{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:51:01Z","timestamp":1765309861807,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"name":"National Key Research and De- velopment Project","award":["Grant 2019YFE0110800"],"award-info":[{"award-number":["Grant 2019YFE0110800"]}]},{"name":"the National Natural Science Foundation of China","award":["Grants 62276040, 62276041, 62221005 and 61976031"],"award-info":[{"award-number":["Grants 62276040, 62276041, 62221005 and 61976031"]}]},{"name":"the National Key Research Instrument Development Program, China","award":["Grant 62027827"],"award-info":[{"award-number":["Grant 62027827"]}]},{"name":"Chongqing Educa-tion Commission Science and Technology Research Project","award":["Grant KJQN202200624"],"award-info":[{"award-number":["Grant KJQN202200624"]}]},{"name":"Chongqing Big Data Collaborative In-novation Center Funding","award":["Grant CQBDCIC202303"],"award-info":[{"award-number":["Grant CQBDCIC202303"]}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing","doi-asserted-by":"publisher","award":["Grant CSTB2022NSCQ-MSX0436)"],"award-info":[{"award-number":["Grant CSTB2022NSCQ-MSX0436)"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755336","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"4175-4184","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Pathology-Aware Reconstruction with Discriminative Knowledge Boosting Alignment for Che-Xray Vision-Language Pre-training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0138-2728","authenticated-orcid":false,"given":"Lihong","family":"Qiao","sequence":"first","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1250-0151","authenticated-orcid":false,"given":"Shiyi","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, ChongQing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5737-9571","authenticated-orcid":false,"given":"Yucheng","family":"Shu","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8469-5302","authenticated-orcid":false,"given":"Bin","family":"Xiao","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9033-8245","authenticated-orcid":false,"given":"Weisheng","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1443-0776","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The unified medical language system (UMLS): integrating biomedical terminology. Nucleic acids research","author":"Bodenreider Olivier","year":"2004","unstructured":"Olivier Bodenreider. 2004. The unified medical language system (UMLS): integrating biomedical terminology. Nucleic acids research, Vol. 32, suppl_1 (2004), D267-D270."},{"key":"e_1_3_2_1_2_1","volume-title":"Padchest: A large chest x-ray image dataset with multi-label annotated reports. Medical image analysis","author":"Bustos Aurelia","year":"2020","unstructured":"Aurelia Bustos, Antonio Pertusa, Jose-Maria Salinas, and Maria De La Iglesia-Vaya. 2020. Padchest: A large chest x-ray image dataset with multi-label annotated reports. Medical image analysis, Vol. 66 (2020), 101797."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_48"},{"key":"e_1_3_2_1_4_1","volume-title":"ProtoCLIP: Prototypical Contrastive Language Image Pretraining","author":"Chen Delong","year":"2023","unstructured":"Delong Chen, Zhao Wu, Fan Liu, Zaiquan Yang, Shaoqiu Zheng, Ying Tan, and Erjin Zhou. 2023b. ProtoCLIP: Prototypical Contrastive Language Image Pretraining. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_39"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"e_1_3_2_1_9_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_13_1","unstructured":"J Healthcare. 2020. Object-cxr-automatic detection of foreign objects on chest x-rays."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"e_1_3_2_1_16_1","volume-title":"Du Nguyen Duong, Tan Bui, Pierre Chambon, Yuhao Zhang, Matthew P Lungren, Andrew Y Ng, et al.","author":"Jain Saahil","year":"2021","unstructured":"Saahil Jain, Ashwin Agrawal, Adriel Saporta, Steven QH Truong, Du Nguyen Duong, Tan Bui, Pierre Chambon, Yuhao Zhang, Matthew P Lungren, Andrew Y Ng, et al., 2021. Radgraph: Extracting clinical entities and relations from radiology reports. arXiv preprint arXiv:2106.14463 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Honglak Lee, Kyunghoon Bae, and Edward Choi.","author":"Jang Jongseong","year":"2022","unstructured":"Jongseong Jang, Daeun Kyung, Seung Hwan Kim, Honglak Lee, Kyunghoon Bae, and Edward Choi. 2022. Significantly improving zero-shot x-ray pathology classification via fine-tuning pre-trained image-text encoders. arXiv preprint arXiv:2212.07050 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Better Representations. In International Conference on Learning Representations.","author":"Jiang Ziyu","year":"2023","unstructured":"Ziyu Jiang, Yinpeng Chen, Mengchen Liu, Dongdong Chen, Xiyang Dai, Lu Yuan, Zicheng Liu, and Zhangyang Wang. 2023. Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Better Representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","volume-title":"a de-identified publicly available database of chest radiographs with free-text reports. Scientific data","author":"Johnson Alistair EW","year":"2019","unstructured":"Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. 2019. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data, Vol. 6, 1 (2019), 317."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01059"},{"key":"e_1_3_2_1_22_1","unstructured":"C Steven G Langer. 2019. PhD and M. George Shih MD ''Siim-acr pneumothorax segmentation (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3070847"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294980"},{"key":"e_1_3_2_1_25_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_41"},{"key":"e_1_3_2_1_28_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_29_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention. Springer, 234-241."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"e_1_3_2_1_31_1","volume-title":"Medical vision language pretraining: A survey. arXiv preprint arXiv:2312.06224","author":"Shrestha Prashant","year":"2023","unstructured":"Prashant Shrestha, Sanskar Amgain, Bidur Khanal, Cristian A Linte, and Binod Bhattarai. 2023. Medical vision language pretraining: A survey. arXiv preprint arXiv:2312.06224 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"e_1_3_2_1_33_1","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio Yoshua Bengio et al. 2017. Graph attention networks. stat Vol. 1050 20 (2017) 10-48550."},{"key":"e_1_3_2_1_34_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wan Zhongwei","year":"2024","unstructured":"Zhongwei Wan, Che Liu, Mi Zhang, Jie Fu, Benyou Wang, Sibo Cheng, Lei Ma, C\u00e9sar Quilodr\u00e1n-Casas, and Rossella Arcucci. 2024. Med-unic: Unifying cross-lingual medical vision-language pre-training by diminishing bias. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_35_1","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume":"35","author":"Wang Fuying","year":"2022","unstructured":"Fuying Wang, Yuyin Zhou, Shujun Wang, Varut Vardhanabhuti, and Lequan Yu. 2022b. Multi-granularity cross-modal alignment for generalized medical visual representation learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 33536-33549.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"e_1_3_2_1_37_1","volume-title":"Zhong Qiu Lin, and Alexander Wong","author":"Wang Linda","year":"2020","unstructured":"Linda Wang, Zhong Qiu Lin, and Alexander Wong. 2020. Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific reports, Vol. 10, 1 (2020), 19549."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"e_1_3_2_1_39_1","volume-title":"Medclip: Contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163","author":"Wang Zifeng","year":"2022","unstructured":"Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, and Jimeng Sun. 2022a. Medclip: Contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163 (2022)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"e_1_3_2_1_41_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_2"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"e_1_3_2_1_44_1","volume-title":"Machine Learning for Healthcare Conference. PMLR, 2-25","author":"Zhang Yuhao","year":"2022","unstructured":"Yuhao Zhang, Hang Jiang, Yasuhide Miura, Christopher D Manning, and Curtis P Langlotz. 2022. Contrastive learning of medical visual representations from paired images and text. In Machine Learning for Healthcare Conference. PMLR, 2-25."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00425-9"},{"key":"e_1_3_2_1_46_1","volume-title":"Advancing Radiograph Representation Learning with Masked Record Modeling. In The Eleventh International Conference on Learning Representations.","author":"Zhou Hong-Yu","year":"2023","unstructured":"Hong-Yu Zhou, Chenyu Lian, Liansheng Wang, and Yizhou Yu. 2023. Advancing Radiograph Representation Learning with Masked Record Modeling. In The Eleventh International Conference on Learning Representations."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:50Z","timestamp":1765309610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"alternative-id":["10.1145\/3746027.3755336","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755336","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}