{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T02:04:00Z","timestamp":1768356240256,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556786","type":"print"},{"value":"9789819556793","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5679-3_8","type":"book-chapter","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:56Z","timestamp":1768329416000},"page":"106-119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ClinCoCoOp: An Interpretable Prompt Learning Framework with\u00a0Clinical Concept Guidance for\u00a0Context Optimization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0803-6598","authenticated-orcid":false,"given":"Jianjing","family":"Wei","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2480-3997","authenticated-orcid":false,"given":"Wuman","family":"Luo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8267-086X","authenticated-orcid":false,"given":"Bidong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"8_CR1","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":"8_CR2","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12\u00a0888\u201312\u00a0900. PMLR (2022)"},{"key":"8_CR3","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp. 23\u00a0716\u201323\u00a0736 (2022)"},{"key":"8_CR4","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models, arXiv preprint arXiv:2205.01917 (2022)"},{"issue":"9","key":"8_CR5","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":"8_CR6","unstructured":"Zhou, K., Yang, J., Loy.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16\u00a0816\u201316\u00a0825 (2022)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Patr\u00edcio, C., Teixeira, L.F., Neves, J.C.: Towards concept-based interpretability of skin lesion diagnosis using vision-language models. In: IEEE International Symposium on Biomedical Imaging (ISBI), vol. 2024, pp. 1\u20135. IEEE (2024)","DOI":"10.1109\/ISBI56570.2024.10635623"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Fang, X., Lin, Y., Zhang, D., Cheng, K.-T., Chen, H.: Aligning medical images with general knowledge from large language models. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, pp. 57\u201367 (2024)","DOI":"10.1007\/978-3-031-72117-5_6"},{"key":"8_CR9","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":"8_CR10","doi-asserted-by":"crossref","unstructured":"Bie, Y., Luo, L., Chen, Z., Chen, H.: Xcoop: explainable prompt learning for computer-aided diagnosis via concept-guided context optimization. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, pp. 773\u2013783 (2024)","DOI":"10.1007\/978-3-031-72390-2_72"},{"key":"8_CR11","unstructured":"Lipton, Z.C.: The doctor just won\u2019t accept that! arXiv preprint arXiv:1711.08037 (2017)"},{"issue":"5","key":"8_CR12","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin, C.: Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nat. Mach. Intell. 1(5), 206\u2013215 (2019)","journal-title":"Nat. Mach. Intell."},{"key":"8_CR13","unstructured":"Bordes, F., et al.: An introduction to vision-language modeling, arXiv preprint arXiv:2405.17247 (2024)"},{"key":"8_CR14","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030 (2017)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, volume 1 (long and short papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"8_CR16","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11\u00a0975\u201311\u00a0986 (2023)"},{"key":"8_CR17","unstructured":"Lavoie, S., et al.: Modeling caption diversity in contrastive vision-language pretraining, arXiv preprint arXiv:2405.00740 (2024)"},{"key":"8_CR18","unstructured":"Kwon, G., Cai, Z., Ravichandran, A., Bas, E., Bhotika, R., Soatto, S.: Masked vision and language modeling for multi-modal representation learning, arXiv preprint arXiv:2208.02131 (2022)"},{"key":"8_CR19","unstructured":"Singh, A., et al.: Flava: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15\u00a0638\u201315\u00a0650 (2022)"},{"key":"8_CR20","unstructured":"Yu, L., et al.: Scaling autoregressive multi-modal models: pretraining and instruction tuning. arXiv preprint arXiv:2309.02591 (2023)"},{"issue":"1","key":"8_CR21","doi-asserted-by":"publisher","first-page":"9613","DOI":"10.1038\/s41467-024-53450-8","volume":"15","author":"Y Gao","year":"2024","unstructured":"Gao, Y., et al.: An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer. Nat. Commun. 15(1), 9613 (2024)","journal-title":"Nat. Commun."},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Visual-linguistic diagnostic semantic enhancement for medical report generation. J. Biomed. Inf. 161, 104764 (2025). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1532046424001825","DOI":"10.1016\/j.jbi.2024.104764"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Rodriguez-Opazo, C., Teney, D., Gould, S.: Image retrieval on real-life images with pre-trained vision-and-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2125\u20132134 (2021)","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"8_CR24","unstructured":"Mann, B., et al.: Language models are few-shot learners, arXiv preprint arXiv:2005.14165, vol.\u00a01, p.\u00a03 (2020)"},{"key":"8_CR25","unstructured":"Petroni, F., et al.: Language models as knowledge bases? arXiv preprint arXiv:1909.01066 (2019)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Cui, L., Wu, Y., Liu, J., Yang, S., Zhang, Y.: Template-based named entity recognition using bart, arXiv preprint arXiv:2106.01760 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.161"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning, arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"8_CR28","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation, arXiv preprint arXiv:2101.00190 (2021)"},{"key":"8_CR29","unstructured":"Wang, Y., Jiang, X., Cheng, D., Zhao, X., Wang, Z., Li, D., Zhao, C.: Exploring interpretability for visual prompt tuning with hierarchical concepts, arXiv preprint arXiv:2503.06084 (2025)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Paiss, R., Chefer, H., Wolf, L.: No token left behind: explainability-aided image classification and generation. In: European Conference on Computer Vision, Springer, pp. 334\u2013350 (2022)","DOI":"10.1007\/978-3-031-19775-8_20"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 951\u2013958. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"8_CR32","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space, arXiv preprint arXiv:1301.3781 (2013)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"8_CR34","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, vol.\u00a026 (2013)"},{"key":"8_CR35","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":"8_CR36","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision. arxiv 2021, arXiv preprint arXiv:2111.11432 (2021)"},{"issue":"2","key":"8_CR37","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1109\/JBHI.2018.2824327","volume":"23","author":"J Kawahara","year":"2018","unstructured":"Kawahara, J., Daneshvar, S., Argenziano, G., Hamarneh, G.: Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE J. Biomed. Health Inform. 23(2), 538\u2013546 (2018)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Kermany, D.S., et\u00a0al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5), 1122\u20131131 (2018)","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"8_CR39","unstructured":"Codella, N., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (isic), arXiv preprint arXiv:1902.03368 (2019)"},{"key":"8_CR40","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale, arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"19","key":"8_CR41","doi-asserted-by":"publisher","first-page":"6578","DOI":"10.1016\/j.eswa.2015.04.034","volume":"42","author":"I Giotis","year":"2015","unstructured":"Giotis, I., Molders, N., Land, S., Biehl, M., Jonkman, M.F., Petkov, N.: Med-node: a computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert Syst. Appl. 42(19), 6578\u20136585 (2015)","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"8_CR42","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1038\/s41597-024-03387-w","volume":"11","author":"C Hern\u00e1ndez-P\u00e9rez","year":"2024","unstructured":"Hern\u00e1ndez-P\u00e9rez, C., et al.: Bcn20000: Dermoscopic lesions in the wild. Sci. Data 11(1), 641 (2024)","journal-title":"Sci. Data"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5679-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:37:01Z","timestamp":1768329421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5679-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556786","9789819556793"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5679-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}