{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:55:04Z","timestamp":1769849704532,"version":"3.49.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439896","type":"print"},{"value":"9783031439902","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43990-2_35","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"371-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Medical Phrase Grounding with\u00a0Region-Phrase Context Contrastive Alignment"],"prefix":"10.1007","author":[{"given":"Zhihao","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Anh","family":"Tran","sequence":"additional","affiliation":[]},{"given":"Junting","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Wan","sequence":"additional","affiliation":[]},{"given":"Gideon Su Kai","family":"Ooi","sequence":"additional","affiliation":[]},{"given":"Lionel Tim-Ee","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Choon Hua","family":"Thng","sequence":"additional","affiliation":[]},{"given":"Xinxing","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"35_CR1","doi-asserted-by":"publisher","unstructured":"Boecking, B., et al.: Making the most of text semantics to improve biomedical vision-language processing. In: Avidan, S., Brostow, G., Ciss\u00e9 M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13696, pp. 1\u201321. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_1","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"35_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Li, B.: Multi-modal dynamic graph transformer for visual grounding. In: proceedings of CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TranSVG: end-to-end visual grounding with transformers. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"35_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: Proceedings of ICLR (2021)"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Z., Liu, Q., Wang, Y.: Visual grounding with transformers. In: Proceedings of ICME (2022)","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"35_CR8","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of International Conference on Artificial Intelligence and Statistics (2010)"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR10","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 ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"issue":"1","key":"35_CR11","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"Johnson, A.E., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","journal-title":"Sci. Data"},{"key":"35_CR12","unstructured":"Johnson, A.E., Pollard, T.J., Mark, R.G., Berkowitz, S.J., Horng, S.: MIMIC-CXR database (version 2.0.0). In: PhysioNet (2019)"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"35_CR14","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT (2019)"},{"key":"35_CR15","unstructured":"Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. In: Proceedings of NeurIPS (2021)"},{"key":"35_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of ICLR (2019)"},{"key":"35_CR17","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"35_CR18","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of NeurIPS (2019)"},{"key":"35_CR19","unstructured":"Qin, Z., Yi, H., Lao, Q., Li, K.: Medical image understanding with pretrained vision language models: a comprehensive study. In: Proceedings of ICLR (2023)"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MattNet: modular attention network for referring expression comprehension. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"35_CR24","doi-asserted-by":"publisher","unstructured":"Zhu, C., et al.: SeqTR: a simple yet universal network for visual grounding. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13695. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_35","DOI":"10.1007\/978-3-031-19833-5_35"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43990-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T15:39:40Z","timestamp":1710171580000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43990-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439896","9783031439902"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43990-2_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","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":"2250","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":"730","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":"32% - 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","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":"5","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)"}}]}}