{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T21:56:40Z","timestamp":1789768600312,"version":"4.0.1"},"reference-count":96,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"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":["62206316"],"award-info":[{"award-number":["62206316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072482"],"award-info":[{"award-number":["62072482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2095"],"award-info":[{"award-number":["U22A2095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32100901"],"award-info":[{"award-number":["32100901"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010843","name":"Guangzhou Science, Technology and Innovation Commission","doi-asserted-by":"publisher","award":["202206030003"],"award-info":[{"award-number":["202206030003"]}],"id":[{"id":"10.13039\/501100010843","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515011254"],"award-info":[{"award-number":["2022A1515011254"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["21ZR1434700"],"award-info":[{"award-number":["21ZR1434700"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["23ptpy79"],"award-info":[{"award-number":["23ptpy79"]}],"id":[{"id":"10.13039\/501100012226","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":[[2025,6]]},"DOI":"10.1007\/s11263-025-02354-1","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T07:11:33Z","timestamp":1738048293000},"page":"3746-3761","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Learning with Enriched Inductive Biases for Vision-Language Models"],"prefix":"10.1007","volume":"133","author":[{"given":"Lingxiao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ru-Yuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-4679","authenticated-orcid":false,"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"2354_CR1","first-page":"23716","volume":"35","author":"J-B Alayrac","year":"2022","unstructured":"Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., et al. (2022). Flamingo: A visual language model for few-shot learning. Advances in neural information processing systems, 35, 23716\u201323736.","journal-title":"Advances in neural information processing systems"},{"key":"2354_CR2","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Van\u00a0Gool, L. (2014). Food-101\u2013mining discriminative components with random forests. European conference on computer vision (pp. 446\u2013461).","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"2354_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33, 1877\u20131901.","journal-title":"Advances in neural information processing systems"},{"key":"2354_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2354_CR5","doi-asserted-by":"crossref","unstructured":"Bulat, A., & Tzimiropoulos, G. (2023). Lasp: Text-to-text optimization for language-aware soft prompting of vision & language models. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 23232\u201323241).","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"2354_CR6","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao, Y., & Zhang, K. (2022a). Plot: Prompt learning with optimal transport for vision-language models. International conference on learning representations."},{"key":"2354_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102311","volume":"107","author":"Q Chen","year":"2024","unstructured":"Chen, Q., Chen, Y., Huang, Y., Xie, X., & Yang, L. (2024). Region-based online selective examination for weakly supervised semantic segmentation. Information Fusion, 107, 102311.","journal-title":"Information Fusion"},{"key":"2354_CR8","first-page":"16664","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen, S., Ge, C., Tong, Z., Wang, J., Song, Y., Wang, J., & Luo, P. (2022). Adaptformer: Adapting vision transformers for scalable visual recognition. Advances in Neural Information Processing Systems, 35, 16664\u201316678.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2354_CR9","unstructured":"Chen, Z., Duan, Y., Wang, W., He, J., Lu, T., Dai, J., & Qiao, Y. (2022c). Vision transformer adapter for dense predictions. International conference on learning representations."},{"key":"2354_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., Huang, X., Guan, Q., Lin, L., & Luo, W. (2023). A retrospect to multi-prompt learning across vision and language. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 22190\u201322201).","DOI":"10.1109\/ICCV51070.2023.02028"},{"key":"2354_CR11","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014). Describing textures in the wild. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3606\u20133613).","DOI":"10.1109\/CVPR.2014.461"},{"key":"2354_CR12","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. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2354_CR13","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805,"},{"key":"2354_CR14","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.-S., & Dai, D. (2022). Decoupling zero-shot semantic segmentation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11583\u201311592).","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"2354_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T. others (2020). An image is worth 16x16 words: Transformers for image recognition at scale. International conference on learning representations."},{"key":"2354_CR16","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. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops (pp. 178\u2013178).","DOI":"10.1109\/CVPR.2004.383"},{"key":"2354_CR17","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Jie, Z., Chu, X., Ren, H., Wei, X., & Ma, L. (2022). Promptdet: Towards open-vocabulary detection using uncurated images. European conference on computer vision (pp. 701\u2013717).","DOI":"10.1007\/978-3-031-20077-9_41"},{"issue":"2","key":"2354_CR18","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2023","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., & Qiao, Y. (2023). 