{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:43Z","timestamp":1779948103986,"version":"3.53.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00166","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1750-1759","source":"Crossref","is-referenced-by-count":0,"title":["Dense Motion Captioning"],"prefix":"10.1109","author":[{"given":"Shiyao","family":"Xu","sequence":"first","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benedetta","family":"Liberatori","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00fcl","family":"Varol","sequence":"additional","affiliation":[{"name":"Univ Gustave Eiffel, CNRS,LIGM, Ecole des Ponts, IP Paris"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Rota","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687559"},{"key":"ref2","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00199"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3627546"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00832"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_19"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01287"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00671"},{"key":"ref14","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"ref16","article-title":"MotionGPT: Human motion as a foreign language","author":"Jiang","year":"2024","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00027"},{"key":"ref19","article-title":"Human motion instruction tuning","author":"Li","year":"2024","journal-title":"arXiv"},{"key":"ref20","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref21","article-title":"Motion-X: A large-scale 3D expressive whole-body human motion dataset","author":"Lin","year":"2023","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02594"},{"key":"ref24","article-title":"Tulip: Token-length upgraded clip","author":"Najdenkoska","year":"2024","journal-title":"arXiv"},{"key":"ref25","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref32","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2024","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/325165.325242"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-024-00272-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i11.37878"},{"key":"ref36","article-title":"Human motion diffusion model","author":"Tevet","year":"2023","journal-title":"ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01765"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3694713"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02392-9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01284"},{"key":"ref43","article-title":"Motion-agent: A conversational framework for human motion generation with LLMs","author":"Wu","year":"2025","journal-title":"ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref47","article-title":"KinMo: Kinematic-aware human motion understanding and generation","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_21"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00982"},{"key":"ref50","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2020","journal-title":"ICLR"},{"key":"ref51","article-title":"Motion-X++: A large-scale multimodal 3D whole-body human motion dataset","author":"Zhang","year":"2025","journal-title":"arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533273.pdf?arnumber=11533273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:20Z","timestamp":1779944540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00166","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}