{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T13:07:28Z","timestamp":1775653648465,"version":"3.50.1"},"reference-count":58,"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\/s11633-025-1618-5","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:35:42Z","timestamp":1775644542000},"page":"429-443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IKA2: Internal Knowledge Adaptive Activation for Robust Recognition in Complex Scenarios"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7756-8233","authenticated-orcid":false,"given":"Shuo","family":"Ye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lixin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiaoqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0556-9605","authenticated-orcid":false,"given":"Chaomeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shutao","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"1618_CR1","doi-asserted-by":"publisher","unstructured":"Y. Su, P. Yan, J. Lin, C. Wen, Y. Fan. Few-shot defect recognition for the multi-domain industry via attention embedding and fine-grained feature enhancement. Knowledge-Based Systems, vol. 284, Article number 111265, 2024. DOI: https:\/\/doi.org\/10.1016\/j.knosys.2023.111265.","DOI":"10.1016\/j.knosys.2023.111265"},{"key":"1618_CR2","doi-asserted-by":"publisher","unstructured":"S. Lei, X. Xiao, T. Zhang, H. C. Li, Z. Shi, Q. Zhu. Exploring fine-grained image-text alignment for referring remote sensing image segmentation. IEEE Transactions on Geoscience and Remote Sensing, vol. 63, Article number 5604611, 2025. DOI: https:\/\/doi.org\/10.1109\/TGRS.2024.3522293.","DOI":"10.1109\/TGRS.2024.3522293"},{"issue":"5","key":"1618_CR3","doi-asserted-by":"publisher","first-page":"3587","DOI":"10.1109\/JBHI.2025.3528196","volume":"29","author":"X Liang","year":"2025","unstructured":"X. Liang, X. Li, F. Li, J. Jiang, Q. Dong, W. Wang, K. Wang, S. Dong, G. Luo, S. Li. MedFILIP: Medical finegrained language-image pre-training. IEEE Journal of Biomedical and Health Informatics, vol. 29, no. 5, pp. 3587\u20133597, 2025. DOI: https:\/\/doi.org\/10.1109\/JBHI.2025.3528196.","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"1618_CR4","doi-asserted-by":"publisher","unstructured":"Y. Zhu, J. Xie, M. Liu, L. Yao, Y. Chen. BF3D: Bi-directional fusion 3D detector with semantic sampling and geometric mapping. Image and Vision Computing, vol. 139, Article number 104835, 2023. DOI: https:\/\/doi.org\/10.1016\/j.imavis.2023.104835.","DOI":"10.1016\/j.imavis.2023.104835"},{"key":"1618_CR5","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1007\/978-3-031-20047-2_39","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"C Wong","year":"2022","unstructured":"C. Wong, B. Xia, Z. Hong, Q. Peng, W. Yuan, Q. Cao, Y. Yang, X. You. View vertically: A hierarchical network for trajectory prediction via Fourier spectrums. In Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel, pp. 682\u2013700, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-20047-2_39."},{"key":"1618_CR6","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-981-99-8565-4_18","volume-title":"Proceedings of the 17th Chinese Conference on Biometric Recognition","author":"Y Lai","year":"2023","unstructured":"Y. Lai, Z. Luo, Z. Yu. Detect any deepfakes: Segment anything meets face forgery detection and localization. In Proceedings of the 17th Chinese Conference on Biometric Recognition, Xuzhou, China, pp. 180\u2013190, 2023. DOI: https:\/\/doi.org\/10.1007\/978-981-99-8565-4_18."},{"key":"1618_CR7","doi-asserted-by":"publisher","first-page":"2335","DOI":"10.1109\/ICASSP48485.2024.10447889","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Y Lai","year":"2024","unstructured":"Y. Lai, G. Yang, Y. He, Z. Luo, S. Li. Selective domaininvariant feature for generalizable deepfake detection. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Republic of Korea, pp. 2335\u20132339, 2024. DOI: https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447889."