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":"2354_CR19","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 580\u2013587).","DOI":"10.1109\/CVPR.2014.81"},{"key":"2354_CR20","unstructured":"Gu, X., Lin, T.-Y., Kuo, W., & Cui, Y. (2021). Open-vocabulary object detection via vision and language knowledge distillation. International conference on learning representations."},{"key":"2354_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2354_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2354_CR23","doi-asserted-by":"crossref","unstructured":"He, W., Jamonnak, S., Gou, L., & Ren, L. (2023). Clip-s4: Language-guided self-supervised semantic segmentation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11207\u201311216).","DOI":"10.1109\/CVPR52729.2023.01078"},{"issue":"7","key":"2354_CR24","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":"2354_CR25","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., Mu, N., Kadavath, S., Wang, F., Dorundo, E. others (2021). The many faces of robustness: A critical analysis of out-of-distribution generalization. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8340\u20138349).","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"2354_CR26","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2021). Natural adversarial examples. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 15262\u201315271).","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"2354_CR27","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De\u00a0Laroussilhe, Q., Gesmundo, A., & Gelly, S. (2019). Parameter-efficient transfer learning for NLP. International conference on machine learning (pp. 2790\u20132799)."},{"key":"2354_CR28","unstructured":"Hu, E. J., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., & Wang, L. (2021). others. Lora: Low-rank adaptation of large language models. International conference on learning representations"},{"key":"2354_CR29","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2354_CR30","unstructured":"Huang, S., Dong, L., Wang, W., Hao, Y., Singhal, S., Ma, S. others (2023). Language is not all you need: Aligning perception with language models. arXiv preprint arXiv:2302.14045"},{"key":"2354_CR31","doi-asserted-by":"publisher","unstructured":"Ilharco, G., Wortsman, M., Wightman, R., Gordon, C., Carlini, N., Taori, R., & Schmidt, L. (2021). Openclip. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"2354_CR32","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., & Duerig, T. (2021). Scaling up visual and vision-language representation learning with noisy text supervision. International conference on machine learning (pp. 4904\u20134916)."},{"key":"2354_CR33","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. European conference on computer vision (pp. 709\u2013727).","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"2354_CR34","unstructured":"Jiang, H., Zhang, J., Huang, R., Ge, C., Ni, Z., Lu, J., & Huang, G. (2022). Cross-modal adapter for text-video retrieval. arXiv preprint arXiv:2211.09623"},{"key":"2354_CR35","doi-asserted-by":"crossref","unstructured":"Khattak, M. U., Rasheed, H., Maaz, M., Khan, S., & Khan, F. S. (2023a). Maple: Multi-modal prompt learning. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19113\u201319122).","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"2354_CR36","doi-asserted-by":"crossref","unstructured":"Khattak, M. U., Wasim, S. T., Naseer, M., Khan, S., Yang, M.-H., & Khan, F. S. (2023b). Self-regulating prompts: Foundational model adaptation without forgetting. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 15190\u201315200).","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"2354_CR37","unstructured":"Kim, K., Laskin, M., Mordatch, I., & Pathak, D. (2021). How to adapt your large-scale vision-and-language model."},{"key":"2354_CR38","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013). 3d object representations for fine-grained categorization. Proceedings of the IEEE\/CVF international conference on computer vision workshops (pp. 554\u2013561).","DOI":"10.1109\/ICCVW.2013.77"},{"key":"2354_CR39","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60, 84\u201390.","journal-title":"Communications of the ACM"},{"key":"2354_CR40","doi-asserted-by":"crossref","unstructured":"Lee, D., Song, S., Suh, J., Choi, J., Lee, S., & Kim, H. J. (2023). Read-only prompt optimization for vision-language few-shot learning. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1401\u20131411).","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"2354_CR41","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., & Constant, N. (2021). The power of scale for parameter-efficient prompt tuning. Proceedings of the conference on empirical methods in natural language processing (pp. 3045\u20133059).","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"2354_CR42","doi-asserted-by":"crossref","unstructured":"Li, X. L., & Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. arXiv:2101.00190 [cs.CL]","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"2354_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"2354_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. European conference on computer vision (pp. 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2354_CR45","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). SSD: Single shot multibox detector. European conference on computer vision (pp. 21\u201337).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2354_CR46","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2354_CR47","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3431\u20133440).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2354_CR48","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, J., Zhang, Y., Liu, Y., & Tian, X. (2022). Prompt distribution learning. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5206\u20135215).","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"2354_CR49","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151"},{"key":"2354_CR50","doi-asserted-by":"crossref","unstructured":"Maniparambil, M., Vorster, C., Molloy, D., Murphy, N., McGuinness, K., & O\u2019Connor, N. E. (2023). Enhancing clip with gpt-4: Harnessing visual descriptions as prompts. