: Sam 3: Segment anything with concepts. arXiv preprint arXiv:2511.16719 (2025)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Schwing, A.G.: XMem: long-term video object segmentation with an atkinson-shiffrin memory model. In: ECCV, pp. 640\u2013658. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"8_CR10","first-page":"11781","volume":"34","author":"HK Cheng","year":"2021","unstructured":"Cheng, H.K., Tai, Y.W., Tang, C.K.: Rethinking space-time networks with improved memory coverage for efficient video object segmentation. NeurIPS 34, 11781\u201311794 (2021)","journal-title":"NeurIPS"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M.J.: Monocular expressive body regression through body-driven attention, ECCV (2020)","DOI":"10.1007\/978-3-030-58607-2_2"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Doering, A., Chen, D., Zhang, S., Schiele, B., Gall, J.: PoseTrack21: a dataset for person search, multi-object tracking and multi-person pose tracking. In: CVPR, pp. 20963\u201320972 (2022)","DOI":"10.1109\/CVPR52688.2022.02029"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., Malik, J.: Humans in 4D: reconstructing and tracking humans with transformers. In: ICCV, pp. 14783\u201314794 (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Milan, A., Gall, J.: PoseTrack: joint multi-person pose estimation and tracking. In: CVPR (2017). http:\/\/arxiv.org\/abs\/1611.07727","DOI":"10.1109\/CVPR.2017.495"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, W., Kolotouros, N., Pavlakos, G., Zhou, X., Daniilidis, K.: Coherent reconstruction of multiple humans from a single image. In: CVPR, pp. 5579\u20135588 (2020)","DOI":"10.1109\/CVPR42600.2020.00562"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3D human dynamics from video, CVPR (2019)","DOI":"10.1109\/CVPR.2019.00576"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: Pare: Part attention regressor for 3D human body estimation. In: ICCV, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00463"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: Accelerate DETR training by introducing query denoising. In: CVPR, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: Hybrik: a hybrid analytical-neural inverse kinematics solution for 3D human pose and shape estimation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: CVPR, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: Common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Liu, K., et al.: Motions as queries: one-stage multi-person holistic human motion capture. In: CVPR, pp. 17529\u201317539 (2025)","DOI":"10.1109\/CVPR52734.2025.01633"},{"key":"8_CR27","unstructured":"Liu, S., et al.: DAB-DETR: Dynamic anchor boxes are better queries for DETR. arXiv preprint arXiv:2201.12329 (2022)"},{"issue":"6","key":"8_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"2","key":"8_CR29","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","volume":"129","author":"J Luiten","year":"2021","unstructured":"Luiten, J., Osep, A., Dendorfer, P., Torr, P., Geiger, A., Leal-Taix\u00e9, L., Leibe, B.: HOTA: a higher order metric for evaluating multi-object tracking. Int. J. Comput. Vision 129(2), 548\u2013578 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Single-shot multi-person 3D body pose estimation from monocular RGB input. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 2018 International Conference on 3D Vision (3DV), pp. 120\u2013130. IEEE (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: TrackFormer: multi-object tracking with transformers. In: CVPR, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: ICCV, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Moon, G., Choi, H., Lee, K.M.: Neuralannot: neural annotator for 3D human mesh training sets. In: CVPR, pp. 2299\u20132307 (2022)","DOI":"10.1109\/CVPRW56347.2022.00256"},{"key":"8_CR36","unstructured":"Newell, A., Hu, P., Lipson, L., Richter, S., Koltun, V.: CoMotion: concurrent multi-person 3D motion. In. ICLR (2025)"},{"key":"8_CR37","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Patel, P., Huang, C.H.P., Tesch, J., Hoffmann, D.T., Tripathi, S., Black, M.J.: Agora: avatars in geography optimized for regression analysis. In: CVPR, pp. 13468\u201313478 (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"8_CR40","first-page":"23703","volume":"34","author":"J Rajasegaran","year":"2021","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., Malik, J.: Tracking people with 3D representations. NeurIPS 34, 23703\u201323713 (2021)","journal-title":"NeurIPS"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., Malik, J.: Tracking people by predicting 3D appearance, location and pose. In: CVPR, pp. 2740\u20132749 (2022)","DOI":"10.1109\/CVPR52688.2022.00276"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Rogez, G., Weinzaepfel, P., Schmid, C.: LCR-Net++: multi-person 2D and 3D pose detection in natural images. In: TPAMI (2019)","DOI":"10.1109\/TPAMI.2019.2892985"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"S\u00e1r\u00e1ndi, I., Pons-Moll, G.: Neural localizer fields for continuous 3D human pose and shape estimation. NeurIPS (2024)","DOI":"10.52202\/079017-4444"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Su, C., Ma, X., Su, J., Wang, Y.: SAT-HMR: real-time multi-person 3D mesh estimation via scale-adaptive tokens. In: CVPR, pp. 16796\u201316806 (2025)","DOI":"10.1109\/CVPR52734.2025.01565"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Sun, Q., et\u00a0al.: AiOS: all-in-one-stage expressive human pose and shape estimation. In: CVPR, pp. 1834\u20131843 (2024)","DOI":"10.1109\/CVPR52733.2024.00180"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M.J., Mei, T.: Monocular, one-stage, regression of multiple 3D people. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Mei, T., Black, M.J.: Trace: 5D temporal regression of avatars with dynamic cameras in 3D environments. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00855"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, W., Bao, Q., Fu, Y., Mei, T., Black, M.J.: Putting people in their place: monocular regression of 3D people in depth. In: CVPR, pp. 13243\u201313252 (2022)","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Patel, P., Daniilidis, K., Black, M.J., Kocabas, M.: PromptHMR: promptable human mesh recovery. In: CVPR, pp. 1148\u20131159 (2025)","DOI":"10.1109\/CVPR52734.2025.00115"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., Wang, S.: Towards real-time multi-object tracking. In: ECCV, pp. 107\u2013122. Springer (2020)","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"8_CR51","unstructured":"Xiu, Y., Li, J., Wang, H., Fang, Y., Lu, C.: Pose Flow: efficient online pose tracking. In: BMVC (2018)"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Zanfir, A., Marinoiu, E., Sminchisescu, C.: Monocular 3D pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints. In: CVPR, pp. 2148\u20132157 (2018)","DOI":"10.1109\/CVPR.2018.00229"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20047-2_1"},{"issue":"11","key":"8_CR54","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: FairMOT: on the fairness of detection and re-identification in multiple object tracking. IJCV 129(11), 3069\u20133087 (2021)","journal-title":"IJCV"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Zheng, C., Zhu, S., Mendieta, M., Yang, T., Chen, C., Ding, Z.: 3D human pose estimation with spatial and temporal transformers. In: ICCV, pp. 11656\u201311665 (2021)","DOI":"10.1109\/ICCV48922.2021.01145"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37595-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:35:17Z","timestamp":1788935717000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37595-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375940","9783032375957"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37595-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}