},{"issue":"12","key":"1618_CR8","doi-asserted-by":"publisher","first-page":"11348","DOI":"10.1109\/TPAMI.2025.3601053","volume":"47","author":"R Cai","year":"2025","unstructured":"R. Cai, Y. Cui, Z. Yu, X. Lin, C. Chen, A. Kot. Rehearsal-free and efficient continual learning for cross-domain face anti-spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 12, pp. 11348\u201311365, 2025. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2025.3601053.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"1618_CR9","doi-asserted-by":"publisher","first-page":"7608","DOI":"10.1109\/TPAMI.2025.3573785","volume":"47","author":"X Lin","year":"2025","unstructured":"X. Lin, A. Liu, Z. Yu, R. Cai, S. Wang, Y. Yu, J. Wan, Z. Lei, X. Cao, A. Kot. Reliable and balanced transfer learning for generalized multimodal face anti-spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 9, pp. 7608\u20137625, 2025. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2025.3573785.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"1618_CR10","doi-asserted-by":"publisher","first-page":"5092","DOI":"10.1109\/TNNLS.2022.3202534","volume":"35","author":"S Ye","year":"2024","unstructured":"S. Ye, Q. Peng, W. Sun, J. Xu, Y. Wang, X. You, Y. M. Cheung. Discriminative suprasphere embedding for finegrained visual categorization. IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 4, pp. 5092\u20135102, 2024. DOI: https:\/\/doi.org\/10.1109\/TNNLS.2022.3202534.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"1618_CR11","doi-asserted-by":"publisher","first-page":"8043","DOI":"10.1109\/TIFS.2025.3592531","volume":"20","author":"J Wang","year":"2025","unstructured":"J. Wang, B. Tondi, M. Barni. BOSC: A backdoor-based framework for open set synthetic image attribution. IEEE Transactions on Information Forensics and Security, vol. 20, pp. 8043\u20138058, 2025. DOI: https:\/\/doi.org\/10.1109\/TIFS.2025.3592531.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1618_CR12","doi-asserted-by":"publisher","unstructured":"S. Ye, Q. Peng, Y. M. Cheung, Y. Wang, Z. Zou, X. You. FN-NET: Adaptive data augmentation network for fine-grained visual categorization. Pattern Recognition, vol. 165, Article number 111618, 2025. DOI: https:\/\/doi.org\/10.1016\/j.patcog.2025.111618.","DOI":"10.1016\/j.patcog.2025.111618"},{"issue":"10","key":"1618_CR13","doi-asserted-by":"publisher","first-page":"8674","DOI":"10.1109\/TPAMI.2025.3582389","volume":"47","author":"Q Ye","year":"2025","unstructured":"Q. Ye, Z. Yu, R. Shao, Y. Cui, X. Kang, X. Liu, P. Torr, X. Cao. CAT+: Investigating and enhancing audio-visual understanding in large language models. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 10, pp. 8674\u20138690, 2025. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2025.3582389.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1618_CR14","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":"1618_CR15","doi-asserted-by":"publisher","unstructured":"Y. Shi, Y. Gao, Y. Lai, H. Wang, J. Feng, L. He, J. Wan, C. Chen, Z. Yu, X. Cao. SHIELD: An evaluation benchmark for face spoofing and forgery detection with multimodal large language models. Visual Intelligence, vol. 3, no. 1, Article number 9, 2025. DOI: https:\/\/doi.org\/10.1007\/s44267-025-00079-w.","DOI":"10.1007\/s44267-025-00079-w"},{"key":"1618_CR16","doi-asserted-by":"publisher","first-page":"3527","DOI":"10.1609\/aaai.v39i4.32366","volume-title":"Proceedings of the 39th AAAI Conference on Artificial Intelligence","author":"W Hou","year":"2025","unstructured":"W. Hou, D. Fu, K. Li, S. Chen, H. Fan, Y. Yang. ZeroMamba: Exploring visual state space model for zero-shot learning. In Proceedings of the 39th AAAI Conference on Artificial Intelligence, Philadelphia, USA, pp. 3527\u20133535, 2025. DOI: https:\/\/doi.org\/10.1609\/aaai.v39i4.32366."},{"key":"1618_CR17","series-title":"Technical Report CNS-TR-2010-001","volume-title":"The Caltech-UCSD Birds-200\u20132011 Dataset","author":"C Wah","year":"2011","unstructured":"C. Wah, S. Branson, P. Welinder, P. Perona, S. Belongie. The Caltech-UCSD Birds-200\u20132011 Dataset, Technical Report CNS-TR-2010-001, California Institute of Technology, Pasadena, USA, 2011."