{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:09:06Z","timestamp":1783008546303,"version":"3.54.5"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"2","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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach. Intell. Res."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11633-025-1575-z","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:35:44Z","timestamp":1775644544000},"page":"366-382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["CM-CLIP: Few-shot Cross-modal Generalization for Face Anti-spoofing via Prompt Learning"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0640-5671","authenticated-orcid":false,"given":"Hui","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7788-9368","authenticated-orcid":false,"given":"Ajian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8387-4245","authenticated-orcid":false,"given":"Xun","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-3513","authenticated-orcid":false,"given":"Hugo Jair","family":"Escalante","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9266-1783","authenticated-orcid":false,"given":"Isabelle","family":"Guyon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4735-2885","authenticated-orcid":false,"given":"Jun","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5780-8540","authenticated-orcid":false,"given":"Yanyan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"1575_CR1","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/CVPR.2019.00101","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Zhang","year":"2019","unstructured":"S. Zhang, X. Wang, A. Liu, C. Zhao, J. Wan, S. Escalera, H. Shi, Z. Wang, S. Z. Li. A dataset and benchmark for large-scale multi-modal face anti-spoofing. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 919\u2013928, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00101."},{"issue":"2","key":"1575_CR2","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/TBIOM.2020.2973001","volume":"2","author":"S Zhang","year":"2020","unstructured":"S. Zhang, A. Liu, J. Wan, Y. Liang, G. Guo, S. Escalera, H. J. Escalante, S. Z. Li. CASIA-SURF: A large-scale multi-modal benchmark for face anti-spoofing. IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 2, no. 2, pp. 182\u2013193, 2020. DOI: https:\/\/doi.org\/10.1109\/TBIOM.2020.2973001.","journal-title":"IEEE Transactions on Biometrics, Behavior, and Identity Science"},{"key":"1575_CR3","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/WACV48630.2021.00122","volume-title":"Proceedings of Winter Conference on Applications of Computer Vision","author":"A Liu","year":"2021","unstructured":"A. Liu, Z. Tan, J. Wan, S. Escalera, G. Guo, S. Z. Li. CASIA-SURF CeFA: A benchmark for multi-modal cross-ethnicity face anti-spoofing. In Proceedings of Winter Conference on Applications of Computer Vision, IEEE, Waikoloa, USA, pp. 1179\u20131187, 2021. DOI: https:\/\/doi.org\/10.1109\/WACV48630.2021.00122."},{"key":"1575_CR4","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/TIFS.2019.2916652","volume":"15","author":"A George","year":"2020","unstructured":"A. George, Z. Mostaani, D. Geissenbuhler, O. Nikisins, A. Anjos, S. Marcel. Biometric face presentation attack detection with multi-channel convolutional neural network. IEEE Transactions on Information Forensics and Security, vol. 15, pp. 42\u201355, 2020. DOI: https:\/\/doi.org\/10.1109\/TIFS.2019.2916652.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1575_CR5","doi-asserted-by":"publisher","first-page":"2759","DOI":"10.1109\/TIFS.2021.3065495","volume":"16","author":"A Liu","year":"2021","unstructured":"A. Liu, Z. Tan, J. Wan, Y. Liang, Z. Lei, G. Guo, S. Z. Li. Face anti-spoofing via adversarial cross-modality translation. IEEE Transactions on Information Forensics and Security, vol. 16, pp. 2759\u20132772, 2021. DOI: https:\/\/doi.org\/10.1109\/TIFS.2021.3065495.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1575_CR6","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1109\/CVPRW.2019.00202","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"A Liu","year":"2019","unstructured":"A. Liu, J. Wan, S. Escalera, H. J. Escalante, Z. Tan, Q. Yuan, K. Wang, C. Lin, G. Guo, I. Guyon, S. Z. Li. Multi-modal face anti-spoofing attack detection challenge at CVPR2019. