{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T13:01:53Z","timestamp":1780318913680,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20211307"],"award-info":[{"award-number":["BK20211307"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679668","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"2742-2752","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["CLR2G: Cross modal Contrastive Learning on Radiology Report Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8325-5799","authenticated-orcid":false,"given":"Hongchen","family":"Xue","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2418-090X","authenticated-orcid":false,"given":"Qingzhi","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8980-4950","authenticated-orcid":false,"given":"Guanfeng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3212-7618","authenticated-orcid":false,"given":"Jianfeng","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6983-8088","authenticated-orcid":false,"given":"Yuanjun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6368-576X","authenticated-orcid":false,"given":"An","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"72","volume-title":"Proceedings of the 2nd Clinical Natural Language Processing Workshop. Ed. by Anna Rumshisky et al","author":"Emily","year":"2019","unstructured":"Emily Alsentzer et al. 'Publicly Available Clinical BERT Embeddings'. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop. Ed. by Anna Rumshisky et al. Minneapolis, Minnesota, USA: Association for Computational Linguistics, June 2019, pp. 72--78."},{"key":"e_1_3_2_1_2_1","first-page":"65","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization.","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. '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, pp. 65--72."},{"key":"e_1_3_2_1_3_1","first-page":"126","volume-title":"PMLR.","author":"William","year":"2020","unstructured":"William Boag et al. 'Baselines for chest x-ray report generation'. In: Machine learning for health workshop. PMLR. 2020, pp. 126--140."},{"key":"e_1_3_2_1_4_1","first-page":"415","volume-title":"International Conference on Database Systems for Advanced Applications. Springer.","author":"Yiming","year":"2023","unstructured":"Yiming Cao et al. 'CMT: Cross-modal Memory Transformer for Medical Image Report Generation'. In: International Conference on Database Systems for Advanced Applications. Springer. 2023, pp. 415--424."},{"key":"e_1_3_2_1_5_1","first-page":"117","volume-title":"International Conference on Database Systems for Advanced Applications. Springer.","author":"Yiming","year":"2022","unstructured":"Yiming Cao et al. 'Kdtnet: medical image report generation via knowledge-driven transformer'. In: International Conference on Database Systems for Advanced Applications. Springer. 2022, pp. 117--132."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Zhihong Chen et al. '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). Ed. by Chengqing Zong et al. Online: Association for Computational Linguistics Aug. 2022 pp. 5904--5914.","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"e_1_3_2_1_7_1","first-page":"1439","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Ed. by Bonnie Webber et al. Online: Association for Computational Linguistics","author":"Zhihong","year":"2020","unstructured":"Zhihong Chen et al. 'Generating Radiology Reports via Memory-driven Transformer'. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Ed. by Bonnie Webber et al. Online: Association for Computational Linguistics, Nov. 2020, pp. 1439--1449."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"e_1_3_2_1_10_1","first-page":"10578","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","author":"Marcella","year":"2020","unstructured":"Marcella Cornia et al. 'Meshed-memory transformer for image captioning'. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020, pp. 10578--10587."},{"key":"e_1_3_2_1_11_1","first-page":"2","volume":"2","author":"Demner-Fushman Dina","year":"2016","unstructured":"Dina Demner-Fushman et al. 'Preparing a collection of radiology examinations for distribution and retrieval'. In: Journal of the American Medical Informatics Association 23.2 (2016), pp. 304--310.","journal-title":"Journal of the American Medical Informatics Association"},{"key":"e_1_3_2_1_12_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Alexey","year":"2021","unstructured":"Alexey Dosovitskiy et al. 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net, 2021. url: https:\/\/openreview.net\/forum?id=YicbFdNTTy."},{"key":"e_1_3_2_1_13_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Xiuye","year":"2022","unstructured":"Xiuye Gu et al. 'Open-vocabulary Object Detection via Vision and Language Knowledge Distillation'. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net, 2022. url: https:\/\/openreview.net\/forum?id=lL3lnMbR4WU."},{"key":"e_1_3_2_1_14_1","first-page":"3942","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision.","author":"Shih-Cheng","year":"2021","unstructured":"Shih-Cheng Huang et al. 'Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition'. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021, pp. 3942--3951."