{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:56:59Z","timestamp":1777874219680,"version":"3.51.4"},"reference-count":90,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2021ZD0109802"],"award-info":[{"award-number":["2021ZD0109802"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81972248"],"award-info":[{"award-number":["81972248"]}],"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","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133555","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:18:18Z","timestamp":1775841498000},"page":"133555","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MoDe: Multi-modal discriminative priors for prompt tuning"],"prefix":"10.1016","volume":"685","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8369-7533","authenticated-orcid":false,"given":"Xinyang","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5155-7069","authenticated-orcid":false,"given":"Chuang","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1237-0423","authenticated-orcid":false,"given":"Maoyuan","family":"Shao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3655-872X","authenticated-orcid":false,"given":"Zekuan","family":"Yu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133555_bib0005","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event, Vol. 139 of Proceedings of Machine Learning Research","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.133555_bib0010","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133555_bib0015","series-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, June 19\u201325, 2021","first-page":"5579","article-title":"Vinvl: revisiting visual representations in vision-language models","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133555_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111503","article-title":"MIC: image-text matching in circles with cross-modal generative knowledge enhancement","volume":"289","author":"Pu","year":"2024","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133555_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129826","article-title":"Enhancing generalization in camera trap image recognition: fine-tuning visual language models","volume":"634","author":"Yang","year":"2025","journal-title":"Neurocomputing"},{"issue":"9","key":"10.1016\/j.neucom.2026.133555_bib0030","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.133555_bib0035","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023","article-title":"Learning domain-aware detection head with prompt tuning","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0040","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"7061","article-title":"Open-vocabulary semantic segmentation with mask-adapted CLIP","author":"Liang","year":"2023"},{"issue":"3","key":"10.1016\/j.neucom.2026.133555_bib0045","doi-asserted-by":"crossref","first-page":"2870","DOI":"10.1109\/TCSVT.2024.3488181","article-title":"High efficiency image compression for large visual-language models","volume":"35","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"6","key":"10.1016\/j.neucom.2026.133555_bib0050","doi-asserted-by":"crossref","first-page":"5925","DOI":"10.1109\/TCSVT.2025.3528108","article-title":"Plovad: prompting vision-language models for open vocabulary video anomaly detection","volume":"35","author":"Xu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133555_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6757","article-title":"Visual-language prompt tuning with knowledge-guided context optimization","author":"Yao","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"23438","article-title":"Tcp:textual-based class-aware prompt tuning for visual-language model","author":"Yao","year":"2024"},{"key":"10.1016\/j.neucom.2026.133555_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111395","article-title":"Knowledge-based dynamic prompt learning for multi-label disease diagnosis","volume":"286","author":"Xie","year":"2024","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133555_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110647","article-title":"Kpt++: refined knowledgeable prompt tuning for few-shot text classification","volume":"274","author":"Ni","year":"2023","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133555_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110064","article-title":"Kept: knowledge enhanced prompt tuning for event causality identification","volume":"259","author":"Liu","year":"2023","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133555_bib0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128290","article-title":"Multi-task prompt tuning with soft context sharing for vision-language models","volume":"603","author":"Ding","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133555_bib0085","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15190","article-title":"Self-regulating prompts: foundational model adaptation without forgetting","author":"Khattak","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0090","author":"Li"},{"key":"10.1016\/j.neucom.2026.133555_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19113","article-title":"Maple: multi-modal prompt learning","author":"Khattak","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0100","author":"Yao"},{"key":"10.1016\/j.neucom.2026.133555_bib0105","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7\u201311, 2022","first-page":"11351","article-title":"Prompting ELECTRA: few-shot learning with discriminative pre-trained models","author":"Xia","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0110","series-title":"Proceedings of the 5th Clinical Natural Language Processing Workshop, ClinicalNLP@ACL 2023, Toronto, Canada, July 14, 2023","first-page":"247","article-title":"Prompt discriminative language models for domain adaptation","author":"Lu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0115","series-title":"Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, May 22\u201327, 2022","first-page":"3468","article-title":"Prompt tuning for discriminative pre-trained language models","author":"Yao","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0120","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TMM.2021.3063616","article-title":"Alleviating domain shift via discriminative learning for generalized zero-shot learning","volume":"24","author":"Ye","year":"2022","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.neucom.2026.133555_bib0125","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"3208","article-title":"Digeo: discriminative geometry-aware learning for generalized few-shot object