{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:09:19Z","timestamp":1789124959305,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372802","type":"print"},{"value":"9783032372819","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\/978-3-032-37281-9_1","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:46:18Z","timestamp":1789123578000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-THuMBS: Multi-person Tracking of\u00a03D Human Meshes Beyond Video Shots"],"prefix":"10.1007","author":[{"given":"Jeongwan","family":"On","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Salman","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muneeb A.","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunwoo","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inwoong","family":"Moon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyung Jin","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaekwang","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seong Jong","family":"Ha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungryul","family":"Baek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, E., Jones, M., Marks, T.K.: An Improved Deep Learning Architecture for Person Re-Identification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299016"},{"key":"1_CR2","unstructured":"Brandon, C.: PySceneDetect: Automatic Scene Cut Detection Tool (2014)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Choi, C., Kim, J., Cha, G., Kim, M., Wee, D., Kim, Y.M.: Humans as a calibration pattern: dynamic 3D scene reconstruction from unsynchronized and uncalibrated videos. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00622"},{"key":"1_CR4","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person ReIdentification by Symmetry-Driven Accumulation of Local Features. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539926"},{"key":"1_CR6","unstructured":"Gheissari, N., Sebastian, T.B., Hartley, R.: Person Reidentification Using Spatiotemporal Appearance. In: CVPR (2006)"},{"key":"1_CR7","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 (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a Video Dataset of Spatio-Temporally Localized Atomic Visual Actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"He, S., et al.: TransReID: transformerBased Object Re-Identification. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"1_CR10","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Bansal, A., Ma, L., Newcombe, R., Vo, M., Kitani, K.: EgoHumans: an Egocentric 3D Multi-Human Benchmark. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01814"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Song, J.T., Cao, J., Luo, Z., Kitani, K.: Harmony4D: a Video Dataset for In-The-Wild Close Human Interactions. In: NeurIPS (2024)","DOI":"10.52202\/079017-3407"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Kim, S., Do, S., Park, J.: Showmak3r: compositional tv show reconstruction. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00089"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: VIBE: video Inference for Body Pose and Shape Estimation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W.: The Hungarian Method for the Assignment Problem. Naval Research Logistics Quarterly (1955)","DOI":"10.1002\/nav.3800020109"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding Image Matching in 3D with MASt3R. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Yu, Y., Zhou, Z., Shao, M., Fu, Y.: End-to-End Comparative Attention Network for Person Re-Identification. In: TIP (2017)","DOI":"10.1109\/TIP.2017.2700762"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a Skinned Multi-Person Linear Model. In: ACM ToG (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"1_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled Weight Decay Regularization. In: ICLR (2019)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPR (2019)","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. In: ACM ToG (2017)","DOI":"10.1145\/3072959.3073596"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"M\u00fcller, L., Choi, H., Zhang, A., Yi, B., Malik, J., Kanazawa, A.: Reconstructing people, places, and cameras. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02044"},{"key":"1_CR24","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high performance deep learning library. In: NeuRIPS (2019)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive Body Capture: 3D Hands, Face, and Body from a Single Image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"1_CR26","unstructured":"Pavlakos, G., Kanazawa, A., Malik, J., Black, M.J., Daniilidis, K.: Multi-Shot Person Tracking and Re-Identification in TV Series. In: CVPR (2022)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Malik, J., Kanazawa, A.: Human mesh recovery from multiple shots. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00154"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Weber, E., Tancik, M., Kanazawa, A.: The one where they reconstructed 3D humans and environments in tv shows. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19836-6_41"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., Malik, J.: Tracking people by predicting 3D appearance, location & pose. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00276"},{"key":"1_CR30","unstructured":"Ren, T., et\u00a0al.: Grounded Sam: assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 (2024)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Rojas, S., Armando, M., Ghanem, B., Weinzaepfel, P., Leroy, V., Rogez, G.: Hamst3r: human-aware multi-view stereo 3d reconstruction. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00478"},{"key":"1_CR32","unstructured":"SciPy: Exact Euclidean distance transform, available at: https:\/\/docs.scipy.org\/doc\/scipy\/reference\/generated\/scipy.ndimage.distance_transform_edt.html"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Shen, Z., et al.: World-Grounded Human Motion Recovery via Gravity-View Coordinates. In: ACM ToG (2024)","DOI":"10.1145\/3680528.3687565"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Shin, S., Kim, J., Halilaj, E., Black, M.J.: WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Somers, V., Alahi, A., Vleeschouwer, C.D.: Keypoint promptable re-identification. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72986-7_13"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: MV-DUSt3R+: single-Stage Scene Reconstruction from Sparse Views In 2 Seconds. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00498"},{"key":"1_CR37","unstructured":"Teed, Z., Deng, J.: DROID-SLAM: deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. In: NeurIPS (2021)"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Varior, R.R., Shuai, B., Lu, J., Xu, D., Wang, G.: A Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_48"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual Geometry Grounded Transformer. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: Geometric 3D Vision Made Easy. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"1_CR41","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 (2025)","DOI":"10.1109\/CVPR52734.2025.00115"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose: simple vision transformer baselines for human pose estimation. In: NeurIPS (2022)","DOI":"10.52202\/068431-2795"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Yang, F., Gu, K., Nguyen, H.L., Tse, T.H.E., Yao, A.: Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00573"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Ye, V., Pavlakos, G., Malik, J., Kanazawa, A.: Decoupling Human and Camera Motion from Videos in the Wild. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, C., Zhang, G., Ma, C., Zhang, T., Niu, G.: From poses to identity: Training-free person re-identification via feature centralization. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02273"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Egobody: human body shape and motion of interacting people from head-mounted devices. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: HumanMM: global Human Motion Recovery from Multi-shot Videos. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00190"}],"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\/978-3-032-37281-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:46:30Z","timestamp":1789123590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37281-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372802","9783032372819"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37281-9_1","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":"12 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"}}]}}