{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:07Z","timestamp":1783542487631,"version":"3.55.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ24021"],"award-info":[{"award-number":["JQ24021"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125207"],"award-info":[{"award-number":["62125207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472411"],"award-info":[{"award-number":["62472411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3668226","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:46:38Z","timestamp":1772138798000},"page":"9561-9574","source":"Crossref","is-referenced-by-count":0,"title":["SyMFood: Synergistic Multi-Modal Prompting for Fine-Grained Zero-Shot Food Detection"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9954-0427","authenticated-orcid":false,"given":"Xinlong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-9208","authenticated-orcid":false,"given":"Weiqing","family":"Min","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoulong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6790-0239","authenticated-orcid":false,"given":"Guorui","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Ludong University, Yantai, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4326","authenticated-orcid":false,"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3329168"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374211"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_10"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00747"},{"key":"ref6","article-title":"Zero-shot object detection by hybrid region embedding","author":"Demirel","year":"2018","journal-title":"arXiv:1805.06157"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3140070"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3578654"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3585925"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02586"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01253"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3467229"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3575957"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3563606"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3414275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3262754"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01222"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32212"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23977\/acss.2023.070812"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3444782"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3535818"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02230"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680694"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612523"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3529937"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28381"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01869"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612661"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3360899"},{"key":"ref39","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"Norouzi","year":"2013","journal-title":"arXiv:1312.5650"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_34"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3184821"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160870"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00171"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586118"},{"key":"ref52","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","author":"Qu","year":"2025","journal-title":"arXiv:2502.06501"},{"key":"ref53","article-title":"Locality-aware cross-modal correspondence learning for dense audio-visual events localization","author":"Xing","year":"2024","journal-title":"arXiv:2409.07967"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11414166.pdf?arnumber=11414166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:26Z","timestamp":1783539926000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11414166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":53,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3668226","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}