},{"key":"1618_CR18","volume-title":"Fine-grained visual classification of aircraft","author":"S Maji","year":"2013","unstructured":"S. Maji, E. Rahtu, J. Kannala, M. Blaschko, A. Vedaldi. Fine-grained visual classification of aircraft, [Online], Available: https:\/\/arxiv.org\/abs\/1306.5151, 2013."},{"issue":"10","key":"1618_CR19","doi-asserted-by":"publisher","first-page":"6024","DOI":"10.1109\/TPAMI.2021.3085766","volume":"44","author":"D P Fan","year":"2022","unstructured":"D. P. Fan, G. P. Ji, M. M. Cheng, L. Shao. Concealed object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 10, pp. 6024\u20136042, 2022. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2021.3085766.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1618_CR20","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TIP.2025.3528347","volume":"34","author":"C Hao","year":"2025","unstructured":"C. Hao, Z. Yu, X. Liu, J. Xu, H. Yue, J. Yang. A simple yet effective network based on vision transformer for camouflaged object and salient object detection. IEEE Transactions on Image Processing, vol. 34, pp. 608\u2013622, 2025. DOI: https:\/\/doi.org\/10.1109\/TIP.2025.3528347.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1618_CR21","doi-asserted-by":"publisher","first-page":"4246","DOI":"10.1145\/3664647.3680694","volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia","author":"S Chen","year":"2024","unstructured":"S. Chen, D. Fu, S. Chen, S. Ye, W. Hou, X. You. Causal visual-semantic correlation for zero-shot learning. In Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, Australia, pp. 4246\u20134255, 2024. DOI: https:\/\/doi.org\/10.1145\/3664647.3680694."},{"issue":"1","key":"1618_CR22","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/TCSVT.2023.3284405","volume":"34","author":"S Ye","year":"2024","unstructured":"S. Ye, Y. Wang, Q. Peng, X. You, C. L. P. Chen. The image data and backbone in weakly supervised finegrained visual categorization: A revisit and further thinking. IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 1, pp. 2\u201316, 2024. DOI: https:\/\/doi.org\/10.1109\/TCSVT.2023.3284405.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1618_CR23","volume-title":"CDLT: A dataset with concept drift and long-tailed distribution for fine-grained visual categorization","author":"S Ye","year":"2023","unstructured":"S. Ye, Y. Shi, R. Wang, Y. Wang, J. Xu, C. Yang, X. You. CDLT: A dataset with concept drift and long-tailed distribution for fine-grained visual categorization, [Online], Available: https:\/\/arxiv.org\/abs\/2306.02346v1, 2023."},{"issue":"12","key":"1618_CR24","doi-asserted-by":"publisher","first-page":"5928","DOI":"10.1109\/TAI.2024.3428519","volume":"5","author":"K Acharya","year":"2024","unstructured":"K. Acharya, A. Velasquez, H. H. Song. A survey on symbolic knowledge distillation of large language models. IEEE Transactions on Artificial Intelligence, vol. 5, no. 12, pp. 5928\u20135948, 2024. DOI: https:\/\/doi.org\/10.1109\/TAI.2024.3428519.","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"1618_CR25","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."},{"key":"1618_CR26","doi-asserted-by":"publisher","first-page":"5262","DOI":"10.1609\/aaai.v39i5.32559","volume-title":"Proceedings of the 39th AAAI Conference on Artificial Intelligence","author":"K Lin","year":"2025","unstructured":"K. Lin, Y. Lin, W. Li, T. Yao, B. Li. Standing on the shoulders of giants: Reprogramming visual-language model for general deepfake detection. In Proceedings of the 39th AAAI Conference on Artificial Intelligence, Philadelphia, USA, pp. 5262\u20135270, 2025. DOI: https:\/\/doi.org\/10.1609\/aaai.v39i5.32559."},{"issue":"12","key":"1618_CR27","doi-asserted-by":"publisher","first-page":"8927","DOI":"10.1109\/TPAMI.2021.3126648","volume":"44","author":"X S Wei","year":"2022","unstructured":"X. S. Wei, Y. Z. Song, O. M. Aodha, J. Wu, Y. Peng, J. Tang, J. Yang, S. Belongie. Fine-grained image analysis with deep learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 12, pp. 8927\u20138948, 2022. