{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:10:36Z","timestamp":1773137436558,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFA0706202"],"award-info":[{"award-number":["2019YFA0706202"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/jbhi.2025.3631045","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:49:18Z","timestamp":1762800558000},"page":"1972-1985","source":"Crossref","is-referenced-by-count":0,"title":["MoChat: Joints-Grouped Spatio-Temporal Grounding Multimodal Large Language Model for Multi-Turn Motion Comprehension and Description"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3925-4560","authenticated-orcid":false,"given":"Jiawei","family":"Mo","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9924-3252","authenticated-orcid":false,"given":"Yixuan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6005-3131","authenticated-orcid":false,"given":"Rifen","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongkang","family":"Ni","sequence":"additional","affiliation":[{"name":"School of Software, Xinjiang University, Urumqi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8542-9871","authenticated-orcid":false,"given":"Feng","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Medical Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1726-0955","authenticated-orcid":false,"given":"Min","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-699X","authenticated-orcid":false,"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Medical Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0188-1394","authenticated-orcid":false,"given":"Min","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR66766.2025.11063192"},{"key":"ref2","article-title":"SkelMamba: A state space model for efficient skeleton action recognition of neurological disorders","author":"Martinel","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref7","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref9","first-page":"20067","article-title":"MotionGPT: Human motion as a foreign language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2024"},{"key":"ref10","first-page":"30641","article-title":"LanguageBind: Extending video-language pretraining to n-modality by language-based semantic alignment","volume-title":"Int. Conf. Learn. Represent.","author":"Zhu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00516"},{"key":"ref12","first-page":"11045","article-title":"Part-level graph convolutional network for skeleton-based action recognition","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Huang","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref14","first-page":"41340","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Qian","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"ref24","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Den","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. 2019 Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref30","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%  chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref32","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"ref34","article-title":"Joint-partition group attention for skeleton-based action recognition","volume-title":"Signal Process.","volume":"224","author":"Cui","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.08287"},{"key":"ref36","article-title":"ChatGLM: A family of large language models from GLM-130b to GLM-4 all tools","author":"GLM","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref40","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref42","first-page":"5333","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02433-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2025.3579203"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11424173\/11237042.pdf?arnumber=11237042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:09Z","timestamp":1773086349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11237042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3631045","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}