{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T19:00:33Z","timestamp":1770231633076,"version":"3.49.0"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128614","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13913-13919","source":"Crossref","is-referenced-by-count":1,"title":["Social-MAE: Social Masked Autoencoder for Multi-Person Motion Representation Learning"],"prefix":"10.1109","author":[{"given":"Mahsa","family":"Ehsanpour","sequence":"first","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"Reid","sequence":"additional","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref2","article-title":"Social-bigat: Multimodal trajectory forecasting using bicycle-gan and graph attention networks","volume":"32","author":"Kosaraju","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01314"},{"key":"ref4","first-page":"6036","article-title":"Multi-person 3d motion prediction with multi-range transformers","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","article-title":"Stochastic multi-person 3d motion forecasting","volume-title":"The Eleventh International Conference on Learning Representations","author":"Xu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01215-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_15"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref15","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","author":"Xu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"35 946","article-title":"Masked autoencoders as spatiotemporal learners","volume":"35","author":"Feichtenhofer","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pretraining","author":"Tong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01530"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_45"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00144"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00074"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010742"},{"key":"ref29","article-title":"Somoformer: Multi-person pose forecasting with transformers","author":"Vendrow","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.176"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070525"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/c.24.50"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738732"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3392824"},{"key":"ref36","article-title":"Real-time trajectorybased social group detection","author":"Jahangard","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00833"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref41","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning","author":"Chen","year":"2020"},{"key":"ref42","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref43","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref47","article-title":"Vimpac: Video pre-training via masked token prediction and contrastive learning","author":"Tan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref49","article-title":"Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_3"},{"key":"ref51","article-title":"Maskgae: masked graph modeling meets graph autoencoders","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3216899"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547796"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00334"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_28"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00255"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00958"},{"key":"ref59","article-title":"An improved baseline framework for pose estimation challenge at eccv 2022 visual perception for navigation in human environments workshop","volume-title":"arXiv preprint","author":"Fu","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00332"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3070543"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128614.pdf?arnumber=11128614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:12:29Z","timestamp":1756879949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128614","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}