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2021.3126648.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1618_CR28","doi-asserted-by":"publisher","first-page":"23627","DOI":"10.1109\/CVPR52733.2024.02230","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"W Hou","year":"2024","unstructured":"W. Hou, S. Chen, S. Chen, Z. Hong, Y. Wang, X. Feng, S. Khan, F. S. Khan, X. You. Visual-augmented dynamic semantic prototype for generative zero-shot learning. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 23627\u201323637, 2024. DOI: https:\/\/doi.org\/10.1109\/CVPR52733.2024.02230."},{"key":"1618_CR29","doi-asserted-by":"publisher","first-page":"4683","DOI":"10.1109\/TIP.2020.2973812","volume":"29","author":"D Chang","year":"2020","unstructured":"D. Chang, Y. Ding, J. Xie, A. K. Bhunia, X. Li, Z. Ma, M. Wu, J. Guo, Y. Z. Song. The devil is in the channels: Mutual-channel loss for fine-grained image classification. IEEE Transactions on Image Processing, vol. 29, pp. 4683\u20134695, 2020. DOI: https:\/\/doi.org\/10.1109\/TIP.2020.2973812.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1618_CR30","doi-asserted-by":"publisher","unstructured":"S. Ye, S. Yu, W. Hou, Y. Wang, X. You. Coping with change: Learning invariant and minimum sufficient representations for fine-grained visual categorization. Computer Vision and Image Understanding, vol. 237, Article number 103837, 2023. DOI: https:\/\/doi.org\/10.1016\/j.cviu.2023.103837.","DOI":"10.1016\/j.cviu.2023.103837"},{"key":"1618_CR31","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2016","unstructured":"K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770\u2013778, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.90."},{"key":"1618_CR32","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 16 \u00d7 16 words: Transformers for image recognition at scale. In Proceedings of the 9th International Conference on Learning Representations, 2021."},{"key":"1618_CR33","first-page":"68777","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"C Xie","year":"2025","unstructured":"C. Xie, B. Wang, F. Kong, J. Li, D. Liang, G. Zhang, D. Leng, Y. Yin. FG-CLIP: Fine-grained visual and textual alignment. In Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, pp. 68777\u201368793, 2025."},{"key":"1618_CR34","volume-title":"Agent4-FaceForgery: Multi-agent LLM framework for realistic face forgery detection","author":"Y Lai","year":"2025","unstructured":"Y. Lai, Z. Yu, J. Wang, L. Shen, Y. Xu, X. Cao. Agent4-FaceForgery: Multi-agent LLM framework for realistic face forgery detection, [Online], Available: https:\/\/arxiv.org\/abs\/2509.12546v1, 2025."},{"key":"1618_CR35","doi-asserted-by":"publisher","first-page":"3622","DOI":"10.1109\/TIP.2023.3286710","volume":"32","author":"C Liu","year":"2023","unstructured":"C. Liu, Y. Zhang, H. Wang, W. Chen, F. Wang, Y. Huang, Y. D. Shen, L. Wang. Efficient token-guided image-text retrieval with consistent multimodal contrastive training. IEEE Transactions on Image Processing, vol. 32, pp. 3622\u20133633, 2023. DOI: https:\/\/doi.org\/10.1109\/TIP.2023.3286710.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1618_CR36","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations","author":"H A Tsao","year":"2024","unstructured":"H. A. Tsao, L. Hsiung, P. Y. Chen, S. Liu, T. Y. Ho. AutoVP: An automated visual prompting framework and benchmark. In Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria, [Online], Available: https:\/\/openreview.net\/forum?id=wR9qVlPh0P, 2024."},{"key":"1618_CR37","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":"1618_CR38","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"G F Elsayed","year":"2019","unstructured":"G. F. Elsayed, I. Goodfellow, J. Sohl-Dickstein. Adversarial reprogramming of neural networks. In Proceedings of the 7th International Conference on Learning Representations, New Orleans, USA, 2019."