{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T20:03:34Z","timestamp":1784923414400,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2025YFF0511302"],"award-info":[{"award-number":["2025YFF0511302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668541","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"6266-6274","source":"Crossref","is-referenced-by-count":0,"title":["MambaGesture2: Co-Speech Gesture Generation via Hierarchical Fusion and Spatiotemporal Aggregation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3732-3035","authenticated-orcid":false,"given":"Chencan","family":"Fu","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6592-8411","authenticated-orcid":false,"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2771-5196","authenticated-orcid":false,"given":"Haoyang","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3437-3565","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"YouTu Lab, Tencent","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-8090","authenticated-orcid":false,"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"YouTu Lab, Tencent","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4665-6852","authenticated-orcid":false,"given":"Ying","family":"Tai","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"YouTu Lab, Tencent","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616114"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680625"},{"key":"ref3","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521798"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405743"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3658134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127831"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00155"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3407692"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3348331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3607711"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00217"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558061"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680684"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680847"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687922"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687677"},{"key":"ref20","article-title":"InterAct: Capture and modelling of realistic, expressive and interactive activities between two persons in daily scenarios","author":"Huang","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00138"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111774"},{"key":"ref23","article-title":"Simplified state space layers for sequence modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Smith","year":"2023"},{"key":"ref24","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0633"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00672"},{"key":"ref28","article-title":"Vision Mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2274"},{"key":"ref30","article-title":"U-Mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024"},{"key":"ref31","article-title":"Jamba: A hybrid transformer-mamba language model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lenz","year":"2025"},{"key":"ref32","first-page":"265","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref33","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref34","article-title":"Human motion diffusion model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tevet","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref40","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref44","article-title":"SaRA: High-efficient diffusion model fine-tuning with progressive sparse low-rank adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3541588"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3203421"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205747"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3341332"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11417237.pdf?arnumber=11417237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:06:51Z","timestamp":1784920011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668541","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}