{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:05:44Z","timestamp":1770332744015,"version":"3.49.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732089","type":"print"},{"value":"9783031732096","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73209-6_2","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"18-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MedRAT: Unpaired Medical Report Generation via\u00a0Auxiliary Tasks"],"prefix":"10.1007","author":[{"given":"Elad","family":"Hirsch","sequence":"first","affiliation":[]},{"given":"Gefen","family":"Dawidowicz","sequence":"additional","affiliation":[]},{"given":"Ayellet","family":"Tal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"2_CR1","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization (2005)"},{"key":"2_CR2","unstructured":"Bengio, Y., Ducharme, R., Vincent, P.: A neural probabilistic language model. In: Advances in Neural Information Processing Systems, vol. 13 (2000)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Shen, Y., Song, Y., Wan, X.: Cross-modal memory networks for radiology report generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.H., Wan, X.: Generating radiology reports via memory-driven transformer. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Dawidowicz, G., Hirsch, E., Tal, A.: Limitr: leveraging local information for medical image-text representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 21165\u201321173 (2023)","DOI":"10.1109\/ICCV51070.2023.01935"},{"issue":"2","key":"2_CR7","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D., et al.: 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":"2_CR8","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Liu, W., Luo, J.: Unsupervised image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4125\u20134134 (2019)","DOI":"10.1109\/CVPR.2019.00425"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Gu, J., Joty, S., Cai, J., Wang, G.: Unpaired image captioning by language pivoting. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 503\u2013519 (2018)","DOI":"10.1007\/978-3-030-01246-5_31"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Joty, S., Cai, J., Zhao, H., Yang, X., Wang, G.: Unpaired image captioning via scene graph alignments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10323\u201310332 (2019)","DOI":"10.1109\/ICCV.2019.01042"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Gu, T., Liu, D., Li, Z., Cai, W.: Complex organ mask guided radiology report generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 7995\u20138004 (2024)","DOI":"10.1109\/WACV57701.2024.00781"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Venugopalan, S., Rohrbach, M., Mooney, R., Saenko, K., Darrell, T.: Deep compositional captioning: Describing novel object categories without paired training data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u201310 (2016)","DOI":"10.1109\/CVPR.2016.8"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hirsch, E., Dawidowicz, G., Tal, A.: Medcycle: unpaired medical report generation via cycle-consistency. In: Findings of the Association for Computational Linguistics: NAACL 2024, pp. 1929\u20131944 (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.125"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, X., Zhang, S.: Kiut: knowledge-injected u-transformer for radiology report generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19809\u201319818 (2023)","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Irvin, J., et\u00a0al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"2_CR17","unstructured":"Jing, B., Xie, P., Xing, E.: On the automatic generation of medical imaging reports. arXiv preprint arXiv:1711.08195 (2017)"},{"issue":"1","key":"2_CR18","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"Johnson, A.E., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","journal-title":"Sci. Data"},{"key":"2_CR19","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: Advance in Neural Information Processing System, vol. 33, pp. 18661\u201318673 (2020)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Navab, N.: Towards unsupervised image captioning with shared multimodal embeddings. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7414\u20137424 (2019)","DOI":"10.1109\/ICCV.2019.00751"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Li, C.Y., Liang, X., Hu, Z., Xing, E.P.: Knowledge-driven encode, retrieve, paraphrase for medical image report generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 6666\u20136673 (2019)","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, B., Cheng, X., Zhu, Z., Li, H., Zou, Y.: Unify, align and refine: multi-level semantic alignment for radiology report generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2863\u20132874 (2023)","DOI":"10.1109\/ICCV51070.2023.00268"},{"key":"2_CR23","unstructured":"Li, Y., Liang, X., Hu, Z., Xing, E.P.: Hybrid retrieval-generation reinforced agent for medical image report generation. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"2_CR24","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out. Association for Computational Linguistics (2004)"},{"key":"2_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014 Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"2_CR26","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: 5th International Conference on Learning Representations, ICLR (2017)"},{"key":"2_CR27","unstructured":"Liu, F., Gao, M., Zhang, T., Zou, Y.: Exploring semantic relationships for unpaired image captioning. arXiv preprint arXiv:2106.10658 (2021)"},{"key":"2_CR28","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13753\u201313762 (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"2_CR29","unstructured":"Liu, F., You, C., Wu, X., Ge, S., Sun, X., et al.: Auto-encoding knowledge graph for unsupervised medical report generation. In: Advance in Neural Information Processing System, vol. 34, pp. 16266\u201316279 (2021)"},{"key":"2_CR30","unstructured":"Liu, G., et al.: Clinically accurate chest x-ray report generation. In: Machine Learning for Healthcare Conference, pp. 249\u2013269. PMLR (2019)"},{"key":"2_CR31","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-031-20059-5_13","volume-title":"ECCV 2022 Part XXXVI","author":"Z Meng","year":"2022","unstructured":"Meng, Z., Yang, D., Cao, X., Shah, A., Lim, S.N.: Object-centric unsupervised image captioning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022 Part XXXVI. LNCS, vol. 13696, pp. 219\u2013235. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_13"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Miura, Y., Zhang, Y., Tsai, E., Langlotz, C., Jurafsky, D.: Improving factual completeness and consistency of image-to-text radiology report generation. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.naacl-main.416"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Nishino, T., et al.: Reinforcement learning with imbalanced dataset for data-to-text medical report generation. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 2223\u20132236 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.202"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Nizan, O., Tal, A.: Breaking the cycle-colleagues are all you need. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7860\u20137869 (2020)","DOI":"10.1109\/CVPR42600.2020.00788"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"2_CR36","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: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"issue":"2","key":"2_CR37","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., et al.: Yfcc100m: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","journal-title":"Commun. ACM"},{"key":"2_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Anne\u00a0Hendricks, L., Rohrbach, M., Mooney, R., Darrell, T., Saenko, K.: Captioning images with diverse objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5753\u20135761 (2017)","DOI":"10.1109\/CVPR.2017.130"},{"key":"2_CR40","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/978-3-031-19833-5_33","volume-title":"ECCV 2022 Part XXXV","author":"J Wang","year":"2022","unstructured":"Wang, J., Bhalerao, A., He, Y.: Cross-modal prototype driven network for radiology report generation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022 Part XXXV. LNCS, vol. 13695, pp. 563\u2013579. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_33"},{"key":"2_CR41","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1007\/978-3-031-16437-8_63","volume-title":"MICCAI 2022","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Tang, M., Wang, L., Li, X., Zhou, L.: A medical semantic-assisted transformer for radiographic report generation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13433, pp. 655\u2013664. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16437-8_63"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Yu, F., et\u00a0al.: Evaluating progress in automatic chest x-ray radiology report generation. Patterns 4(9) (2023)","DOI":"10.1016\/j.patter.2023.100802"},{"key":"2_CR43","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12910\u201312917 (2020)","DOI":"10.1609\/aaai.v34i07.6989"}],"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\/978-3-031-73209-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T12:22:49Z","timestamp":1744114969000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73209-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732089","9783031732096"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73209-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 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"}}]}}