{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:48:59Z","timestamp":1771026539389,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030871956","type":"print"},{"value":"9783030871963","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87196-3_53","type":"book-chapter","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T06:19:41Z","timestamp":1632377981000},"page":"571-581","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Improving Pneumonia Localization via Cross-Attention on Medical Images and\u00a0Reports"],"prefix":"10.1007","author":[{"given":"Riddhish","family":"Bhalodia","sequence":"first","affiliation":[]},{"given":"Ali","family":"Hatamizadeh","sequence":"additional","affiliation":[]},{"given":"Leo","family":"Tam","sequence":"additional","affiliation":[]},{"given":"Ziyue","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xiaosong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Evrim","family":"Turkbey","sequence":"additional","affiliation":[]},{"given":"Daguang","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"53_CR1","doi-asserted-by":"crossref","unstructured":"Chen, K., Gao, J., Nevatia, R.: Knowledge aided consistency for weakly supervised phrase grounding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4042\u20134050 (2018)","DOI":"10.1109\/CVPR.2018.00425"},{"key":"53_CR2","doi-asserted-by":"crossref","unstructured":"Choe, J., Shim, H.: Attention-based dropout layer for weakly supervised object localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2219\u20132228 (2019)","DOI":"10.1109\/CVPR.2019.00232"},{"key":"53_CR3","doi-asserted-by":"crossref","unstructured":"Cohen, J.P., et al.: Predicting COVID-19 pneumonia severity on chest x-ray with deep learning. Cureus 12(7) (2020)","DOI":"10.7759\/cureus.9448"},{"key":"53_CR4","unstructured":"Cohen, J.P., Morrison, P., Dao, L.: COVID-19 image data collection. arXiv 2003.11597 (2020). https:\/\/github.com\/ieee8023\/covid-chestxray-dataset"},{"key":"53_CR5","doi-asserted-by":"crossref","unstructured":"Datta, S., Sikka, K., Roy, A., Ahuja, K., Parikh, D., Divakaran, A.: Align2Ground: weakly supervised phrase grounding guided by image-caption alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2601\u20132610 (2019)","DOI":"10.1109\/ICCV.2019.00269"},{"key":"53_CR6","doi-asserted-by":"crossref","unstructured":"Gupta, T., Vahdat, A., Chechik, G., Yang, X., Kautz, J., Hoiem, D.: Contrastive learning for weakly supervised phrase grounding. arXiv preprint arXiv:2006.09920 (2020)","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"53_CR7","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":"53_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K-H Lee","year":"2018","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"53_CR9","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Thoracic disease identification and localization with limited supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8290\u20138299 (2018)","DOI":"10.1109\/CVPR.2018.00865"},{"key":"53_CR10","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"53_CR11","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, L., Wang, S., Zha, Z.J., Meng, D., Huang, Q.: Adaptive reconstruction network for weakly supervised referring expression grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2611\u20132620 (2019)","DOI":"10.1109\/ICCV.2019.00270"},{"key":"53_CR12","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"53_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-030-00928-1_51","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"M Moradi","year":"2018","unstructured":"Moradi, M., Madani, A., Gur, Y., Guo, Y., Syeda-Mahmood, T.: Bimodal network architectures for automatic generation of image annotation from text. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 449\u2013456. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00928-1_51"},{"key":"53_CR14","unstructured":"of North America, R.S.: RSNA pneumonia detection challenge (08 2018)"},{"key":"53_CR15","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"53_CR17","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Lee, Y.J.: Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3544\u20133553. IEEE (2017)","DOI":"10.1109\/ICCV.2017.381"},{"key":"53_CR18","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"53_CR19","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, T., Li, Y., Zhang, Y., Wu, F.: Multi-modality cross attention network for image and sentence matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"53_CR20","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Automatic bounding box annotation of chest x-ray data for localization of abnormalities. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 799\u2013803. IEEE (2020)","DOI":"10.1109\/ISBI45749.2020.9098482"},{"key":"53_CR21","doi-asserted-by":"crossref","unstructured":"Xiao, F., Sigal, L., Jae Lee, Y.: Weakly-supervised visual grounding of phrases with linguistic structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5945\u20135954 (2017)","DOI":"10.1109\/CVPR.2017.558"},{"key":"53_CR22","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87196-3_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T06:54:07Z","timestamp":1632380047000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87196-3_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030871956","9783030871963"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87196-3_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 September 2021","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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccai2021.org\/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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1622","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":"531","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":"33% - 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":"4","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}