detection","author":"Ma","year":"2023"},{"issue":"12","key":"10.1016\/j.neucom.2026.133555_bib0130","doi-asserted-by":"crossref","first-page":"12756","DOI":"10.1109\/TCSVT.2024.3436148","article-title":"Learning discriminative representations from cross-scale features for camouflaged object detection","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133555_bib0135","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"19325","article-title":"Multimodality helps unimodality: cross-modal few-shot learning with multimodal models","author":"Lin","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0140","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"15471","article-title":"Expanding large pre-trained unimodal models with multimodal information injection for image-text multimodal classification","author":"Liang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0145","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"16795","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"256","article-title":"Distilling CLIP with dual guidance for learning discriminative human body shape representation","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133555_bib0155","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"6935","article-title":"Cross-domain image captioning with discriminative finetuning","author":"Dess\u00ec","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129752","article-title":"Few-shot medical relation extraction via prompt tuning enhanced pre-trained language model","volume":"633","author":"He","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133555_bib0165","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event, Vol. 139 of Proceedings of Machine Learning Research","first-page":"5583","article-title":"Vilt: vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.neucom.2026.133555_bib0170","series-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada","first-page":"13","article-title":"Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019"},{"key":"10.1016\/j.neucom.2026.133555_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12924","article-title":"Dept: decoupled prompt tuning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133555_bib0180","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"issue":"10","key":"10.1016\/j.neucom.2026.133555_bib0185","doi-asserted-by":"crossref","first-page":"9882","DOI":"10.1109\/TCSVT.2024.3405069","article-title":"Patchmixing masked autoencoders for 3D point cloud self-supervised learning","volume":"34","author":"Lin","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133555_bib0190","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15534","article-title":"Black box few-shot adaptation for vision-language models","author":"Ouali","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0195","series-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA, USA","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2026.133555_bib0200","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12104","article-title":"Scaling vision transformers","author":"Zhai","year":"2022"},{"issue":"5","key":"10.1016\/j.neucom.2026.133555_bib0205","doi-asserted-by":"crossref","first-page":"3192","DOI":"10.1109\/TCSVT.2023.3312858","article-title":"Transformer-based multimodal emotional perception for dynamic facial expression recognition in the wild","volume":"34","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133555_bib0210","author":"Li"},{"issue":"4","key":"10.1016\/j.neucom.2026.133555_bib0215","doi-asserted-by":"crossref","first-page":"2574","DOI":"10.1109\/TCSVT.2023.3303945","article-title":"Snp-s 3: shared network pre-training and significant semantic strengthening for various video-text tasks","volume":"34","author":"Dong","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133555_bib0220","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0225","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15638","article-title":"Flava: a foundational language and vision alignment model","author":"Singh","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0230","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event, Vol. 139 of Proceedings of Machine Learning Research","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neucom.2026.133555_bib0235","author":"Schuhmann"},{"key":"10.1016\/j.neucom.2026.133555_bib0240","first-page":"25278","article-title":"Laion-5b: an open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.neucom.2026.133555_bib0245","doi-asserted-by":"crossref","first-page":"1048","DOI":"10.1109\/TCSVT.2021.3073410","article-title":"Generalizable no-reference image quality assessment via deep meta-learning","volume":"32","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"9","key":"10.1016\/j.neucom.2026.133555_bib0250","doi-asserted-by":"crossref","first-page":"3153","DOI":"10.1109\/TCSVT.2019.2938038","article-title":"Visual tracking by structurally optimizing pre-trained CNN","volume":"30","author":"Liu","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133555_bib0255","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15659","article-title":"Prompt-aligned gradient for prompt tuning","author":"Zhu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129192","article-title":"Domain adaptation for textual adversarial defense via prompt-tuning","volume":"620","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133555_bib0265","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129008","article-title":"Soft prompt-tuning for unsupervised domain adaptation via self-supervision","volume":"617","author":"Zhu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133555_bib0270","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129082","article-title":"An enhanced few-shot text classification approach by integrating topic modeling and prompt-tuning","volume":"617","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133555_bib0275","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130316","article-title":"Relevance-aware prompt-tuning method for multimodal social entity and relation extraction","volume":"640","author":"Chen","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133555_bib0280","author":"Zang"},{"key":"10.1016\/j.neucom.2026.133555_bib0285","first-page":"3834","article-title":"Debiased fine-tuning for vision-language models by prompt regularization","author":"Zhu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0290","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2811","article-title":"Eco: ensembling context optimization for vision-language models","author":"Agnolucci","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0295","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022","first-page":"5196","article-title":"Prompt