{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T06:41:36Z","timestamp":1776494496998,"version":"3.51.2"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62431017"],"award-info":[{"award-number":["62431017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11263-025-02690-2","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T17:33:35Z","timestamp":1773077615000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Language Efficient Tuning for Mitigating Catastrophic Forgetting in Multi-Modal Learning"],"prefix":"10.1007","volume":"134","author":[{"given":"Yaoming","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-5778","authenticated-orcid":false,"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junni","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"key":"2690_CR1","doi-asserted-by":"crossref","unstructured":"Ben\u00a0Zaken, E., Goldberg, Y., & Ravfogel, S. (2022). BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Proceedings of the 60th annual meeting of the association for computational linguistics, ACL, pp 1\u20139.","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"2690_CR2","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Gool, L. V. (2014). Food-101\u2013mining discriminative components with random forests. In: 13th European conference on computer vision, Springer pp 446\u2013461.","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"2690_CR3","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., & Amodei, D. (2020). Language models are few-shot learners. In: Advances in neural information processing systems 33, Curran Associates, Inc., pp 1877\u20131901"},{"issue":"4","key":"2690_CR4","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1007\/s11263-023-01904-9","volume":"132","author":"A Bulat","year":"2024","unstructured":"Bulat, A., & Tzimiropoulos, G. (2024). Language-aware soft prompting: Text-to-text optimization for few-and zero-shot adaptation of V & L models. International Journal of Computer Vision,132(4), 1108\u20131125.","journal-title":"International Journal of Computer Vision"},{"key":"2690_CR5","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao. Y., & Zhang, K. (2023). Plot: Prompt learning with optimal transport for vision-language models. In: The eleventh international conference on learning representations (ICLR)."},{"key":"2690_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Ge, C., Tong, Z., Wang, J., Song, Y., Wang, J., & Luo, P. (2022). AdaptFormer: Adapting vision transformers for scalable visual recognition. In: Advances in neural information processing systems 35, Curran Associates, Inc., pp 16664\u201316678.","DOI":"10.52202\/068431-1212"},{"key":"2690_CR7","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014). Describing textures in the wild. In: 2014 IEEE conference on computer vision and pattern recognition, IEEE, pp 3606\u20133613.","DOI":"10.1109\/CVPR.2014.461"},{"key":"2690_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE, pp 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2690_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In: The ninth international conference on learning representations (ICLR)."},{"key":"2690_CR10","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. In: 2004 conference on computer vision and pattern recognition workshop, IEEE, pp 178\u2013178.","DOI":"10.1109\/CVPR.2004.383"},{"issue":"2","key":"2690_CR11","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., & Qiao, Y. (2024). CLIP-Adapter: Better vision-language models with feature adapters. International Journal of Computer Vision,132(2), 581\u2013595.","journal-title":"International Journal of Computer Vision"},{"key":"2690_CR12","doi-asserted-by":"crossref","unstructured":"Gebru, T., Krause, J., Wang, Y., Chen, D., Deng, J., & Fei-Fei, L. (2017). Fine-grained car detection for visual census estimation. In: Proceedings of the 31st AAAI conference on artificial intelligence, AAAI Press, pp 4502\u20134508.","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"2690_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7","key":"2690_CR14","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., & Borth, D. (2019). EuroSat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,12(7), 2217\u20132226.