{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:54:51Z","timestamp":1784904891065,"version":"3.55.0"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62076192"],"award-info":[{"award-number":["62076192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Fund Project of National Natural Science Foundation of China","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}]},{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZC20232033"],"award-info":[{"award-number":["GZC20232033"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M742738"],"award-info":[{"award-number":["2023M742738"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406231"],"award-info":[{"award-number":["62406231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT_15R53"],"award-info":[{"award-number":["IRT_15R53"]}]},{"name":"Fund for Foreign Scholars in University Research and Teaching Programs","award":["B07048"],"award-info":[{"award-number":["B07048"]}]},{"name":"Key Scientific Technological Innovation Research Project by Ministry of Education"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Fund of Xidian University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3607837","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:32:35Z","timestamp":1757611955000},"page":"8366-8380","source":"Crossref","is-referenced-by-count":3,"title":["Anomaly-Led Prompting Learning Caption Generating Model and Benchmark"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-3881","authenticated-orcid":false,"given":"Qianyue","family":"Bao","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2604-4381","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2002-3894","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoliang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3040591"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104078"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037538"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2984093"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3112814"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3336576"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413887"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413973"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.11.018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177308"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295098"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3003592"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref32","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3230262"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3194869"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/c2019-0-00628-0"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3174873"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_29"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053563"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00684"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083152"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475693"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3227044"},{"key":"ref51","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072863"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01953"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3150763"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00316"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3307969"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135420"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01250"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01096"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424566"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311447"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3386339"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402242"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612345"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3021980"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129349"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3461718"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023303"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074805"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292596"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405716"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2950530"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3175611"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147369"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535377"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref94","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"issue":"1","key":"ref95","first-page":"5485","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":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref97","article-title":"ERNIE: Enhanced representation through knowledge integration","author":"Sun","year":"2019"},{"key":"ref98","article-title":"Spacy","year":"2016"},{"key":"ref99","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref100","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref101","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bao","year":"2022"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02188"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11159180.pdf?arnumber=11159180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:34Z","timestamp":1763059474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11159180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3607837","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}