{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T16:13:19Z","timestamp":1777392799100,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62172101"],"award-info":[{"award-number":["No.62172101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Municipal Hospital Frontier Joint Research Project","award":["SHDC12024136"],"award-info":[{"award-number":["SHDC12024136"]}]},{"DOI":"10.13039\/501100003347","name":"Fudan University","doi-asserted-by":"publisher","award":["EKYX202409"],"award-info":[{"award-number":["EKYX202409"]}],"id":[{"id":"10.13039\/501100003347","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\/3746027.3754991","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"3133-3142","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Semantic-Aware Hard Negative Mining for Medical Vision-Language Contrastive Pretraining"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0499-2192","authenticated-orcid":false,"given":"Yongxin","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-3998","authenticated-orcid":false,"given":"Ying","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0936-470X","authenticated-orcid":false,"given":"Yaning","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0440-8516","authenticated-orcid":false,"given":"Wen","family":"He","sequence":"additional","affiliation":[{"name":"National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6252-2565","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4747-0574","authenticated-orcid":false,"given":"Rui","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China, National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China, and College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-5414","authenticated-orcid":false,"given":"Xiaobo","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, 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":"Publicly available clinical BERT embeddings. arXiv preprint arXiv:1904.03323","author":"Alsentzer Emily","year":"2019","unstructured":"Emily Alsentzer, John R Murphy, Willie Boag, Wei-Hung Weng, Di Jin, Tristan Naumann, and Matthew McDermott. 2019. Publicly available clinical BERT embeddings. arXiv preprint arXiv:1904.03323 (2019)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"e_1_3_2_1_3_1","volume-title":"INCREMENTAL FALSE NEGATIVE DETECTION FOR CONTRASTIVE LEARNING. In 10th International Conference on Learning Representations, ICLR","author":"Chen Tsai Shien","year":"2022","unstructured":"Tsai Shien Chen, Wei Chih Hung, Hung Yu Tseng, Shao Yi Chien, and Ming Hsuan Yang. 2022a. INCREMENTAL FALSE NEGATIVE DETECTION FOR CONTRASTIVE LEARNING. In 10th International Conference on Learning Representations, ICLR 2022."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"e_1_3_2_1_6_1","volume-title":"Debiased contrastive learning. Advances in neural information processing systems","author":"Chuang Ching-Yao","year":"2020","unstructured":"Ching-Yao Chuang, Joshua Robinson, Yen-Chen Lin, Antonio Torralba, and Stefanie Jegelka. 2020. Debiased contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 8765-8775."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Jeffrey De Fauw Joseph R Ledsam Bernardino Romera-Paredes Stanislav Nikolov Nenad Tomasev Sam Blackwell Harry Askham Xavier Glorot Brendan O'Donoghue Daniel Visentin et al. 2018. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature medicine Vol. 24 9 (2018) 1342-1350.","DOI":"10.1038\/s41591-018-0107-6"},{"key":"e_1_3_2_1_8_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_9_1","volume-title":"Dermatologist-level classification of skin cancer with deep neural networks. nature","author":"Esteva Andre","year":"2017","unstructured":"Andre Esteva, Brett Kuprel, Roberto A Novoa, Justin Ko, Susan M Swetter, Helen M Blau, and Sebastian Thrun. 2017. Dermatologist-level classification of skin cancer with deep neural networks. nature, Vol. 542, 7639 (2017), 115-118."},{"key":"e_1_3_2_1_10_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00106"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"e_1_3_2_1_15_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_16_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. 2019a. 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_17_1","volume-title":"a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042","author":"Johnson Alistair EW","year":"2019","unstructured":"Alistair EW Johnson, Tom J Pollard, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Yifan Peng, Zhiyong Lu, Roger G Mark, Seth J Berkowitz, and Steven Horng. 2019b. MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)."},{"key":"e_1_3_2_1_18_1","volume-title":"Noe Pion, Philippe Weinzaepfel, and Diane Larlus.","author":"Kalantidis Yannis","year":"2020","unstructured":"Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel, and Diane Larlus. 2020. Hard negative mixing for contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 21798-21809."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_8"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01112"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294980"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_61"},{"key":"e_1_3_2_1_23_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"e_1_3_2_1_26_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_27_1","first-page":"188","article-title":"NegBio: a high-performance tool for negation and uncertainty detection in radiology reports","volume":"2018","author":"Peng Yifan","year":"2018","unstructured":"Yifan Peng, Xiaosong Wang, Le Lu, Mohammadhadi Bagheri, Ronald Summers, and Zhiyong Lu. 2018. NegBio: a high-performance tool for negation and uncertainty detection in radiology reports. AMIA Summits on Translational Science Proceedings, Vol. 2018 (2018), 188.","journal-title":"AMIA Summits on Translational Science Proceedings"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Pranav Rajpurkar Jeremy Irvin Robyn L Ball Kaylie Zhu Brandon Yang Hershel Mehta Tony Duan Daisy Ding Aarti Bagul Curtis P Langlotz et al. 2018. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS medicine Vol. 15 11 (2018) e1002686.","DOI":"10.1371\/journal.pmed.1002686"},{"key":"e_1_3_2_1_31_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"CONTRASTIVE LEARNING WITH HARD NEGATIVE SAMPLES. In International Conference on Learning Representations (ICLR).","author":"Robinson Joshua","year":"2021","unstructured":"Joshua Robinson, Ching-Yao Chuang, Suvrit Sra, and Stefanie Jegelka. 2021. CONTRASTIVE LEARNING WITH HARD NEGATIVE SAMPLES. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_33_1","first-page":"234","volume-title":"Munich","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-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"e_1_3_2_1_36_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_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","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"e_1_3_2_1_42_1","unstructured":"Anna Zawacki Carol Wu George Shih Julia Elliott Mikhail Fomitchev Mohannad Hussain ParasLakhani Phil Culliton and Shunxing Bao. 2019. SIIM-ACR Pneumothorax Segmentation. https:\/\/kaggle.com\/competitions\/siim-acr-pneumothorax-segmentation. Kaggle."},{"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","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text. In Machine learning for healthcare conference","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.","journal-title":"PMLR"},{"key":"e_1_3_2_1_45_1","volume-title":"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. International Conference on Learning Representations (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:39Z","timestamp":1765340079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754991"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":45,"alternative-id":["10.1145\/3746027.3754991","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754991","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"}}]}}