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"2690_CR15","unstructured":"Houlsby N, Giurgiu A, Jastrzebski S, Morrone B, De\u00a0Laroussilhe Q, Gesmundo A, Attariyan M, Gelly S (2019) Parameter-efficient transfer learning for NLP. In: Proceedings of the 36th International Conference on Machine Learning, PMLR, pp 2790\u20132799"},{"key":"2690_CR16","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2022) LoRA: Low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations (ICLR)"},{"key":"2690_CR17","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B. C., Cardie, C., Belongie, S., Hariharan, B., & Lim, S. N. (2022). Visual prompt tuning. In: 17th european conference on computer vision, Springer, pp 709\u2013727.","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"2690_CR18","doi-asserted-by":"crossref","unstructured":"Jie, S., Deng, Z. H., Chen, S., & Jin, Z. (2024). Convolutional bypasses are better vision transformer adapters. In: 27th european conference on artificial intelligence, IOP Press, pp 202\u2013209.","DOI":"10.3233\/FAIA240489"},{"key":"2690_CR19","unstructured":"Karimi\u00a0Mahabadi, R., Henderson, J., & Ruder, S. (2021). Compacter: Efficient low-rank hypercomplex adapter layers. In: Advances in neural information processing systems 34, Curran Associates, Inc., pp 1022\u20131035."},{"key":"2690_CR20","doi-asserted-by":"crossref","unstructured":"Khattak, M. U., Rasheed, H., Maaz, M., Khan, S., & Khan, F. S. (2023). MaPLe: Multi-modal prompt learning. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), IEEE, pp 19113\u201319122.","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"2690_CR21","doi-asserted-by":"crossref","unstructured":"Khattak, M. U., Wasim, S. T., Naseer, M., Khan, S., Yang, M. H., & Khan, F. S. (2023). Self-regulating prompts: Foundational model adaptation without forgetting. In: 2023 IEEE\/CVF international conference on computer vision (ICCV), IEEE, pp 15190\u201315200.","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"2690_CR22","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., & Constant, N. (2021). The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 conference on empirical methods in natural language processing, ACL, pp 3045\u20133059.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"2690_CR23","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., & Hoi, S. C. H. (2021). Align before fuse: Vision and language representation learning with momentum distillation. In: Advances in neural information processing systems 34, Curran Associates, Inc., pp 9694\u20139705."},{"key":"2690_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., He, X., Wei, L., Qian, L., Zhu, L., Xie, L., Zhuang, Y., Tian, Q., & Tang, S. (2022). Fine-grained semantically aligned vision-language pre-training. In: Advances in neural information processing systems 35, Curran Associates, Inc., pp 7290\u20137303.","DOI":"10.52202\/068431-0529"},{"key":"2690_CR25","unstructured":"Li, J., Li, D., Xiong, C., & Hoi, S. (2022). BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the 39th international conference on machine learning, PMLR, pp 12888\u201312900."},{"key":"2690_CR26","doi-asserted-by":"crossref","unstructured":"Li, X. L., & Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, ACL, pp 4582\u20134597.","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"2690_CR27","unstructured":"Liu, W., Wen, Y., Yu, Z., & Yang, M. (2016). Large-margin softmax loss for convolutional neural networks. arXiv preprint arXiv:1612.02295."},{"key":"2690_CR28","doi-asserted-by":"crossref","unstructured":"Liu, W., Lin, R., Liu, Z., Rehg, J. M., Paull, L., Xiong, L., Song, L., & Weller, A. (2021). Orthogonal over-parameterized training. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), IEEE, pp 7251\u20137260.","DOI":"10.1109\/CVPR46437.2021.00717"},{"key":"2690_CR29","unstructured":"Long, S., Zhao, Z., Yuan, J., Tan, Z., Liu, J., Feng, J., Wang, S., & Wang, J. (2024). Mutual prompt learning for vision language models. International Journal of Computer Vision pp 1\u201319."},{"key":"2690_CR30","unstructured":"Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In: The seventh international conference on learning representations (ICLR)."},{"key":"2690_CR31","doi-asserted-by":"crossref","unstructured":"Mahabadi, R. K., Ruder, S., Dehghani, M., & Henderson, J. (2021). Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, ACL, pp 565\u2013576.","DOI":"10.18653\/v1\/2021.acl-long.47"},{"key":"2690_CR32","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151."},{"key":"2690_CR33","doi-asserted-by":"crossref","unstructured":"Nilsback, M. E., & Zisserman, A. (2006). A visual vocabulary for flower classification. In: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201906), IEEE, pp 1447\u20131454.","DOI":"10.1109\/CVPR.2006.42"},{"key":"2690_CR34","unstructured":"OpenAI. (2023). GPT-4 technical report. arXiv preprint arXiv:2303.08774."},{"key":"2690_CR35","doi-asserted-by":"crossref","unstructured":"Parkhi, O. M., Vedaldi, A., Zisserman, A., & Jawahar, C. (2012). Cats and dogs. In: 2012 IEEE conference on computer vision and pattern recognition, IEEE, pp 3498\u20133505.","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"2690_CR36","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Liu, W., Feng, H., Xue, Y., Feng, Y., Liu, Z., Zhang, D., Weller, A., & Sch\u00f6lkopf, B. (2023). Controlling text-to-image diffusion by orthogonal finetuning. In: Advances in neural information processing systems 36, Curran Associates, Inc., pp 79320\u201379362.","DOI":"10.52202\/075280-3472"},{"key":"2690_CR37","unstructured":", Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J. et al. (2021). Learning transferable visual models from natural language supervision. In: Proceedings of the 38th international conference on machine learning, PMLR, pp 8748\u20138763."