{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:36:23Z","timestamp":1782394583273,"version":"3.54.5"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031917202","type":"print"},{"value":"9783031917219","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91721-9_2","type":"book-chapter","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T05:03:33Z","timestamp":1748495013000},"page":"16-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with\u00a0Multilevel Semantic Granularity"],"prefix":"10.1007","author":[{"given":"Hanqi","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixuan","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhou","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruimao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"2_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Alsentzer, E., et al.: Publicly available clinical BERT embeddings. arXiv preprint arXiv:1904.03323 (2019)","DOI":"10.18653\/v1\/W19-1909"},{"key":"2_CR3","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: VQA-Med: overview of the medical visual question answering task at ImageCLEF 2019. In: Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes. 9-12 September 2019 (2019)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Bodenreider, O.: The unified medical language system (UMLS): integrating biomedical terminology. Nucleic Acids Res. 32(suppl_1), D267\u2013D270 (2004)","DOI":"10.1093\/nar\/gkh061"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Boecking, B., et\u00a0al.: Making the most of text semantics to improve biomedical vision\u2013language processing. In: European Conference on Computer Vision, pp. 1\u201321. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"2_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"2_CR7","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: universal image-text representation learning. In: European Conference on Computer Vision, pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Diao, S., Wang, B., Li, G., Wan, X.: Towards unifying medical vision-and-language pre-training via soft prompts. arXiv preprint arXiv:2302.08958 (2023)","DOI":"10.1109\/ICCV51070.2023.02139"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 679\u2013689. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, G., Wan, X.: Align, reason and learn: enhancing medical vision-and-language pre-training with knowledge. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5152\u20135161 (2022)","DOI":"10.1145\/3503161.3547948"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, P., Lin, L., Lyu, J., Huang, Y., Luo, W., Tang, X.: PRIOR: prototype representation joint learning from medical images and reports. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"2_CR13","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2_CR17","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_CR18","doi-asserted-by":"crossref","unstructured":"Hu, J., Li, J., Chen, Z., Shen, Y., Song, Y., Wan, X., Chang, T.H.: Word graph guided summarization for radiology findings. arXiv preprint arXiv:2112.09925 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.441"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Hu, J., Li, Z., Chen, Z., Li, Z., Wan, X., Chang, T.H.: Graph enhanced contrastive learning for radiology findings summarization. arXiv preprint arXiv:2204.00203 (2022)","DOI":"10.18653\/v1\/2022.acl-long.320"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Shen, L., Lungren, M.P., Yeung, S.: 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, pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Irvin, J., Rajpurkar, P., 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_CR22","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"2_CR23","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":"2_CR24","doi-asserted-by":"crossref","unstructured":"Khare, Y., Bagal, V., Mathew, M., Devi, A., Priyakumar, U.D., Jawahar, C.: MMBERT: multimodal BERT pretraining for improved medical VQA. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1033\u20131036. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"2_CR25","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"issue":"1","key":"2_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5(1), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a034, pp. 11336\u201311344 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"2_CR28","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"2_CR29","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Li, X., et\u00a0al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXX 16, pp. 121\u2013137. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"2_CR31","unstructured":"Li, Y., et al.: Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Wu, X.M.: Contrastive pre-training and representation distillation for medical visual question answering based on radiology images. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part II 24, pp. 210\u2013220. Springer (2021)","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"2_CR34","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"2_CR35","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"issue":"12","key":"2_CR36","doi-asserted-by":"publisher","first-page":"6070","DOI":"10.1109\/JBHI.2022.3207502","volume":"26","author":"JH Moon","year":"2022","unstructured":"Moon, J.H., Lee, H., Shin, W., Kim, Y.H., Choi, E.: Multi-modal understanding and generation for medical images and text via vision-language pre-training. IEEE J. Biomed. Health Inform. 26(12), 6070\u20136080 (2022)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: SLIP: self-supervision meets language-image pre-training. In: European Conference on Computer Vision, pp. 529\u2013544. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Kaissis, G., Zou, C., Rueckert, D.: Joint learning of localized representations from medical images and reports. In: European Conference on Computer Vision, pp. 685\u2013701. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"2_CR39","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR40","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Shih, G., et\u00a0al.: Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia. Radiol. Artif. Intell. 1(1), e180041 (2019)","DOI":"10.1148\/ryai.2019180041"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: FLAVA: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15638\u201315650 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"2_CR44","unstructured":"Sotudeh, S., Goharian, N., Filice, R.W.: Attend to medical ontologies: Content selection for clinical abstractive summarization. arXiv preprint arXiv:2005.00163 (2020)"},{"key":"2_CR45","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J.: VL-BERT: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"2_CR47","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"2_CR48","first-page":"33536","volume":"35","author":"F Wang","year":"2022","unstructured":"Wang, F., Zhou, Y., Wang, S., Vardhanabhuti, V., Yu, L.: Multi-granularity cross-modal alignment for generalized medical visual representation learning. Adv. Neural. Inf. Process. Syst. 35, 33536\u201333549 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR49","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: Simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"2_CR50","unstructured":"Yao, L., et al.: FILIP: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)"},{"key":"2_CR51","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12104\u201312113 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"2_CR53","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. In: Machine Learning for Healthcare Conference, pp. 2\u201325. PMLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91721-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T05:03:54Z","timestamp":1748495034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91721-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031917202","9783031917219"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91721-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}