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Long Beach, USA, pp. 1601\u20131610, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPRW.2019.00202."},{"issue":"1","key":"1575_CR7","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1049\/bme2.12002","volume":"10","author":"A Liu","year":"2021","unstructured":"A. Liu, X. Li, J. Wan, Y. Liang, S. Escalera, H. J. Escalante, M. Madadi, Y. Jin, Z. Wu, X. Yu, Z. Tan, Q. Yuan, R. Yang, B. Zhou, G. Guo, S. Z. Li. Cross-ethnicity face anti-spoofing recognition challenge: A review. IET Biometrics, vol. 10, no. 1, pp. 24\u201343, 2021. DOI: https:\/\/doi.org\/10.1049\/bme2.12002.","journal-title":"IET Biometrics"},{"key":"1575_CR8","first-page":"1180","volume-title":"Proceedings of the 31st International Joint Conference on Artificial Intelligence","author":"A Liu","year":"2022","unstructured":"A. Liu, Y. Liang. MA-ViT: Modality-agnostic vision transformers for face anti-spoofing. In Proceedings of the 31st International Joint Conference on Artificial Intelligence, Vienna, Austria, pp. 1180\u20131186, 2022."},{"key":"1575_CR9","doi-asserted-by":"publisher","first-page":"4775","DOI":"10.1109\/TIFS.2023.3296330","volume":"18","author":"A Liu","year":"2023","unstructured":"A. Liu, Z. Tan, Z. Yu, C. Zhao, J. Wan, Y. Liang, Z. Lei, D. Zhang, S. Z. Li, G. Guo. FM-ViT: Flexible modal vision transformers for face anti-spoofing. IEEE Transactions on Information Forensics and Security, vol. 18, pp. 4775\u20134786, 2023. DOI: https:\/\/doi.org\/10.1109\/TIFS.2023.3296330.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1575_CR10","doi-asserted-by":"publisher","first-page":"8228","DOI":"10.1145\/3664647.3680856","volume-title":"Proceedings of the 32nd International Conference on Multimedia","author":"A Liu","year":"2024","unstructured":"A. Liu, H. Ma, J. Zheng, H. Yuan, X. Yu, Y. Liang, S. Escalera, J. Wan, Z. Lei. FM-CLIP: Flexible modal CLIP for face anti-spoofing. In Proceedings of the 32nd International Conference on Multimedia, ACM, Melbourne, Australia, pp. 8228\u20138237, 2024. DOI: https:\/\/doi.org\/10.1145\/3664647.3680856."},{"key":"1575_CR11","doi-asserted-by":"publisher","first-page":"24563","DOI":"10.1109\/CVPR52729.2023.02353","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Sun","year":"2023","unstructured":"Y. Sun, Y. Liu, X. Liu, Y. Li, W. S. Chu. Rethinking domain generalization for face anti-spoofing: Separability and alignment. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, Canada, pp. 24563\u201324574, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.02353."},{"key":"1575_CR12","doi-asserted-by":"publisher","first-page":"20453","DOI":"10.1109\/CVPR52729.2023.01959","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Q Zhou","year":"2023","unstructured":"Q. Zhou, K. Y. Zhang, T. Yao, X. Lu, R. Yi, S. Ding, L. Ma. Instance-aware domain generalization for face anti-spoofing. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, Canada, pp. 20453\u201320463, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.01959."},{"key":"1575_CR13","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-031-19778-9_3","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"H P Huang","year":"2022","unstructured":"H. P. Huang, D. Sun, Y. Liu, W. S. Chu, T. Xiao, J. Yuan, H. Adam, M. H. Yang. Adaptive transformers for robust few-shot cross-domain face anti-spoofing. In Proceedings of the 17th European Conference on Computer Vision, Springer, Tel Aviv, Israel, pp. 37\u201354, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-19778-9_3."},{"key":"1575_CR14","doi-asserted-by":"publisher","first-page":"19685","DOI":"10.1109\/ICCV51070.2023.01803","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"K Srivatsan","year":"2023","unstructured":"K. Srivatsan, M. Naseer, K. Nandakumar. FLIP: Cross-domain face anti-spoofing with language guidance. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Paris, France, pp. 19685\u201319696, 2023. DOI: https:\/\/doi.org\/10.1109\/ICCV51070.2023.01803."