{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:04:42Z","timestamp":1777889082218,"version":"3.51.4"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["52074305,52274160,51874300"],"award-info":[{"award-number":["52074305,52274160,51874300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002888","name":"R&D Program of Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KM202211417005"],"award-info":[{"award-number":["KM202211417005"]}],"id":[{"id":"10.13039\/501100002888","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00237","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models"],"prefix":"10.1109","author":[{"given":"Jiaqi","family":"Wu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simin","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Tang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhe","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lixu","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Lin","sequence":"additional","affiliation":[{"name":"Beijing Baidu Netcom Science Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehua","family":"Wang","sequence":"additional","affiliation":[{"name":"University of British Columbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Tian","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology (Beijing)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/792548.611918"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.488"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01493"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02355"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.422"},{"key":"ref8","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref10","article-title":"Black-box prompt learning for pre-trained language models","author":"Diao","year":"2023","journal-title":"Trans. Mach. Learn. Res., 2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00983"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00819"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240559"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3302410"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29179"},{"key":"ref18","article-title":"Exploring backdoor attacks against large language model-based decision making","author":"Jiao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671573"},{"issue":"7","key":"ref20","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref23","volume-title":"Tele-flm technical report","author":"Li","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02359"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3431526"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01895-7"},{"key":"ref28","article-title":"Where to begin? on the impact of pre-training and initialization in federated learning","author":"Nguyen","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Federated text-driven prompt generation for visionlanguage models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qiu","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9760.2004.00190.x"},{"key":"ref31","article-title":"Fedbpt: Efficient federated black-box prompt tuning for large language models","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17219"},{"key":"ref34","article-title":"Non-transferable learning: A new approach for model ownership verification and applicability authorization","volume-title":"International Conference on Learning Representation (ICLR2022)","author":"Wang","year":"2022"},{"key":"ref35","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3703626"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28387"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680779"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671897"},{"key":"ref40","article-title":"Feddtpt: federated discrete and transferable prompt tuning for black-box large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/187"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612222"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547883"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095356"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00072"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28615"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443593.pdf?arnumber=11443593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:36Z","timestamp":1777611996000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00237","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}