{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:14:33Z","timestamp":1784211273212,"version":"3.55.0"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729065","type":"print"},{"value":"9783031729072","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72907-2_27","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"459-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Improving Zero-Shot Generalization of\u00a0Learned Prompts via\u00a0Unsupervised Knowledge Distillation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6630-6477","authenticated-orcid":false,"given":"Marco","family":"Mistretta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5012-5800","authenticated-orcid":false,"given":"Alberto","family":"Baldrati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-218X","authenticated-orcid":false,"given":"Marco","family":"Bertini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6408-7043","authenticated-orcid":false,"given":"Andrew D.","family":"Bagdanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"27_CR1","unstructured":"Abdul\u00a0Samadh, J., et al.: Align your prompts: test-time prompting with distribution alignment for zero-shot generalization. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Agnolucci, L., Baldrati, A., Todino, F., Becattini, F., Bertini, M., Del\u00a0Bimbo, A.: Eco: ensembling context optimization for vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2811\u20132815 (2023)","DOI":"10.1109\/ICCVW60793.2023.00299"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Agnolucci, L., Bertini, M., Del\u00a0Bimbo, A.: Zero-shot composed image retrieval with textual inversion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15338\u201315347 (2023)","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Barraco, M., Cornia, M., Cascianelli, S., Baraldi, L., Cucchiara, R.: The unreasonable effectiveness of clip features for image captioning: an experimental analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4662\u20134670 (2022)","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Beyer, L., Zhai, X., Royer, A., Markeeva, L., Anil, R., Kolesnikov, A.: Knowledge distillation: a good teacher is patient and consistent. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10925\u201310934 (2022)","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"27_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: LASP: text-to-text optimization for language-aware soft prompting of vision & language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23232\u201323241 (2023)","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"27_CR8","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao, Y., Zhang, K.: Plot: prompt learning with optimal transport for vision-language models. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"27_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/978-3-030-20893-6_13","volume-title":"Computer Vision \u2013 ACCV 2018","author":"W-C Chen","year":"2019","unstructured":"Chen, W.-C., Chang, C.-C., Lee, C.-R.: Knowledge distillation with feature maps for image classification. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 200\u2013215. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_13"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Desai, K., Johnson, J.: Virtex: learning visual representations from textual annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11162\u201311173 (2021)","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"27_CR14","unstructured":"Ding, Y., Liu, L., Tian, C., Yang, J., Ding, H.: Don\u2019t stop learning: towards continual learning for the clip model. arXiv preprint arXiv:2207.09248 (2022)"},{"key":"27_CR15","unstructured":"Dong, X., et al.: Clip itself is a strong fine-tuner: achieving 85.7% and 88.0% top-1 accuracy with VIT-B and VIT-L on imagenet. arXiv preprint arXiv:2212.06138 (2022)"},{"key":"27_CR16","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"issue":"7","key":"27_CR17","doi-asserted-by":"publisher","first-page":"2415","DOI":"10.1109\/TMI.2019.2963882","volume":"39","author":"Q Dou","year":"2020","unstructured":"Dou, Q., Liu, Q., Heng, P.A., Glocker, B.: Unpaired multi-modal segmentation via knowledge distillation. IEEE Trans. Med. Imaging 39(7), 2415\u20132425 (2020)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"27_CR18","unstructured":"Fang, A., Jose, A.M., Jain, A., Schmidt, L., Toshev, A.T., Shankar, V.: Data filtering networks. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"27_CR19","unstructured":"Fang, Z., Wang, J., Wang, L., Zhang, L., Yang, Y., Liu, Z.: Seed: self-supervised distillation for visual representation. In: International Conference on Learning Representations (2020)"},{"key":"27_CR20","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: 2004 Conference on Computer Vision and Pattern Recognition Workshop, pp. 178\u2013178. IEEE (2004)"},{"key":"27_CR21","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference on Learning Representations (2021)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"He, T., Shen, C., Tian, Z., Gong, D., Sun, C., Yan, Y.: Knowledge adaptation for efficient semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 578\u2013587 (2019)","DOI":"10.1109\/CVPR.2019.00067"},{"issue":"7","key":"27_CR23","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.: Eurosat: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J. Sel. Top. Appl. Obs. Remote Sens. 12(7), 2217\u20132226 (2019)","journal-title":"IEEE J. Sel. Top. Appl. Obs. Remote Sens."