},{"issue":"11","key":"1575_CR15","doi-asserted-by":"publisher","first-page":"5439","DOI":"10.1007\/s11263-024-02135-2","volume":"132","author":"A Liu","year":"2024","unstructured":"A. Liu. CA-MoEiT: Generalizable face anti-spoofing via dual cross-attention and semi-fixed mixture-of-expert. International Journal of Computer Vision, vol. 132, no. 11, pp. 5439\u20135452, 2024. DOI: https:\/\/doi.org\/10.1007\/s11263-024-02135-2.","journal-title":"International Journal of Computer Vision"},{"key":"1575_CR16","volume-title":"Domain generalization for face anti-spoofing via content-aware composite prompt engineering","author":"J Guo","year":"2025","unstructured":"J. Guo, A. Liu, Y. Diao, J. Zhang, H. Ma, B. Zhao, R. Hong, M. Wang. Domain generalization for face anti-spoofing via content-aware composite prompt engineering, [Online], Available: https:\/\/arxiv.org\/abs\/2504.04470, 2025."},{"key":"1575_CR17","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"A Radford","year":"2021","unstructured":"A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, I. Sutskever. Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763, 2021."},{"issue":"9","key":"1575_CR18","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"K. Zhou, J. Yang, C. C. Loy, Z. Liu. Learning to prompt for vision-language models. International Journal of Computer Vision, vol. 130, no. 9, pp. 2337\u20132348, 2022. DOI: https:\/\/doi.org\/10.1007\/s11263-022-01653-1.","journal-title":"International Journal of Computer Vision"},{"key":"1575_CR19","doi-asserted-by":"publisher","first-page":"16795","DOI":"10.1109\/CVPR52688.2022.01631","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K Zhou","year":"2022","unstructured":"K. Zhou, J. Yang, C. C. Loy, Z. Liu. Conditional prompt learning for vision-language models. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 16795\u201316804, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01631."},{"key":"1575_CR20","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1109\/CVPR52733.2024.00029","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Liu","year":"2024","unstructured":"A. Liu, S. Xue, J. Gan, J. Wan, Y. Liang, J. Deng, S. Escalera, Z. Lei. CFPL-FAS: Class free prompt learning for generalizable face anti-spoofing. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 222\u2013232, 2024. DOI: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00029."},{"key":"1575_CR21","doi-asserted-by":"publisher","first-page":"5294","DOI":"10.1109\/CVPR42600.2020.00534","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Yu","year":"2020","unstructured":"Z. Yu, C. Zhao, Z. Wang, Y. Qin, Z. Su, X. Li, F. Zhou, G. Zhao. Searching central difference convolutional networks for face anti-spoofing. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 5294\u20135304, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00534."},{"key":"1575_CR22","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/978-3-031-19775-8_30","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"Y Liu","year":"2022","unstructured":"Y. Liu, Y. Chen, W. Dai, M. Gou, C. T. Huang, H. Xiong. Source-free domain adaptation with contrastive domain alignment and self-supervised exploration for face anti-spoofing. In Proceedings of the 17th European Conference on Computer Vision, Springer, Tel Aviv, Israel, pp. 511\u2013528, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-19775-8_30."},{"key":"1575_CR23","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1007\/978-3-031-19778-9_14","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"X Guo","year":"2022","unstructured":"X. Guo, Y. Liu, A. Jain, X. Liu. Multi-domain learning for updating face anti-spoofing models. In Proceedings of the 17th European Conference on Computer Vision, Springer, Tel Aviv, Israel, pp. 230\u2013249, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-19778-9_14."},{"key":"1575_CR24","doi-asserted-by":"publisher","first-page":"10071","DOI":"10.1109\/TIFS.2024.3486098","volume":"19","author":"Y He","year":"2024","unstructured":"Y. He, F. Peng, R. Cai, Z. Yu, M. Long, K. Y. Lam. Category-conditional gradient alignment for domain adaptive face anti-spoofing. IEEE Transactions on Information Forensics and Security, vol. 19, pp. 10071\u201310085, 2024. DOI: https:\/\/doi.org\/10.1109\/TIFS.2024.3486098.