{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T10:08:02Z","timestamp":1776161282311,"version":"3.50.1"},"reference-count":29,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"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"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1205123"],"award-info":[{"award-number":["2023YFF1205123"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["62572339"],"award-info":[{"award-number":["62572339"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1204100"],"award-info":[{"award-number":["2023YFF1204100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.jvcir.2026.104782","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T17:27:08Z","timestamp":1773854828000},"page":"104782","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DualAdapt : A simple parallel framework makes CLIP-based Few-shot Learning classifier see better"],"prefix":"10.1016","volume":"117","author":[{"given":"Jiayi","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longlong","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104782_b1","unstructured":"A. Radford, J.W. Kim, C. Hallacy, et al., Learning transferable visual models from natural language supervision, in: Proceedings of the International Conference on Machine Learning, ICML, 2021."},{"key":"10.1016\/j.jvcir.2026.104782_b2","unstructured":"J. Li, D. Li, S. Savarese, et al., BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models, in: Proceedings of the International Conference on Machine Learning, ICML, 2023."},{"key":"10.1016\/j.jvcir.2026.104782_b3","series-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104782_b4","series-title":"Semantic prompt for few-shot image recognition","author":"Chen","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104782_b5","series-title":"Findings of the Association for Computational Linguistics","article-title":"AutoPrompt: Eliciting knowledge from language models with automatically generated prompts","author":"Shin","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104782_b6","doi-asserted-by":"crossref","unstructured":"A. Aghajanyan, S. Gupta, L. Zettlemoyer, Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning, in: Proceedings of the Annual Meeting of the Association for Computational Linguistics, ACL, 2021.","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"10.1016\/j.jvcir.2026.104782_b7","series-title":"On the stability of fine-tuning BERT","author":"Mosbach","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104782_b8","article-title":"VTPL: Visual-text prompt learning for efficient adaptation of vision-language models","volume":"104","author":"Sun","year":"2024","journal-title":"J. Vis. Commun. Image Represent. (JVCI)"},{"key":"10.1016\/j.jvcir.2026.104782_b9","article-title":"GLP-EAA: Global-local prompt enhanced adaptive aggregation for CLIP-based classification","volume":"105","author":"Zhang","year":"2024","journal-title":"JVCI"},{"key":"10.1016\/j.jvcir.2026.104782_b10","article-title":"Multi-level similarity transfer with adaptive fusion for few-shot image recognition","volume":"102","author":"Zhu","year":"2024","journal-title":"JVCI"},{"key":"10.1016\/j.jvcir.2026.104782_b11","article-title":"Bi-modal semantic fusion network for cross-modal few-shot recognition","volume":"101","author":"Li","year":"2024","journal-title":"JVCI"},{"key":"10.1016\/j.jvcir.2026.104782_b12","article-title":"Prototype-guided multimodal alignment for CLIP-based few-shot learning","volume":"108","author":"Wang","year":"2025","journal-title":"JVCI"},{"key":"10.1016\/j.jvcir.2026.104782_b13","series-title":"Meta-Transfer Learning for Few-Shot Learning","author":"Sun","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104782_b14","article-title":"Prompt-guided semantic alignment for robust CLIP transfer learning","volume":"104","author":"Gao","year":"2024","journal-title":"JVCI"},{"key":"10.1016\/j.jvcir.2026.104782_b15","article-title":"Lightweight multi-scale visual representation learning for few-shot classification","volume":"100","author":"Chen","year":"2024","journal-title":"JVCI"},{"key":"10.1016\/j.jvcir.2026.104782_b16","article-title":"Attention-efficient cross-modal fusion for CLIP adaptation","volume":"107","author":"Zhou","year":"2025","journal-title":"JVCI"},{"key":"10.1016\/j.jvcir.2026.104782_b17","doi-asserted-by":"crossref","unstructured":"W. Li, L. Wang, J. Xu, et al., Revisiting local descriptor based image-to-class measure for few-shot learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019.","DOI":"10.1109\/CVPR.2019.00743"},{"key":"10.1016\/j.jvcir.2026.104782_b18","series-title":"Task Agnostic Meta-Learning for Few-Shot Learning","author":"Jamal","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104782_b19","series-title":"Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning","author":"Gidaris","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104782_b20","article-title":"Adaptive cross-modal few-shot learning","author":"Xing","year":"2019","journal-title":"NeurIPS"},{"key":"10.1016\/j.jvcir.2026.104782_b21","doi-asserted-by":"crossref","unstructured":"Z. Peng, Z. Li, J. Zhang, et al., Few-shot image recognition with knowledge transfer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2019.","DOI":"10.1109\/ICCV.2019.00053"},{"key":"10.1016\/j.jvcir.2026.104782_b22","series-title":"Universal language model fine-tuning for text classification","author":"Howard","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104782_b23","unstructured":"J. Wang, et al., NAS-FPN: Learning scalable feature pyramid architecture for object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020."},{"key":"10.1016\/j.jvcir.2026.104782_b24","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.jvcir.2026.104782_b25","series-title":"A survey on CLIP: fundamentals, applications, and advances","author":"Liu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104782_b26","series-title":"Diverse and robust representation learning from CLIP","author":"Shin","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104782_b27","unstructured":"X. Wang, et al., Cross-modal contrastive learning for image-text retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021."},{"key":"10.1016\/j.jvcir.2026.104782_b28","series-title":"MiniGPT-4: Enhancing vision-language understanding with advanced multimodal training","author":"Zhu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104782_b29","series-title":"Multimodal learning with CLIP for image classification","author":"Wang","year":"2020"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000775?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000775?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T09:08:29Z","timestamp":1776157709000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000775"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":29,"alternative-id":["S1047320326000775"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104782","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DualAdapt : A simple parallel framework makes CLIP-based Few-shot Learning classifier see better","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104782","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104782"}}