},{"key":"1618_CR39","doi-asserted-by":"publisher","first-page":"22584","DOI":"10.1609\/aaai.v38i20.30267","volume-title":"Proceedings of the 38th AAAI Conference on Artificial Intelligence","author":"P Y Chen","year":"2024","unstructured":"P. Y. Chen. Model reprogramming: Resource-efficient cross-domain machine learning. In Proceedings of the 38th AAAI Conference on Artificial Intelligence, Vancouver, Canada, pp. 22584\u201322591, 2024. DOI: https:\/\/doi.org\/10.1609\/aaai.v38i20.30267."},{"key":"1618_CR40","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Q Wang","year":"2022","unstructured":"Q. Wang, F. Liu, Y. Zhang, J. Zhang, C. Gong, T. Liu, B. Han. Watermarking for out-of-distribution detection. In Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, USA, Article number 1131, 2022."},{"key":"1618_CR41","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"C Cai","year":"2024","unstructured":"C. Cai, Z. Ye, L. Feng, J. Qi, F. Liu. Sample-specific masks for visual reprogramming-based prompting. In Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria, 2024."},{"key":"1618_CR42","doi-asserted-by":"publisher","first-page":"19133","DOI":"10.1109\/CVPR52729.2023.01834","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Chen","year":"2023","unstructured":"A. Chen, Y. Yao, P. Y. Chen, Y. Zhang, S. Liu. Understanding and improving visual prompting: A label-mapping perspective. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, Canada, pp. 19133\u201319143, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.01834."},{"key":"1618_CR43","volume-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","author":"C Cai","year":"2024","unstructured":"C. Cai, Z. Ye, L. Feng, J. Qi, F. Liu. Bayesian-guided label mapping for visual reprogramming. In Proceedings of the 38th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 561, 2024."},{"key":"1618_CR44","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"C Cai","year":"2025","unstructured":"C. Cai, Z. Ye, L. Feng, J. Qi, F. Liu. Understanding model reprogramming for CLIP via decoupling visual prompts. In Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, 2025."},{"key":"1618_CR45","doi-asserted-by":"publisher","first-page":"11586","DOI":"10.1109\/CVPR46437.2021.01142","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Lv","year":"2021","unstructured":"Y. Lv, J. Zhang, Y. Dai, A. Li, B. Liu, N. Barnes, D. P. Fan. Simultaneously localize, segment and rank the camouflaged objects. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, pp. 11586\u201311596, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.01142."},{"key":"1618_CR46","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.cviu.2019.04.006","volume":"184","author":"T N Le","year":"2019","unstructured":"T. N. Le, T. V. Nguyen, Z. Nie, M. T. Tran, A. Sugimoto. Anabranch network for camouflaged object segmentation. Computer Vision and Image Understanding, vol. 184, pp. 45\u201356, 2019. DOI: https:\/\/doi.org\/10.1016\/j.cviu.2019.04.006.","journal-title":"Computer Vision and Image Understanding"},{"key":"1618_CR47","volume-title":"Toward realistic camouflaged object detection: Benchmarks and method","author":"Z Xin","year":"2025","unstructured":"Z. Xin, T. Wu, S. Chen, S. Ye, Z. Xie, Y. Zou, X. You, Y. Guo. Toward realistic camouflaged object detection: Benchmarks and method, [Online], Available: https:\/\/arxiv.org\/abs\/2501.07297, 2025."},{"key":"1618_CR48","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"M Minderer","year":"2022","unstructured":"M. Minderer, A. Gritsenko, A. Stone, M. Neumann, D. Weissenborn, A. Dosovitskiy, A. Mahendran, A. Arnab, M. Dehghani, Z. Shen, X. Wang, X. Zhai, T. Kipf, N. Houlsby. Simple open-vocabulary object detection. In Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel, pp. 728\u2013755, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42."},{"key":"1618_CR49","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"M Minderer","year":"2023","unstructured":"M. Minderer, A. Gritsenko, N. Houlsby. Scaling open-vocabulary object detection. In Proceedings of the 37th International Conference on Neural Information Processing Systems, New Orleans, USA, Article number 3191, 2023."