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 262\u2013271).","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"2354_CR51","unstructured":"Menon, S., & Vondrick, C. (2022). Visual classification via description from large language models. arXiv preprint arXiv:2210.07183"},{"key":"2354_CR52","doi-asserted-by":"crossref","unstructured":"Nilsback, M.-E., & Zisserman, A. (2008). Automated flower classification over a large number of classes. Sixth indian conference on computer vision, graphics & image processing (pp. 722\u2013729).","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"2354_CR53","unstructured":"Oord, A.v.d., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"2354_CR54","doi-asserted-by":"crossref","unstructured":"Parkhi, O. M., Vedaldi, A., Zisserman, A., & Jawahar, C. (2012). Cats and dogs. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3498\u20133505).","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"2354_CR55","doi-asserted-by":"crossref","unstructured":"Pratt, S., Covert, I., Liu, R., & Farhadi, A. (2023). What does a platypus look like? generating customized prompts for zero-shot image classification. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 15691\u201315701).","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"2354_CR56","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S. others (2021). Learning transferable visual models from natural language supervision. International conference on machine learning (pp. 8748\u20138763)."},{"key":"2354_CR57","doi-asserted-by":"crossref","unstructured":"Rao, Y., Zhao, W., Chen, G., Tang, Y., Zhu, Z., Huang, G., & Lu, J. (2022). Denseclip: Language-guided dense prediction with context-aware prompting. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18082\u201318091).","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"2354_CR58","unstructured":"Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019). Do imagenet classifiers generalize to imagenet? International conference on machine learning (pp. 5389\u20135400)."},{"key":"2354_CR59","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 779\u2013788).","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"2354_CR60","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2354_CR61","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. International conference on medical image computing and computer-assisted intervention (pp. 234\u2013241).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2354_CR62","doi-asserted-by":"crossref","unstructured":"Saha, O., Van\u00a0Horn, G., & Maji, S. (2024). Improved zero-shot classification by adapting vlms with text descriptions. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 17542\u201317552).","DOI":"10.1109\/CVPR52733.2024.01661"},{"key":"2354_CR63","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C. W., Wightman, R., Cherti, M., & Jitsev, J. (2022). LAION-5b: An open large-scale dataset for training next generation image-text models. Thirty-sixth conference on neural information processing systems datasets and benchmarks track.[SPACE]https:\/\/openreview.net\/forum?id=M3Y74vmsMcY"},{"key":"2354_CR64","doi-asserted-by":"crossref","unstructured":"Sd\u2019Ascoli, S., Touvron, H., Leavitt, M. L., Morcos, A. S., Biroli, G., & Sagun, L. (2021). Convit: Improving vision transformers with soft convolutional inductive biases. International conference on machine learning (pp. 2286\u20132296).","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"2354_CR65","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. International conference on learning representations."},{"key":"2354_CR66","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":"2354_CR67","unstructured":"Stickland, A. C., & Murray, I. (2019). Bert and pals: Projected attention layers for efficient adaptation in multi-task learning. International conference on machine learning (pp. 5986\u20135995)."},{"key":"2354_CR68","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Deng, W., & Wang, S. (2017). Svdnet for pedestrian retrieval. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3800\u20133808).","DOI":"10.1109\/ICCV.2017.410"},{"key":"2354_CR69","unstructured":"Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. International conference on machine learning (pp. 6105\u20136114)."},{"key":"2354_CR70","first-page":"10506","volume":"32","author":"H Wang","year":"2019","unstructured":"Wang, H., Ge, S., Lipton, Z., & Xing, E. P. (2019). Learning robust global representations by penalizing local predictive power. Advances in neural information processing systems, 32, 10506\u201310518.","journal-title":"Advances in neural information processing systems"},{"key":"2354_CR71","doi-asserted-by":"crossref","unstructured":"Wang, Y., Jiang, X., Cheng, D., Li, D., & Zhao, C. (2024). Learning hierarchical prompt with structured linguistic knowledge for vision-language models. Proceedings of the AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v38i6.28387"},{"key":"2354_CR72","unstructured":"Wang, Z., Yu, J., Yu, A. W., Dai, Z., Tsvetkov, Y., & Cao, Y. (2021). Simvlm: Simple visual language model pretraining with weak supervision. International conference on learning representations."},{"key":"2354_CR73","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. European conference on computer vision (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2354_CR74","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., & Zhang, L. (2021). Cvt: Introducing convolutions to vision transformers. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 22\u201331).","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"2354_CR75","doi-asserted-by":"crossref","unstructured":"Xian, Y., Schiele, B., & Akata, Z. (2017). Zero-shot learning-the good, the bad and the ugly. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4582\u20134591).","DOI":"10.1109\/CVPR.2017.328"},{"key":"2354_CR76","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. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3485\u20133492).","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"2354_CR77","unstructured":"Yang, L., Zhang, R.-Y., Li, L., & Xie, X. (2021). Simam: A simple, parameter-free attention module for convolutional neural networks. International conference on machine learning (pp. 11863\u201311874)."},{"key":"2354_CR78","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., & Xu, C. (2023). Visual-language prompt tuning with knowledge-guided context optimization. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6757\u20136767).","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"2354_CR79","unstructured":"Yao, L., Huang, R., Hou, L., Lu, G., Niu, M., Xu, H., & Xu, C. (2021). Filip: Fine-grained interactive language-image pre-training. International conference on learning representations."},{"issue":"6","key":"2354_CR80","doi-asserted-by":"publisher","first-page":"2872","DOI":"10.1109\/TPAMI.2021.3054775","volume":"44","author":"M Ye","year":"2021","unstructured":"Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., & Hoi, S. C. (2021). Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(6), 2872\u20132893.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2354_CR81","unstructured":"Ye, T., Dong, L., Xia, Y., Sun, Y., Zhu, Y., Huang, G., & Wei, F. (2024). Differential transformer. arXiv preprint arXiv:2410.05258"},{"key":"2354_CR82","doi-asserted-by":"crossref","unstructured":"Yu, T., Lu, Z., Jin, X., Chen, Z., & Wang, X. (2023). Task residual for tuning vision-language models. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10899\u201310909).","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"2354_CR83","unstructured":"Yuan, L., Chen, D., Chen, Y.-L., Codella, N., Dai, X., Gao, J. (2021). Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432"},{"key":"2354_CR84","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., & Loy, C. C. (2022a). Open-vocabulary detr with conditional matching. European conference on computer vision (pp. 106\u2013122).","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"2354_CR85","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., & Loy, C. C. (2022b). Unified vision and language prompt learning. arXiv preprint arXiv:2210.07225"},{"key":"2354_CR86","doi-asserted-by":"crossref","unstructured":"Zhai, X., Wang, X., Mustafa, B., Steiner, A., Keysers, D., Kolesnikov, A., & Beyer, L. (2022). Lit: Zero-shot transfer with locked-image text tuning. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18123\u201318133).","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"2354_CR87","doi-asserted-by":"publisher","first-page":"3046","DOI":"10.1007\/s11263-024-02013-x","volume":"132","author":"Q Zhang","year":"2024","unstructured":"Zhang, Q., Lai, J., Feng, Z., & Xie, X. (2024). Uncertainty modeling for group re-identification. International Journal of Computer Vision, 132, 3046.","journal-title":"International Journal of Computer Vision"},{"key":"2354_CR88","doi-asserted-by":"publisher","first-page":"5791","DOI":"10.1109\/TPAMI.2024.3369483","volume":"46","author":"Q Zhang","year":"2024","unstructured":"Zhang, Q., Lai, J., Xie, X., Jin, X., & Huang, S. (2024). Separable spatial-temporal residual graph for cloth-changing group re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46, 5791.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2354_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai, J., & Li, H. (2022). Tip-adapter: Training-free adaption of clip for few-shot classification. European conference on computer vision (pp. 493\u2013510).","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"2354_CR90","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, J., Zhang, P., Li, C., Codella, N., Li, L. H. others (2022). Regionclip: Region-based language-image pretraining. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16793\u201316803).","DOI":"10.1109\/CVPR52688.2022.01629"},{"issue":"6","key":"2354_CR91","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2017). Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1452\u20131464.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2354_CR92","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C. C., & Dai, B. (2022c). Extract free dense labels from clip. European conference on computer vision (pp. 696\u2013712).","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"2354_CR93","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022a). Conditional prompt learning for vision-language models. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16816\u201316825).","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"2354_CR94","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"},{"key":"2354_CR95","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., & Misra, I. (2022d). Detecting twenty-thousand classes using image-level supervision. European conference on computer vision (pp. 350\u2013368).","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"2354_CR96","doi-asserted-by":"crossref","unstructured":"Zhu, B., Niu, Y., Han, Y., Wu, Y., & Zhang, H. (2023). Prompt-aligned gradient for prompt tuning. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 15659\u201315669).","DOI":"10.1109\/ICCV51070.2023.01435"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02354-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02354-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02354-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T02:58:06Z","timestamp":1746845886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02354-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,28]]},"references-count":96,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2354"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02354-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,28]]},"assertion":[{"value":"24 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest."}}]}}