{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:10:43Z","timestamp":1788808243166,"version":"build-2803163510"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["JQ23016"],"award-info":[{"award-number":["JQ23016"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62476273"],"award-info":[{"award-number":["62476273"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Development Fund of Macau Project","award":["0044\/2024\/AGJ"],"award-info":[{"award-number":["0044\/2024\/AGJ"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tcsvt.2026.3692794","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:59:56Z","timestamp":1778788796000},"page":"13317-13330","source":"Crossref","is-referenced-by-count":0,"title":["SSPA: Split-and-Synthesize Prompting With Gated Alignments for Multi-Label Image Recognition"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1421-779X","authenticated-orcid":false,"given":"Hao","family":"Tan","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CASIA)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8501-4123","authenticated-orcid":false,"given":"Zichang","family":"Tan","sequence":"additional","affiliation":[{"name":"Sangfor Technologies Inc.","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9169-7194","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CASIA)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4735-2885","authenticated-orcid":false,"given":"Jun","family":"Wan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CASIA)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CASIA)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-8096","authenticated-orcid":false,"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12230"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01345"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475191"},{"key":"ref12","article-title":"Query2Label: A simple transformer way to multi-label classification","author":"Liu","year":"2021","journal-title":"arXiv:2107.10834"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00142"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01408"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref19","article-title":"Tag2Text: Guiding vision-language model via image tagging","author":"Huang","year":"2023","journal-title":"arXiv:2303.05657"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/su15020901"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2919199"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6883"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806375"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939756"},{"key":"ref25","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":"ref26","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00130"},{"key":"ref28","article-title":"Open vocabulary multi-label classification with dual-modal decoder on aligned visual-textual features","author":"Xu","year":"2022","journal-title":"arXiv:2208.09562"},{"key":"ref29","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521677"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288205"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268997"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284812"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00451"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00474"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01584"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00722"},{"key":"ref43","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3408256"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3577277"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2216"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346405"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3454366"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3354031"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3570440"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3669254"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586118"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3629609"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372451"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00029"},{"key":"ref61","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref62","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref64","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Lisa Li","year":"2021","journal-title":"arXiv:2101.00190"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref67","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv:2210.07183"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01662"},{"key":"ref69","article-title":"LLMs Meet VLMs: Boost open vocabulary object detection with fine-grained descriptors","author":"Jin","year":"2024","journal-title":"arXiv:2402.04630"},{"key":"ref70","article-title":"Improving text-to-image consistency via automatic prompt optimization","author":"Ma\u00f1as","year":"2024","journal-title":"arXiv:2403.17804"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref73","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref74","article-title":"Quaternion recurrent neural networks","author":"Parcollet","year":"2018","journal-title":"arXiv:1806.04418"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02515"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239229"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053012"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.46"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878349"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654966"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3110314"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.09.020"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002185"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00023"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/163"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00113"},{"key":"ref93","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/117"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00100"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01591-y"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.019"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19991"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01499-z"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178144"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.028"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285411"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28419"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref105","first-page":"1","article-title":"Visual classification via description from large language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Menon"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11679504\/11517490.pdf?arnumber=11517490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:07:11Z","timestamp":1788808031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11517490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":105,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3692794","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}