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1575_CR25","doi-asserted-by":"publisher","unstructured":"Y. Cui, J. Zhao, Z. Yu, R. Cai, X. Wang, L. Jin, A. C. Kot, L. Liu, X. Li. CMoA: Contrastive mixture of adapters for generalized few-shot continual learning. IEEE Transactions on Multimedia, vol. 27, pp. 5533\u20135547. DOI: https:\/\/doi.org\/10.1109\/TMM.2025.3543038.","DOI":"10.1109\/TMM.2025.3543038"},{"key":"1575_CR26","doi-asserted-by":"publisher","unstructured":"N. Li, A. Liu, Z. Zhu, X. Lin, H. Ma, H. N. Dai, Y. Liang. Knowledge distillation-based anomaly detection via adaptive discrepancy optimization. IEEE Transactions on Industrial Informatics, vol. 21, no. 9, pp. 7176\u20137187. DOI: https:\/\/doi.org\/10.1109\/TII.2025.3574540.","DOI":"10.1109\/TII.2025.3574540"},{"key":"1575_CR27","doi-asserted-by":"publisher","first-page":"5499","DOI":"10.1609\/aaai.v38i6.28359","volume-title":"Proceedings of the 38th Conference on Artificial Intelligence","author":"K Wang","year":"2024","unstructured":"K. Wang, G. Zhang, H. Yue, A. Liu, G. Zhang, H. Feng, J. Han, E. Ding, J. Wang. Multi-domain incremental learning for face presentation attack detection. In Proceedings of the 38th Conference on Artificial Intelligence, Vancouver, Canada, pp. 5499\u20135507, 2024. DOI: https:\/\/doi.org\/10.1609\/aaai.v38i6.28359."},{"key":"1575_CR28","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1109\/CVPRW63382.2024.00105","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"X He","year":"2024","unstructured":"X. He, D. Liang, S. Yang, Z. Hao, H. Ma, B. Mao, X. Li, Y. Wang, P. Yan, A. Liu. Joint physical-digital facial attack detection via simulating spoofing clues. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Seattle, USA, pp. 995\u20131004, 2024. DOI: https:\/\/doi.org\/10.1109\/CVPRW63382.2024.00105."},{"key":"1575_CR29","first-page":"105","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Guo","year":"2025","unstructured":"X. Guo, X. Song, Y. Zhang, X. Liu, X. Liu. Rethinking vision-language model in face forensics: Multi-modal interpretable forged face detector. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, pp. 105\u2013116, 2025."},{"key":"1575_CR30","volume-title":"Fa3-CLIP: Frequency-aware cues fusion and attack-agnostic prompt learning for unified face attack detection","author":"Y Li","year":"2025","unstructured":"Y. Li, N. Li, A. Liu, H. Ma, L. Yang, X. Chen, Z. Liang, Y. Liang, J. Wan, Z. Lei. Fa3-CLIP: Frequency-aware cues fusion and attack-agnostic prompt learning for unified face attack detection, [Online], Available: https:\/\/arxiv.org\/abs\/2504.00454, 2025."},{"key":"1575_CR31","volume-title":"Benchmarking unified face attack detection via hierarchical prompt tuning","author":"A Liu","year":"2025","unstructured":"A. Liu, H. Yuan, X. Guo, H. Ma, W. Zhuang, C. Miao, Y. Hong, C. Song, J. Lan, Q. Chu, T. Gong, Y. Liang, W. Wang, J. Wan, X. Liu, Z. Lei. Benchmarking unified face attack detection via hierarchical prompt tuning, [Online], Available: https:\/\/arxiv.org\/abs\/2505.13327, 2025."},{"key":"1575_CR32","doi-asserted-by":"publisher","first-page":"20597","DOI":"10.1109\/ICCV51070.2023.01888","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Y Liu","year":"2023","unstructured":"Y. Liu, Y. Chen, M. Gou, C. T. Huang, Y. Wang, W. Dai, H. Xiong. Towards unsupervised domain generalization for face anti-spoofing. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Paris, France, pp. 20597\u201320607, 2023. DOI: https:\/\/doi.org\/10.1109\/ICCV51070.2023.01888."},{"key":"1575_CR33","doi-asserted-by":"publisher","first-page":"2497","DOI":"10.1109\/TIFS.2022.3188149","volume":"17","author":"A Liu","year":"2022","unstructured":"A. Liu, C. Zhao, Z. Yu, J. Wan, A. Su, X. Liu, Z. Tan, S. Escalera, J. Xing, Y. Liang, G. Guo, Z. Lei, S. Z. Li, D. Zhang. Contrastive context-aware learning for 3D high-fidelity mask face presentation attack detection. IEEE Transactions on Information Forensics and Security, vol. 17, pp. 2497\u20132507, 2022. DOI: https:\/\/doi.org\/10.1109\/TIFS.2022.3188149.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1575_CR34","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1109\/CVPRW50498.2020.00333","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"Z Yu","year":"2020","unstructured":"Z. Yu, Y. Qin, X. Li, Z. Wang, C. Zhao, Z. Lei, G. Zhao. Multi-modal face anti-spoofing based on central difference networks. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Seattle, USA, pp. 650\u2013651, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00333."