},{"key":"e_1_3_2_1_15_1","first-page":"590","volume-title":"Proceedings of the AAAI conference on artificial intelligence.","volume":"33","author":"Jeremy","unstructured":"Jeremy Irvin et al. 'Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison'. In: Proceedings of the AAAI conference on artificial intelligence. Vol. 33. 01. 2019, pp. 590--597."},{"key":"e_1_3_2_1_16_1","first-page":"1655","volume-title":"Proceedings of the AAAI conference on artificial intelligence.","volume":"35","author":"Jiayi","year":"2021","unstructured":"Jiayi Ji 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. 2. 2021, pp. 1655--1663."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Ed. by Iryna Gurevych and Yusuke Miyao","author":"Jing Baoyu","unstructured":"Baoyu Jing, Pengtao Xie, and Eric Xing. '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). Ed. by Iryna Gurevych and Yusuke Miyao. Melbourne, Australia: Association for Computational Linguistics, July 2018, pp. 2577--2586."},{"key":"e_1_3_2_1_19_1","volume-title":"MIMIC-CXR database (version 2.0. 0)'. In: physionet 2","author":"A Johnson","year":"2019","unstructured":"A Johnson et al. 'MIMIC-CXR database (version 2.0. 0)'. In: physionet 2 (2019), p. 5."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01062"},{"key":"e_1_3_2_1_21_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Boyi","year":"2022","unstructured":"Boyi Li et al. 'Language-driven Semantic Segmentation'. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net, 2022. url: https:\/\/openreview.net\/forum?id=RriDjddCLN."},{"key":"e_1_3_2_1_22_1","first-page":"1","volume":"2","author":"Mingjie Li","year":"2023","unstructured":"Mingjie Li et al. 'Auxiliary signal-guided knowledge encoder-decoder for medical report generation'. In: World Wide Web 26.1 (2023), pp. 253--270.","journal-title":"World Wide Web"},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in neural information processing systems 31","author":"Yuan Li","year":"2018","unstructured":"Yuan Li et al. 'Hybrid retrieval-generation reinforced agent for medical image report generation'. In: Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_24_1","first-page":"16266","volume":"34","author":"Fenglin Liu","year":"2021","unstructured":"Fenglin Liu et al. 'Auto-encoding knowledge graph for unsupervised medical report generation'. In: Advances in Neural Information Processing Systems 34 (2021), pp. 16266--16279.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_26_1","first-page":"13753","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","author":"Fenglin","year":"2021","unstructured":"Fenglin Liu et al. 'Exploring and distilling posterior and prior knowledge for radiology report generation'. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2021, pp. 13753--13762."},{"key":"e_1_3_2_1_27_1","first-page":"249","volume-title":"Machine Learning for Healthcare Conference. PMLR.","author":"Guanxiong","year":"2019","unstructured":"Guanxiong Liu et al. 'Clinically accurate chest x-ray report generation'. In: Machine Learning for Healthcare Conference. PMLR. 2019, pp. 249--269."},{"key":"e_1_3_2_1_28_1","first-page":"375","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition.","author":"Jiasen","year":"2017","unstructured":"Jiasen Lu et al. '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. 2017, pp. 375--383."},{"key":"e_1_3_2_1_29_1","first-page":"311","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics.","author":"Kishore","year":"2002","unstructured":"Kishore Papineni et al. 'Bleu: a method for automatic evaluation of machine translation'. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 2002, pp. 311--318."},{"key":"e_1_3_2_1_30_1","volume-title":"Inspecting state of the art performance and NLP metrics in image-based medical report generation'. In: arXiv preprint arXiv:2011.09257","author":"Pablo Pino","year":"2020","unstructured":"Pablo Pino et al. 'Inspecting state of the art performance and NLP metrics in image-based medical report generation'. In: arXiv preprint arXiv:2011.09257 (2020)."},{"key":"e_1_3_2_1_31_1","first-page":"8748","volume-title":"International conference on machine learning. PMLR.","author":"Alec","year":"2021","unstructured":"Alec Radford et al. 'Learning transferable visual models from natural language supervision'. In: International conference on machine learning. PMLR. 2021, pp. 8748--8763."},{"key":"e_1_3_2_1_32_1","first-page":"2","volume":"14","author":"Suhail Raoof","year":"2012","unstructured":"Suhail Raoof et al. 'Interpretation of plain chest roentgenogram'. In: Chest 141.2 (2012), pp. 545--558.","journal-title":"Chest"},{"key":"e_1_3_2_1_33_1","first-page":"7008","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition.","author":"Steven","year":"2017","unstructured":"Steven J Rennie et al. 'Self-critical sequence training for image captioning'. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, pp. 7008--7024."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of Workshop on Text Summarization of ACL, Spain.","volume":"5","author":"Rouge Lin CY","year":"2004","unstructured":"Lin CY Rouge. 'A package for automatic evaluation of summaries'. In: Proceedings of Workshop on Text Summarization of ACL, Spain. Vol. 5. 2004."