},{"key":"1618_CR50","volume-title":"DeepEyes: Incentivizing \u201cthinking with images\u201d via reinforcement learning","author":"Z Zheng","year":"2025","unstructured":"Z. Zheng, M. Yang, J. Hong, C. Zhao, G. Xu, L. Yang, C. Shen, X. Yu. DeepEyes: Incentivizing \u201cthinking with images\u201d via reinforcement learning, [Online], Available: https:\/\/arxiv.org\/abs\/2505.14362v2, 2025."},{"key":"1618_CR51","volume-title":"Qwen2.5-VL technical report","author":"S Bai","year":"2025","unstructured":"S. Bai, K. Chen, X. Liu, J. Wang, W. Ge, S. Song, K. Dang, P. Wang, S. Wang, J. Tang, H. Zhong, Y. Zhu, M. Yang, Z. Li, J. Wan, P. Wang, W. Ding, Z. Fu, Y. Xu, J. Ye, X. Zhang, T. Xie, Z. Cheng, H. Zhang, Z. Yang, H. Xu, J. Lin, An Yang, B. Hui, B. Yu, C. Cheng, D. Liu, F. Hong, F. Huang, J. Liu, J. Xu, J. Tu, J. Zeng, J. Zhang, J. Wang, J. Zhang, J. Zhou, K. Yang, M. Li, M. Yan, N. Ni, R. Men, S. Jiang, X. Deng, X. Huang, X. Zhou, X. Ren, Y. Fan, Y. Zhang, Y. Zhu, Y. Liu, Z. Guo. Qwen2.5-VL technical report, [Online], Available: https:\/\/arxiv.org\/abs\/2502.13923, 2025."},{"key":"1618_CR52","volume-title":"VisionReasoner: Unified visual perception and reasoning via reinforcement learning","author":"Y Liu","year":"2025","unstructured":"Y. Liu, T. Qu, Z. Zhong, B. Peng, S. Liu, B. Yu, J. Jia. VisionReasoner: Unified visual perception and reasoning via reinforcement learning, [Online], Available: https:\/\/arxiv.org\/abs\/2505.12081v3, 2025."},{"key":"1618_CR53","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Z Chen","year":"2023","unstructured":"Z. Chen, Y. Duan, W. Wang, J. He, T. Lu, J. Dai, Y. Qiao. Vision transformer adapter for dense predictions. In Proceedings of the 11th International Conference on Learning Representations, Kigali, Rwanda, 2023."},{"issue":"9","key":"1618_CR54","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":"1618_CR55","volume-title":"Proceedings of CVPR Workshop on FineGrained Visual Categorization","author":"A Khosla","year":"2011","unstructured":"A. Khosla, N. Jayadevaprakash, B. Yao, F. F. Li. Novel dataset for fine-grained image categorization: Stanford dogs. In Proceedings of CVPR Workshop on FineGrained Visual Categorization, Colorado Springs, USA, 2011."},{"key":"1618_CR56","doi-asserted-by":"publisher","first-page":"3498","DOI":"10.1109\/CVPR.2012.6248092","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"O M Parkhi","year":"2012","unstructured":"O. M. Parkhi, A. Vedaldi, A. Zisserman, C. V. Jawahar. Cats and dogs. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, pp. 3498\u20133505, 2012. DOI: https:\/\/doi.org\/10.1109\/CVPR.2012.6248092."},{"key":"1618_CR57","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/ICCV.2017.74","volume-title":"Proceedings of IEEE International Conference on Computer Vision","author":"R R Selvaraju","year":"2017","unstructured":"R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp. 618\u2013626, 2017. DOI: https:\/\/doi.org\/10.1109\/ICCV.2017.74."},{"issue":"86","key":"1618_CR58","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"L. van der Maaten, G. Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, vol. 9, no. 86, pp. 2579\u20132605, 2008","journal-title":"Journal of Machine Learning Research"}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1618-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-025-1618-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1618-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T12:05:00Z","timestamp":1775649900000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-025-1618-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["1618"],"URL":"https:\/\/doi.org\/10.1007\/s11633-025-1618-5","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":"24 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 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":"Declarations of conflict of interest"}}]}}