},{"issue":"4","key":"1575_CR35","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/s11633-024-1511-7","volume":"22","author":"Y Jiang","year":"2025","unstructured":"Y. Jiang, Y. Lyu, B. Peng, W. Wang, J. Dong. CMSL: Cross-modal style learning for few-shot image generation. Machine Intelligence Research, vol. 22, no. 4, pp. 752\u2013768, 2025. DOI: https:\/\/doi.org\/10.1007\/S11633-024-1511-7.","journal-title":"Machine Intelligence Research"},{"issue":"1","key":"1575_CR36","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/s11633-023-1442-8","volume":"21","author":"N Luo","year":"2024","unstructured":"N. Luo, W. Shi, Z. Yang, M. Song, T. Jiang. Multimodal fusion of brain imaging data: Methods and applications. Machine Intelligence Research, vol. 21, no. 1, pp. 136\u2013152, 2024. DOI: https:\/\/doi.org\/10.1007\/s11633-023-1442-8.","journal-title":"Machine Intelligence Research"},{"issue":"4","key":"1575_CR37","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1007\/s11633-022-1386-4","volume":"20","author":"H Lu","year":"2023","unstructured":"H. Lu, Y. Huo, M. Ding, N. Fei, Z. Lu. Cross-modal contrastive learning for generalizable and efficient imagetext retrieval. Machine Intelligence Research, vol. 20, no. 4, pp. 569\u2013582, 2023. DOI: https:\/\/doi.org\/10.1007\/s11633-022-1386-4.","journal-title":"Machine Intelligence Research"},{"key":"1575_CR38","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-031-72670-56","volume-title":"Proceedings of the 18th European Conference on Computer Vision","author":"G Zheng","year":"2025","unstructured":"G. Zheng, Y. Liu, W. Dai, C. Li, J. Zou, H. Xiong. Towards unified representation of invariant-specific features in missing modality face anti-spoofing. In Proceedings of the 18th European Conference on Computer Vision, Springer, Milan, Italy, pp. 93\u2013110, 2025. DOI: https:\/\/doi.org\/10.1007\/978-3-031-72670-56."},{"key":"1575_CR39","doi-asserted-by":"publisher","unstructured":"X. Xie, Y. Cui, T. Tan, X. Zheng, Z. Yu. FusionMamba: Dynamic feature enhancement for multimodal image fusion with Mamba. Visual Intelligence, vol. 2, no. 1, Article number 37, 2024. DOI: https:\/\/doi.org\/10.1007\/s44267-024-00072-9.","DOI":"10.1007\/s44267-024-00072-9"},{"key":"1575_CR40","doi-asserted-by":"publisher","first-page":"3045","DOI":"10.18653\/v1\/2021.emnlp-main.243","volume-title":"Proceedings of Conference on Empirical Methods in Natural Language Processing","author":"B Lester","year":"2021","unstructured":"B. Lester, R. Al-Rfou, N. Constant. The power of scale for parameter-efficient prompt tuning. In Proceedings of Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, pp. 3045\u20133059, 2021. DOI: https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.243."},{"key":"1575_CR41","doi-asserted-by":"publisher","first-page":"4582","DOI":"10.18653\/v1\/2021.acl-long.353","volume-title":"Proceedings of the 599th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","author":"X L Li","year":"2021","unstructured":"X. L. Li, P. Liang. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 599th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 4582\u20134597, 2021. DOI: https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.353."},{"key":"1575_CR42","volume-title":"Exploring visual prompts for adapting large-scale models","author":"H Bahng","year":"2022","unstructured":"H. Bahng, A. Jahanian, S. Sankaranarayanan, P. Isola. Exploring visual prompts for adapting large-scale models, [Online], Available: https:\/\/arxiv.org\/abs\/2203.17274, 2022."},{"key":"1575_CR43","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"M Jia","year":"2022","unstructured":"M. Jia, L. Tang, B. C. Chen, C. Cardie, S. Belongie, B. Hariharan, S. N. Lim. Visual prompt tuning. In Proceedings of the 17th European Conference on Computer Vision, Springer, Tel Aviv, Israel, pp. 709\u2013727, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41."},{"key":"1575_CR44","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1007\/978-3-031-19809-0_36","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"Z Wang","year":"2022","unstructured":"Z. Wang, Z. Zhang, S. Ebrahimi, R. Sun, H. Zhang, C. Y. Lee, X. Ren, G. Su, V. Perot, J. Dy, T. Pfister. DualPrompt: Complementary prompting for rehearsal-free continual learning. In Proceedings of the 17th European Conference on Computer Vision, Springer, Tel Aviv, Israel, pp. 631\u2013648, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-19809-0_36."