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.15389"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-45382-3_4"},{"key":"e_1_3_2_1_37_1","volume-title":"Advances in neural information processing systems 30","author":"Ashish Vaswani","year":"2017","unstructured":"Ashish Vaswani et al. 'Attention is all you need'. In: Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_38_1","first-page":"3156","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition.","author":"Oriol","year":"2015","unstructured":"Oriol Vinyals et al. 'Show and tell: A neural image caption generator'. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015, pp. 3156--3164."},{"key":"e_1_3_2_1_39_1","first-page":"9049","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition.","author":"Xiaosong","year":"2018","unstructured":"Xiaosong Wang et al. 'Tienet: Text-image embedding network for common thorax disease classification and reporting in chest x-rays'. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, pp. 9049--9058."},{"key":"e_1_3_2_1_40_1","first-page":"655","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer.","author":"Zhanyu","year":"2022","unstructured":"Zhanyu Wang et al. 'A medical semantic-assisted transformer for radiographic report generation'. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer. 2022, pp. 655--664."},{"key":"e_1_3_2_1_41_1","first-page":"11558","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Zhanyu","year":"2023","unstructured":"Zhanyu Wang et al. 'Metransformer: Radiology report generation by transformer with multiple learnable expert tokens'. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023, pp. 11558--11567."},{"key":"e_1_3_2_1_42_1","volume-title":"Medclip: Contrastive learning from unpaired medical images and text'. In: arXiv preprint arXiv:2210.10163","author":"Zifeng Wang","year":"2022","unstructured":"Zifeng Wang et al. 'Medclip: Contrastive learning from unpaired medical images and text'. In: arXiv preprint arXiv:2210.10163 (2022)."},{"key":"e_1_3_2_1_43_1","first-page":"2048","volume-title":"International conference on machine learning. PMLR.","author":"Kelvin","year":"2015","unstructured":"Kelvin Xu et al. 'Show, attend and tell: Neural image caption generation with visual attention'. In: International conference on machine learning. PMLR. 2015, pp. 2048--2057."},{"key":"e_1_3_2_1_44_1","first-page":"457","volume-title":"Medical Image Computing and Computer Assisted Intervention--MICCAI 2018: 21st International Conference, Granada, Spain, September 16--20","author":"Yuan Xue","year":"2018","unstructured":"Yuan Xue et al. 'Multimodal recurrent model with attention for automated radiology report generation'. In: Medical Image Computing and Computer Assisted Intervention--MICCAI 2018: 21st International Conference, Granada, Spain, September 16--20, 2018, Proceedings, Part I. Springer. 2018, pp. 457--466."},{"key":"e_1_3_2_1_45_1","first-page":"102798","volume-title":"Medical Image Analysis 86","author":"Shuxin","year":"2023","unstructured":"Shuxin Yang et al. 'Radiology report generation with a learned knowledge base and multi-modal alignment'. In: Medical Image Analysis 86 (2023), p. 102798."},{"key":"e_1_3_2_1_46_1","first-page":"721","volume-title":"Medical Image Computing and Computer Assisted Intervention--MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13--17","author":"Jianbo Yuan","year":"2019","unstructured":"Jianbo Yuan et al. 'Automatic radiology report generation based on multi-view image fusion and medical concept enrichment'. In: Medical Image Computing and Computer Assisted Intervention--MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13--17, 2019, Proceedings, Part VI 22. Springer. 2019, pp. 721--729."},{"key":"e_1_3_2_1_47_1","first-page":"1","volume":"1","author":"Xiaoman Zhang","year":"2023","unstructured":"Xiaoman Zhang et al. 'Knowledge-enhanced visual-language pre-training on chest radiology images'. In: Nature Communications 14.1 (2023), p. 4542.","journal-title":"Nature Communications"},{"key":"e_1_3_2_1_48_1","first-page":"15465","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","author":"Xuying","year":"2021","unstructured":"Xuying Zhang et al. 'Rstnet: Captioning with adaptive attention on visual and non-visual words'. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2021, pp. 15465--15474."},{"key":"e_1_3_2_1_49_1","first-page":"12910","volume-title":"Proceedings of the AAAI conference on artificial intelligence.","volume":"34","author":"Yixiao","unstructured":"Yixiao Zhang et al. 'When radiology report generation meets knowledge graph'. In: Proceedings of the AAAI conference on artificial intelligence. Vol. 34. 07. 2020, pp. 12910--12917."},{"key":"e_1_3_2_1_50_1","first-page":"2","volume-title":"Machine Learning for Healthcare Conference. PMLR.","author":"Yuhao","year":"2022","unstructured":"Yuhao Zhang et al. 'Contrastive learning of medical visual representations from paired images and text'. In: Machine Learning for Healthcare Conference. PMLR. 2022, pp. 2--25."}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679668","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:13Z","timestamp":1750294693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":50,"alternative-id":["10.1145\/3627673.3679668","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679668","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}