{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T20:07:15Z","timestamp":1779739635925,"version":"3.53.1"},"reference-count":56,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372441"],"award-info":[{"award-number":["62372441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2023A1515030268"],"award-info":[{"award-number":["2023A1515030268"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shenzhen Science and Technology Program","award":["RCYX20231211090127030"],"award-info":[{"award-number":["RCYX20231211090127030"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20250604182948064"],"award-info":[{"award-number":["JCYJ20250604182948064"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3654382","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:50:42Z","timestamp":1768510242000},"page":"3694-3708","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4161-1598","authenticated-orcid":false,"given":"Shiyao","family":"Yu","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6259-1368","authenticated-orcid":false,"given":"Zi-An","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangning","family":"Yin","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0622-8512","authenticated-orcid":false,"given":"Zheng","family":"Tian","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-715X","authenticated-orcid":false,"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3289-9714","authenticated-orcid":false,"given":"Weixin","family":"Si","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9042-6069","authenticated-orcid":false,"given":"Shihao","family":"Zou","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521736"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405743"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00281"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref11","first-page":"1","article-title":"Human motion diffusion model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tevet","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548090"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548099"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330935"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392440"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00158"},{"key":"ref24","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref26","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref28","first-page":"1","article-title":"Auto-Encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref31","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Den","year":"2017"},{"key":"ref32","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref33","article-title":"COCA: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3393512"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680763"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref37","first-page":"1","article-title":"Distilbert, a distilled version of BERT: Smaller, faster, cheaper and lighter","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Sanh","year":"2019"},{"issue":"140","key":"ref38","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref43","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref44","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":"ref45","first-page":"25105","article-title":"VideoPoet: A large language model for zero-shot video generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kondratyuk","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007511"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-023-00207-w"},{"key":"ref48","first-page":"130084","article-title":"An efficient memory module for graph few-shot class-incremental learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Li","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref51","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref55","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11353936.pdf?arnumber=11353936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:55:16Z","timestamp":1779738916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3654382","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}