},{"key":"1575_CR45","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/CVPR52688.2022.00024","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Wang","year":"2022","unstructured":"Z. Wang, Z. Zhang, C. Y. Lee, H. Zhang, R. Sun, X. Ren, G. Su, V. Perot, J. Dy, T. Pfister. Learning to prompt for continual learning. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 139\u2013149, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00024."},{"issue":"1","key":"1575_CR46","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11633-023-1470-4","volume":"22","author":"X Zheng","year":"2025","unstructured":"X. Zheng, F. Che, J. Tao. A comprehensive survey of few-shot information networks. Machine Intelligence Research, vol. 22, no. 1, pp. 60\u201378, 2025. DOI: https:\/\/doi.org\/10.1007\/s11633-023-1470-4.","journal-title":"Machine Intelligence Research"},{"key":"1575_CR47","doi-asserted-by":"publisher","first-page":"19113","DOI":"10.1109\/CVPR52729.2023.01832","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"M U Khattak","year":"2023","unstructured":"M. U. Khattak, H. Rasheed, M. Maaz, S. Khan, F. S. Khan. MaPLe: Multi-modal prompt learning. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, Canada, pp. 19113\u201319122, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.01832."},{"key":"1575_CR48","doi-asserted-by":"publisher","first-page":"2976","DOI":"10.18653\/v1\/2022.findings-acl.234","volume-title":"Proceedings of Findings of the Association for Computational Linguistics","author":"S Liang","year":"2022","unstructured":"S. Liang, M. Zhao, H. Sch\u00fctze. Modular and parameter-efficient multimodal fusion with prompting. In Proceedings of Findings of the Association for Computational Linguistics, Dublin, Ireland, pp. 2976\u20132985, 2022. DOI: https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.234."},{"key":"1575_CR49","doi-asserted-by":"publisher","first-page":"18177","DOI":"10.1109\/CVPR52688.2022.01764","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"M Ma","year":"2022","unstructured":"M. Ma, J. Ren, L. Zhao, D. Testuggine, X. Peng. Are multimodal transformers robust to missing modality? In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, New Orleans, USA, pp. 18177\u201318186, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01764."},{"key":"1575_CR50","doi-asserted-by":"publisher","first-page":"6757","DOI":"10.1109\/CVPR52729.2023.00653","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"H Yao","year":"2023","unstructured":"H. Yao, R. Zhang, C. Xu. Visual-language prompt tuning with knowledge-guided context optimization. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, Canada, pp. 6757\u20136767, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.00653."},{"key":"1575_CR51","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"A Dosovitskiy","year":"2021","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of the 9th International Conference on Learning Representations, Austria, 2021."},{"key":"1575_CR52","doi-asserted-by":"publisher","first-page":"202","DOI":"10.3233\/FAIA240489","volume-title":"Proceedings of the 27th European Conference on Artificial Intelligence","author":"S Jie","year":"2024","unstructured":"S. Jie, Z. H. Deng, S. Chen, Z. Jin. Convolutional bypasses are better vision transformer adapters. In Proceedings of the 27th European Conference on Artificial Intelligence, IOS Press, Santiago de Compostela, Spain, pp. 202\u2013209, 2024. DOI: https:\/\/doi.org\/10.3233\/FAIA240489."},{"key":"1575_CR53","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1109\/IC-CV48922.2021.00045","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"H Chefer","year":"2021","unstructured":"H. Chefer, S. Gur, L. Wolf. Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In Proceedings of IEEE\/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 397\u2013406, 2021. DOI: https:\/\/doi.org\/10.1109\/IC-CV48922.2021.00045."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1575-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-025-1575-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1575-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T12:03:24Z","timestamp":1775649804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-025-1575-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["1575"],"URL":"https:\/\/doi.org\/10.1007\/s11633-025-1575-z","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"21 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}