{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:46:18Z","timestamp":1755798378909,"version":"3.44.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,14]]},"DOI":"10.1109\/icip55913.2025.11084554","type":"proceedings-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:41:38Z","timestamp":1755546098000},"page":"617-622","source":"Crossref","is-referenced-by-count":0,"title":["GIP: Gated Interaction Prompt for Parameter Efficient Vision-Language Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Lin","sequence":"first","affiliation":[{"name":"Beihang University,SKLCCSE,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixin","family":"Li","sequence":"additional","affiliation":[{"name":"SCSE, Beihang University,IRIP Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu","family":"Guo","sequence":"additional","affiliation":[{"name":"National Computer Network Emergency Response Technical Team\/Coordination Center of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihong","family":"Wang","sequence":"additional","affiliation":[{"name":"National Computer Network Emergency Response Technical Team\/Coordination Center of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Huang","sequence":"additional","affiliation":[{"name":"Beihang University,SKLCCSE,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref5"},{"key":"ref6","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"ArXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref8","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"International Conference on Machine Learning","author":"Cho"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref10","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref13","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International conference on machine learning","author":"Houlsby"},{"key":"ref14","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.433"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref20","article-title":"Towards a unified view on visual parameter-efficient transfer learning","author":"Yu","year":"2022","journal-title":"ArXiv preprint arXiv:2210.00788"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00281"},{"article-title":"Memory-space visual prompting for efficient vision-language fine-tuning","year":"2024","author":"Jie","key":"ref27"},{"article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","year":"2023","author":"Zhang","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1644"},{"article-title":"Microsoft coco captions: Data collection and evaluation server","year":"2015","author":"Chen","key":"ref32"},{"key":"ref33","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref35","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref36","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref37","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2025 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2025,9,14]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2025,9,17]]}},"container-title":["2025 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11084272\/11083968\/11084554.pdf?arnumber=11084554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T04:50:29Z","timestamp":1755579029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icip55913.2025.11084554","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}