{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T07:05:45Z","timestamp":1790319945297,"version":"4.1.0"},"reference-count":123,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00956","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10262-10274","source":"Crossref","is-referenced-by-count":6,"title":["HERO: Human Reaction Generation from Videos"],"prefix":"10.1109","author":[{"given":"Chengjun","family":"Yu","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition,USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhai","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition,USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition,USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition,USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition,USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Pixverse-v3","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01290"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3163676"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"ref7","volume-title":"Jimeng video","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00456"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"ref10","article-title":"Dancetogether! identity-preserving multi-person interactive video generation","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Motion11 m: Understanding human behaviors from human motions and videos","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242152"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00054"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00724"},{"key":"ref20","volume-title":"Mochi 1","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"ref23","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530750"},{"key":"ref31","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/795360"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275108"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681657"},{"key":"ref35","article-title":"Intermask: 3d human interaction generation via collaborative masked modelling","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Gohar Javed","year":"2025"},{"key":"ref36","article-title":"Brain-Based Learning: Teaching the Way Students Really Learn","author":"Jensen","year":"1996","journal-title":"Turning Point Publishing, Del Mar, CA"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_26"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref41","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"19807","article-title":"Ego-humans: An ego-centric 3d multi-human benchmark","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Khirodkar","year":"2023"},{"key":"ref43","article-title":"Harmony4d: A video dataset for in-the-wild close human interactions","volume-title":"The Thirtyeight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Khirodkar","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_5"},{"key":"ref46","article-title":"Auto-encoding variational bayes","author":"P Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/0278364921990671"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref49","volume-title":"Kling ai","author":"Kuaishou","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.4135\/9781446251409.n4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref53","article-title":"Dispose: Disentangling pose guidance for controllable human image animation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1099"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref58","article-title":"Interactive humanoid: Online full-body motion reaction synthesis with social affordance canonicalization and forecasting","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680636"},{"key":"ref60","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref61","first-page":"32939","article-title":"Humantomato: Text-aligned whole-body motion generation","volume-title":"International Conference on Machine Learning","author":"Lu"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref65","volume-title":"Hailuo ai","author":"MiniMax","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00991"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5244\/c.24.50"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01080"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref70","article-title":"Controlmm: Controllable masked motion generation","author":"Pinyoanuntapong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref73","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref75","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"International conference on machine learning","author":"Rezende"},{"key":"ref76","article-title":"Saying: The Extraordinary Powers of Our Five Senses","author":"Rosenblum","year":"2010","journal-title":"W. W. Norton & Company, New York"},{"key":"ref77","volume-title":"Gen-3 alpha","author":"Runway","year":"2024"},{"key":"ref78","first-page":"4","article-title":"Ut-interaction dataset, icpr contest on semantic description of human activities (sdha)","volume-title":"IEEE International Conference on Pattern Recognition Workshops","author":"S Ryoo","year":"2010"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696462"},{"key":"ref81","article-title":"Human motion diffusion as a generative prior","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shafir","year":"2024"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01615"},{"key":"ref83","volume-title":"Vidu 1.5","year":"2024"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref85","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612832"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581935"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3762244"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref90","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet","year":"2023"},{"key":"ref91","volume-title":"Wanxiang video","author":"Tongyi","year":"2024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref93","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130396"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46843-3_8"},{"key":"ref96","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6911"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00940"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00954"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00135"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00173"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00449"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01541"},{"key":"ref107","article-title":"Egochoir: Capturing 3d human-object interaction regions from egocentric views","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Yang","year":"2024"},{"key":"ref108","article-title":"Videogen-eval: Agent-based system for video generation evaluation","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00487"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref114","article-title":"The dawn of video generation: Preliminary explorations with sora-like models","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4405-4"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01016"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_8"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446239.pdf?arnumber=11446239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:33Z","timestamp":1777611873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":123,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00956","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}