},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"27_CR26","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Stat 1050, 9 (2015)"},{"key":"27_CR27","unstructured":"Huang, T., Chu, J., Wei, F.: Unsupervised prompt learning for vision-language models. arXiv preprint arXiv:2204.03649 (2022)"},{"key":"27_CR28","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., Khan, F.S.: Self-regulating prompts: foundational model adaptation without forgetting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15190\u201315200 (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"7","key":"27_CR33","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision (IJCV) 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045\u20133059 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 4582\u20134597 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Promptkd: unsupervised prompt distillation for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26617\u201326626 (2024)","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, J., Zhang, Y., Liu, Y., Tian, X.: Prompt distribution learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5206\u20135215 (2022)","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"27_CR39","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Mullapudi, R.T., Chen, S., Zhang, K., Ramanan, D., Fatahalian, K.: Online model distillation for efficient video inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3573\u20133582 (2019)","DOI":"10.1109\/ICCV.2019.00367"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Parelli, M., et al.: Clip-guided vision-language pre-training for question answering in 3D scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5606\u20135611 (2023)","DOI":"10.1109\/CVPRW59228.2023.00593"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"27_CR44","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"27_CR45","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imagenet classifiers generalize to imagenet? In: International Conference on Machine Learning, pp. 5389\u20135400. PMLR (2019)"},{"key":"27_CR46","unstructured":"Ren, S., et al.: Prompt pre-training with twenty-thousand classes for open-vocabulary visual recognition. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"27_CR47","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25278\u201325294 (2022)"},{"key":"27_CR48","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Shi, C., Yang, S.: Logoprompt: synthetic text images can be good visual prompts for vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2932\u20132941 (2023)","DOI":"10.1109\/ICCV51070.2023.00274"},{"key":"27_CR50","unstructured":"Shi, Z., Lipani, A.: DePT: decomposed prompt tuning for parameter-efficient fine-tuning. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=KjegfPGRde"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Siam, M., et al.: Video object segmentation using teacher-student adaptation in a human robot interaction (HRI) setting. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 50\u201356. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Song, H., Dong, L., Zhang, W., Liu, T., Wei, F.: Clip models are few-shot learners: empirical studies on VQA and visual entailment. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6088\u20136100 (2022)","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"27_CR53","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"27_CR54","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"27_CR55","unstructured":"Wang, Z., Liang, J., He, R., Xu, N., Wang, Z., Tan, T.: Improving zero-shot generalization for clip with synthesized prompts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3032\u20133042 (2023)"},{"key":"27_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/978-3-030-58545-7_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Xu","year":"2020","unstructured":"Xu, G., Liu, Z., Li, X., Loy, C.C.: Knowledge distillation meets self-supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 588\u2013604. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_34"},{"key":"27_CR57","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., Xu, C.: Visual-language prompt tuning with knowledge-guided context optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6757\u20136767 (2023)","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"27_CR58","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F.E., Li, G., Wang, T., Feng, J.: Revisiting knowledge distillation via label smoothing regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3903\u20133911 (2020)","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"27_CR59","doi-asserted-by":"crossref","unstructured":"Yun, S., Park, J., Lee, K., Shin, J.: Regularizing class-wise predictions via self-knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13876\u201313885 (2020)","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"27_CR60","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Lit: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"27_CR61","unstructured":"Zhang, R., et al.: Tip-adapter: training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930 (2021)"},{"key":"27_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4320\u20134328 (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"27_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., Liang, J.: Decoupled knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11953\u201311962 (2022)","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"27_CR64","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Friedman, D., Chen, D.: Factual probing is [mask]: learning vs. learning to recall. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 5017\u20135033 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"27_CR65","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-031-19815-1_40","volume-title":"European Conference on Computer Vision","author":"C Zhou","year":"2022","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40"},{"key":"27_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"27_CR67","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.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR68","doi-asserted-by":"crossref","unstructured":"Zhu, B., Niu, Y., Han, Y., Wu, Y., Zhang, H.: Prompt-aligned gradient for prompt tuning. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15613\u201315623. IEEE Computer Society (2023)","DOI":"10.1109\/ICCV51070.2023.01435"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72907-2_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:37:30Z","timestamp":1730302650000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72907-2_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729065","9783031729072"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72907-2_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}