{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:23:57Z","timestamp":1778171037811,"version":"3.51.4"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198328","type":"print"},{"value":"9783031198335","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19833-5_33","type":"book-chapter","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:40:30Z","timestamp":1667522430000},"page":"563-579","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Cross-Modal Prototype Driven Network for\u00a0Radiology Report Generation"],"prefix":"10.1007","author":[{"given":"Jun","family":"Wang","sequence":"first","affiliation":[]},{"given":"Abhir","family":"Bhalerao","sequence":"additional","affiliation":[]},{"given":"Yulan","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Bao, G., Zhang, Y., Teng, Z., Chen, B., Luo, W.: G-transformer for document-level machine translation. 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. 3442\u20133455 (2021)","DOI":"10.18653\/v1\/2021.acl-long.267"},{"key":"33_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 (Volume 1: Long Papers), pp. 5904\u20135914 (2021)","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, J., Fostiropoulos, I., Boehm, B., Soleymani, M.: Multimodal phased transformer for sentiment analysis. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2447\u20132458 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"33_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 Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"issue":"2","key":"33_CR6","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":"33_CR7","unstructured":"Denkowski, M., Lavie, A.: Meteor 1.3: automatic metric for reliable optimization and evaluation of machine translation systems. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 85\u201391 (2011)"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., Yao, P., Lu, S., Lu, H.: Normalized and geometry-aware self-attention network for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10327\u201310336 (2020)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"33_CR9","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":"33_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-030-87234-2_28","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"B Hou","year":"2021","unstructured":"Hou, B., Kaissis, G., Summers, R.M., Kainz, B.: RATCHET: medical transformer for\u00a0chest X-ray diagnosis and reporting. In: de Bruijne, M. (ed.) MICCAI 2021. LNCS, vol. 12907, pp. 293\u2013303. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87234-2_28"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Ji, J., et al.: Improving image captioning by leveraging intra-and inter-layer global representation in transformer network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1655\u20131663 (2021)","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Jing, B., Wang, Z., Xing, E.: Show, describe and conclude: on exploiting the structure information of chest x-ray reports. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6570\u20136580 (2019)","DOI":"10.18653\/v1\/P19-1657"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Jing, B., Xie, P., Xing, E.: On the automatic generation of medical imaging reports. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2577\u20132586 (2018)","DOI":"10.18653\/v1\/P18-1240"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: 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":"33_CR15","doi-asserted-by":"crossref","unstructured":"Kacupaj, E., Plepi, J., Singh, K., Thakkar, H., Lehmann, J., Maleshkova, M.: Conversational question answering over knowledge graphs with transformer and graph attention networks. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 850\u2013862 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.72"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Krause, J., Johnson, J., Krishna, R., Fei-Fei, L.: A hierarchical approach for generating descriptive image paragraphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 317\u2013325 (2017)","DOI":"10.1109\/CVPR.2017.356"},{"key":"33_CR17","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. 33, pp. 6666\u20136673 (2019)","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"33_CR18","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 31 (2018)"},{"key":"33_CR19","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Liu, F., Ren, X., Liu, Y., Wang, H., Sun, X.: simNet: stepwise image-topic merging network for generating detailed and comprehensive image captions. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 137\u2013149 (2018)","DOI":"10.18653\/v1\/D18-1013"},{"key":"33_CR21","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 Conference on Computer Vision and Pattern Recognition, pp. 13753\u201313762 (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"33_CR22","unstructured":"Liu, G., et al.: Clinically accurate chest X-ray report generation. In: Machine Learning for Healthcare Conference, pp. 249\u2013269. PMLR (2019)"},{"issue":"2","key":"33_CR23","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"33_CR25","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Melas-Kyriazi, L., Rush, A.M., Han, G.: Training for diversity in image paragraph captioning. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 757\u2013761 (2018)","DOI":"10.18653\/v1\/D18-1084"},{"key":"33_CR27","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, pp. 5288\u20135304 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.416"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Naseem, T., et al.: A semantics-aware transformer model of relation linking for knowledge base question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 256\u2013262 (2021)","DOI":"10.18653\/v1\/2021.acl-short.34"},{"key":"33_CR29","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":"33_CR30","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"33_CR31","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, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Pei, W., Zhang, J., Wang, X., Ke, L., Shen, X., Tai, Y.W.: Memory-attended recurrent network for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8347\u20138356 (2019)","DOI":"10.1109\/CVPR.2019.00854"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Smit, A., Jain, S., Rajpurkar, P., Pareek, A., Ng, A.Y., Lungren, M.: Combining automatic labelers and expert annotations for accurate radiology report labeling using BERT. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1500\u20131519 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"33_CR35","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R., et al.: End-to-end memory networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"33_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Wang, J., Tang, J., Luo, J.: Multimodal attention with image text spatial relationship for OCR-based image captioning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4337\u20134345 (2020)","DOI":"10.1145\/3394171.3413753"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Learning deep transformer models for machine translation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1810\u20131822 (2019)","DOI":"10.18653\/v1\/P19-1176"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wan, Z., Wan, X.: TransModality: an End2End fusion method with transformer for multimodal sentiment analysis. In: Proceedings of The Web Conference 2020, pp. 2514\u20132520 (2020)","DOI":"10.1145\/3366423.3380000"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Yang, K., Xu, H., Gao, K.: CM-BERT: cross-modal BERT for text-audio sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 521\u2013528 (2020)","DOI":"10.1145\/3394171.3413690"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"33_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Improving the transformer translation model with document-level context. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 533\u2013542 (2018)","DOI":"10.18653\/v1\/D18-1049"},{"key":"33_CR44","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. 34, pp. 12910\u201312917 (2020)","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"33_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, X., Xiao, F., Zhong, H., Yao, J., Chen, H.: Condition aware and revise transformer for question answering. In: Proceedings of The Web Conference 2020, pp. 2377\u20132387 (2020)","DOI":"10.1145\/3366423.3380301"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19833-5_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T15:43:59Z","timestamp":1673279039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19833-5_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198328","9783031198335"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19833-5_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}