{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:45Z","timestamp":1774420125211,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888476","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["MMTP: Meta-learning-based Multi-Textual Prompt Tuning for Visual-Language Models"],"prefix":"10.1109","author":[{"given":"Fangtong","family":"Sun","sequence":"first","affiliation":[{"name":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"}]},{"given":"Junjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"}]},{"given":"Zunlin","family":"Fan","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"}]},{"given":"Yiying","family":"Li","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"}]},{"given":"Zhiyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"}]},{"given":"Ke","family":"Yang","sequence":"additional","affiliation":[{"name":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3582688"},{"key":"ref4","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2022","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref6","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103447"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3689095.3689103"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref12","article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2022","journal-title":"ACL"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref17","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","author":"Franceschi","year":"2018","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","first-page":"178","article-title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories","author":"Fei-Fei","year":"2004","journal-title":"CVPR-W"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref24","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref26","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref29","first-page":"3915","article-title":"Feature-critic networks for heterogeneous domain generalization","volume-title":"ICML.","author":"Li","year":"2019"},{"key":"ref30","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","author":"Recht","year":"2019","journal-title":"ICML"},{"key":"ref31","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref34","article-title":"Plot: prompt learning with optimal transport for vision-language models","author":"Chen","year":"2023","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"ref38","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02513"},{"key":"ref40","article-title":"Consistency-guided prompt learning for vision-language models","author":"Roy","year":"2024","journal-title":"ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28387"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888476.pdf?arnumber=10888476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:32Z","timestamp":1774416392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888476","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}