{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T09:22:54Z","timestamp":1769764974128,"version":"3.49.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734700","type":"print"},{"value":"9783031734717","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T00:00:00Z","timestamp":1727481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T00:00:00Z","timestamp":1727481600000},"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\/978-3-031-73471-7_12","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T08:02:17Z","timestamp":1727856137000},"page":"113-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["UniCrossAdapter: Multimodal Adaptation of\u00a0CLIP for\u00a0Radiology Report Generation"],"prefix":"10.1007","author":[{"given":"Yaxiong","family":"Chen","sequence":"first","affiliation":[]},{"given":"Chuang","family":"Du","sequence":"additional","affiliation":[]},{"given":"Chunlei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jingliang","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Yilei","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Xiao Xiang","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Lichao","family":"Mou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,28]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.H., Wan, X.: Generating radiology reports via memory-driven Transformer. In: 2020 Conference on Empirical Methods in Natural Language Processing, pp. 1439\u20131449. (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., Pollard, T.J., Greenbaum, N.R., Lungren, M.P., Deng, C.Y., Peng, Y., Lu, Z., Mark, R.G., Berkowitz, S.J., Horng, S.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Shen, Y., Song, Y., Wan, X.: Cross-modal memory networks for radiology report generation. In: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 5904\u20135914. (2022)","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, X., Ge, S., Fan, W., Zou, Y.: Exploring and distilling posterior and prior knowledge for radiology report generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13753\u201313762. (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Qin, H., Song, Y.: Reinforced cross-modal alignment for radiology report generation. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 448\u2013458. (2022)","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Wang, J., Bhalerao, A., He, Y.: Cross-modal prototype driven network for radiology report generation. In: European Conference on Computer Vision, pp. 563\u2013579. (2022)","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"12_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102798","volume":"86","author":"S Yang","year":"2023","unstructured":"Yang, S., Wu, X., Ge, S., Zheng, Z., Zhou, S.K., Xiao, L.: Radiology report generation with a learned knowledge base and multi-modal alignment. Med. Image Anal. 86, 102798 (2023)","journal-title":"Med. Image Anal."},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, B., Chen, Z., Lin, H., Liang, X., Chang, X.: Dynamic graph enhanced contrastive learning for chest X-ray report generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3334\u20133343. (2023)","DOI":"10.1109\/CVPR52729.2023.00325"},{"issue":"2","key":"12_CR9","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D., Kohli, M.D., Rosenman, M.B., Shooshan, S.E., Rodriguez, L., Antani, S., Thoma, G.R., McDonald, C.J.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23(2), 304\u2013310 (2016)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: The 56th Annual Meeting of the Association for Computational Linguistics, pp. 2556\u20132565. (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568. (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"12_CR12","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. (2021)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Guo, D., Rush, A.M., Kim, Y.: Parameter-efficient transfer learning with diff pruning. In: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 4884\u20134896. (2021)","DOI":"10.18653\/v1\/2021.acl-long.378"},{"issue":"2","key":"12_CR14","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., Qiao, Y.: CLIP-Adapter: Better vision-language models with feature adapters. Int. J. Comput. Vision 132(2), 581\u2013595 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"12_CR15","unstructured":"Chen, S., Ge, C., Tong, Z., Wang, J., Song, Y., Wang, J., Luo, P.: AdaptFormer: Adapting vision Transformers for scalable visual recognition. In: Advances in Neural Information Processing Systems, pp. 16664\u201316678. (2022)"},{"issue":"9","key":"12_CR16","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":"12_CR17","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: LoRA: Low-Rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"12_CR18","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De Laroussilhe, Q., Gesmundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. (2019)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"R\u00fcckl\u00e9, A., Geigle, G., Glockner, M., Beck, T., Pfeiffer, J., Reimers, N., Gurevych, I.: AdapterDrop: On the efficiency of adapters in Transformers. In: 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7930\u20137946. (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.626"},{"key":"12_CR20","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"12_CR21","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 6000\u20136010. (2017)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Kong, M., Huang, Z., Kuang, K., Zhu, Q., Wu, F.: TranSQ: Transformer-based semantic query for medical report generation. In: International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 610\u2013620. (2022)","DOI":"10.1007\/978-3-031-16452-1_58"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., Li, S., Hu, Y., Tao, H.: A self-guided framework for radiology report generation. In: International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 588\u2013598. (2022)","DOI":"10.1007\/978-3-031-16452-1_56"},{"key":"12_CR24","unstructured":"Chen, X., Fang, H., Lin, T.Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A., Xu, D.: When radiology report generation meets knowledge graph. In: AAAI Conference on Artificial Intelligence, pp. 12910\u201312917. (2020)","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Liu, F., Ge, S., Wu, X.: Competence-based multimodal curriculum learning for medical report generation. In: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 3001\u20133012. (2021)","DOI":"10.18653\/v1\/2021.acl-long.234"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Nooralahzadeh, F., Gonzalez, N.P., Frauenfelder, T., Fujimoto, K., Krauthammer, M.: Progressive Transformer-based generation of radiology reports. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 2824\u20132832. (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"12_CR28","unstructured":"Chen, W., Liu, Y., Wang, C., Li, G., Zhu, J., Lin, L.: Visual-linguistic causal intervention for radiology report generation. arXiv preprint arXiv:2303.09117 (2023)"},{"key":"12_CR29","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1109\/TMM.2023.3273390","volume":"26","author":"K Zhang","year":"2024","unstructured":"Zhang, K., Jiang, H., Zhang, J., Huang, Q., Fan, J., Yu, J., Han, W.: Semi-supervised medical report generation via graph-guided hybrid feature consistency. IEEE Trans. Multimedia 26, 904\u2013915 (2024)","journal-title":"IEEE Trans. Multimedia"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Jin, H., Che, H., Lin, Y., Chen, H.: PromptMRG: Diagnosis-driven prompts for medical report generation. In: AAAI Conference on Artificial Intelligence, pp. 2607\u20132615. (2024)","DOI":"10.1609\/aaai.v38i3.28038"}],"container-title":["Lecture Notes in Computer Science","Foundation Models for General Medical AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73471-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T08:03:20Z","timestamp":1727856200000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73471-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,28]]},"ISBN":["9783031734700","9783031734717"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73471-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,28]]},"assertion":[{"value":"28 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MedAGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Foundation Models for General Medical AI","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"5 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"medagi2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/medagi.github.io\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}