distribution learning","author":"Lu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0300","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22004","article-title":"Distribution-aware prompt tuning for vision-language models","author":"Cho","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0305","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15670","article-title":"Knowledge-aware prompt tuning for generalizable vision-language models","author":"Kan","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0310","series-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023","article-title":"PLOT: prompt learning with optimal transport for vision-language models","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0315","author":"Shen"},{"key":"10.1016\/j.neucom.2026.133555_bib0320","series-title":"Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXV, Vol. 13695 of Lecture Notes in Computer Science","first-page":"493","article-title":"Tip-adapter: training-free adaption of CLIP for few-shot classification","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0325","author":"Gao"},{"key":"10.1016\/j.neucom.2026.133555_bib0330","series-title":"European Conference on Computer Vision (ECCV)","article-title":"Efficient and versatile robust fine-tuning of zero-shot models","author":"Kim","year":"2024"},{"issue":"6","key":"10.1016\/j.neucom.2026.133555_bib0335","doi-asserted-by":"crossref","first-page":"5251","DOI":"10.1109\/TCSVT.2025.3529923","article-title":"Variational adapter: improving CLIP in data-imbalanced scenarios","volume":"35","author":"Lu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133555_bib0340","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neucom.2026.133555_bib0345","author":"Fujisawa"},{"key":"10.1016\/j.neucom.2026.133555_bib0350","series-title":"Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023","first-page":"4896","article-title":"Clip-hand3D: exploiting 3D hand pose estimation via context-aware prompting","author":"Guo","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0355","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"19606","article-title":"Winclip: zero-\/few-shot anomaly classification and segmentation","author":"Jeong","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0360","series-title":"IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22\u201329, 2017","first-page":"618","article-title":"Grad-cam: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"10.1016\/j.neucom.2026.133555_bib0365","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR Workshops 2020, Seattle, WA, USA, June 14\u201319, 2020","first-page":"111","article-title":"Score-cam: score-weighted visual explanations for convolutional neural networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133555_bib0370","series-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA, USA","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017"},{"key":"10.1016\/j.neucom.2026.133555_bib0375","series-title":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"1","key":"10.1016\/j.neucom.2026.133555_bib0380","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cviu.2005.09.012","article-title":"Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories","volume":"106","author":"Fei-Fei","year":"2007","journal-title":"Comput. Vis. Image Underst."},{"issue":"7","key":"10.1016\/j.neucom.2026.133555_bib0385","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"Eurosat: a novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.neucom.2026.133555_bib0390","series-title":"The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, 13\u201318 June 2010","first-page":"3485","article-title":"SUN database: large-scale scene recognition from abbey to zoo","author":"Xiao","year":"2010"},{"key":"10.1016\/j.neucom.2026.133555_bib0395","series-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, June 23\u201328, 2014","first-page":"3606","article-title":"Describing textures in the wild","author":"Cimpoi","year":"2014"},{"key":"10.1016\/j.neucom.2026.133555_bib0400","author":"Soomro"},{"key":"10.1016\/j.neucom.2026.133555_bib0410","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, June 16\u201321, 2012","first-page":"3498","article-title":"Cats and dogs","author":"Parkhi","year":"2012"},{"key":"10.1016\/j.neucom.2026.133555_bib0415","series-title":"2013 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2013, Sydney, Australia, December 1\u20138, 2013","first-page":"554","article-title":"3D object representations for fine-grained categorization","author":"Krause","year":"2013"},{"key":"10.1016\/j.neucom.2026.133555_bib0420","series-title":"Sixth Indian Conference on Computer Vision, Graphics & Image Processing, ICVGIP 2008, Bhubaneswar, India, 16\u201319 December 2008","first-page":"722","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"key":"10.1016\/j.neucom.2026.133555_bib0425","series-title":"Computer Vision - ECCV 2014 - 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part VI, Vol. 8694 of Lecture Notes in Computer Science","first-page":"446","article-title":"Food-101 - mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.neucom.2026.133555_bib0430","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023","first-page":"10899","article-title":"Task residual for tuning vision-language models","author":"Yu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133555_bib0435","series-title":"AAAI","first-page":"1528","article-title":"Weak distribution detectors lead to stronger generalizability of vision-language prompt tuning","author":"Ding","year":"2024"},{"key":"10.1016\/j.neucom.2026.133555_bib0440","author":"Li"},{"key":"10.1016\/j.neucom.2026.133555_bib0445","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","article-title":"Lora: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133555_bib0450","author":"Li"},{"key":"10.1016\/j.neucom.2026.133555_bib0455","author":"Zanella"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009525?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009525?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:20:10Z","timestamp":1777576810000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226009525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":90,"alternative-id":["S0925231226009525"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133555","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MoDe: Multi-modal discriminative priors for prompt tuning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133555","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133555"}}