},{"key":"2690_CR38","unstructured":"Soomro, K., Zamir, A.R., & Shah, M. (2012). UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402."},{"key":"2690_CR39","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y. (2023). EVA-CLIP: Improved training techniques for CLIP at scale. arXiv preprint arXiv:2303.15389."},{"key":"2690_CR40","unstructured":"Sung, Y. L., Nair, V., & Raffel, C. A. (2021). Training neural networks with fixed sparse masks. In: Advances in neural information processing systems 34, Curran Associates, Inc., pp 24193\u201324205."},{"key":"2690_CR41","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M. A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., & Lample, G. (2023). LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"2690_CR42","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In: Advances in neural information processing systems 30, Curran Associates, Inc., pp 5998\u20136008."},{"key":"2690_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, Y., Zhang, X., Li, J., Shi, B., Li, C., Dai, W., Xiong, H., & Tian, Q. (2023). VioLET: Vision-language efficient tuning with collaborative multi-modal gradients. In: Proceedings of the 31st ACM international conference on multimedia, ACM, pp 4595\u20134605.","DOI":"10.1145\/3581783.3611706"},{"key":"2690_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shi, B., Zhang, X., Li, J., Liu, Y., Dai, W., Li, C., Xiong, H., & Tian, Q. (2023). Adapting shortcut with normalizing flow: An efficient tuning framework for visual recognition. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), IEEE, pp 15965\u201315974.","DOI":"10.1109\/CVPR52729.2023.01532"},{"key":"2690_CR45","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K. A., Oliva, A., & Torralba, A. (2010). SUN database: Large-scale scene recognition from abbey to zoo. In: 2010 IEEE computer society conference on computer vision and pattern recognition, IEEE, pp 3485\u20133492.","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"2690_CR46","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s11263-024-02172-x","volume":"133","author":"C Xu","year":"2025","unstructured":"Xu, C., Zhu, Y., Shen, H., Chen, B., Liao, Y., Chen, X., & Wang, L. (2025). Progressive visual prompt learning with contrastive feature re-formation. International Journal of Computer Vision,133, 511\u2013526.","journal-title":"International Journal of Computer Vision"},{"key":"2690_CR47","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., & Xu, C. (2023). Visual-language prompt tuning with knowledge-guided context optimization. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), IEEE, pp 6757\u20136767.","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"2690_CR48","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., & Finn, C. (2020). Gradient surgery for multi-task learning. In: Advances in neural information processing systems 33, Curran Associates, Inc., pp 5824\u20135836."},{"key":"2690_CR49","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., & Loy, C. C. (2022). Unified vision and language prompt learning. arXiv preprint arXiv:2210.07225."},{"key":"2690_CR50","unstructured":"Zhang, R., Han, J., Liu, C., Gao, P., Zhou, A., Hu, X., Yan, S., Lu, P., Li, H., & Qiao, Y. (2023). LLaMA-Adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199."},{"key":"2690_CR51","unstructured":"Zhang, Y., Zhou, K., & Liu, Z. (2024). Neural prompt search. IEEE transactions on pattern analysis and machine intelligence early access"},{"key":"2690_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Conditional prompt learning for vision-language models. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), IEEE, pp 16816\u201316825.","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"2690_CR53","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision,130(9), 2337\u20132348.","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02690-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02690-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02690-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:46:34Z","timestamp":1776491194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02690-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":53,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2690"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02690-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]},"assertion":[{"value":"13 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"182"}}