{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:23:18Z","timestamp":1771950198517,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031340475","type":"print"},{"value":"9783031340482","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\/978-3-031-34048-2_35","type":"book-chapter","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T12:03:35Z","timestamp":1686139415000},"page":"457-470","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Using Multiple Instance Learning to\u00a0Build Multimodal Representations"],"prefix":"10.1007","author":[{"given":"Peiqi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William M.","family":"Wells","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seth","family":"Berkowitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Horng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Polina","family":"Golland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"35_CR1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.artint.2013.06.003","volume":"201","author":"J Amores","year":"2013","unstructured":"Amores, J.: Multiple instance classification: review, taxonomy and comparative study. Artif. Intell. 201, 81\u2013105 (2013)","journal-title":"Artif. Intell."},{"key":"35_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20059-5_1","volume-title":"Computer Vision - ECCV 2022","author":"B Boecking","year":"2022","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.) ECCV 2022. LNCS, vol. 13696, pp. 1\u201321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_1"},{"key":"35_CR3","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","volume":"77","author":"MA Carbonneau","year":"2018","unstructured":"Carbonneau, M.A., Cheplygina, V., Granger, E., Gagnon, G.: Multiple instance learning: a survey of problem characteristics and applications. Pattern Recognit. 77, 329\u2013353 (2018)","journal-title":"Pattern Recognit."},{"key":"35_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-030-59713-9_51","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"G Chauhan","year":"2020","unstructured":"Chauhan, G., et al.: Joint modeling of chest radiographs and radiology reports for pulmonary edema assessment. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 529\u2013539. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59713-9_51"},{"key":"35_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Desai, K., Johnson, J.: VirTex: learning visual representations from textual annotations. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"35_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S026988890999035X","volume":"25","author":"J Foulds","year":"2010","unstructured":"Foulds, J., Frank, E.: A review of multi-instance learning assumptions. Knowl. Eng. Rev. 25, 1\u201325 (2010)","journal-title":"Knowl. Eng. Rev."},{"key":"35_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-01219-9_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Gao","year":"2018","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 36\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_3"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Harwath, D., Recasens, A., Sur\u00eds, D., Chuang, G., Torralba, A.: Jointly discovering visual objects and spoken words from raw sensory input. In: IJCV (2020)","DOI":"10.1007\/s11263-019-01205-0"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR13","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: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"35_CR14","unstructured":"Ilse, M., Tomczak, J., Welling, M.: Attention-based deep multiple instance learning. In: ICML (2018)"},{"key":"35_CR15","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AEW Johnson","year":"2019","unstructured":"Johnson, A.E.W., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6, 317 (2019)","journal-title":"Sci. Data"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. TPAMI (2017)","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"35_CR17","unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.: Deep fragment embeddings for bidirectional image sentence mapping. In: NIPS (2014)"},{"key":"35_CR18","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Kraus, O.Z., Ba, J.L., Frey, B.J.: Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics 32, i52\u2013i59 (2016)","DOI":"10.1093\/bioinformatics\/btw252"},{"key":"35_CR20","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":"35_CR21","doi-asserted-by":"crossref","unstructured":"Li, B., Li, Y., Eliceiri, K.W.: Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"35_CR22","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:1908.0355 (2019)"},{"key":"35_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-87196-3_26","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"R Liao","year":"2021","unstructured":"Liao, R., et al.: Multimodal representation learning via maximization of local mutual information. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 273\u2013283. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_26"},{"key":"35_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"35_CR25","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"35_CR26","unstructured":"Maron, O., Lozano-P\u00e9rez, T.: A framework for multiple-instance learning. In: NIPS (1998)"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"35_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/978-3-031-19809-0_39","volume-title":"Computer Vision - ECCV 2022","author":"P M\u00fcller","year":"2022","unstructured":"M\u00fcller, P., Kaissis, G., Zou, C., Rueckert, D.: Joint learning of localized representations from medical images and reports. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13686, pp. 685\u2013701. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_39"},{"key":"35_CR29","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv:1807.03748 (2018)"},{"key":"35_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"35_CR31","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Sadvilkar, N., Neumann, M.: PySBD: pragmatic sentence boundary disambiguation. In: NLP-OSS (2020)","DOI":"10.18653\/v1\/2020.nlposs-1.15"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Shih, G., et al.: Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia. Radiol. Artif. Intell. 1, e180041 (2019)","DOI":"10.1148\/ryai.2019180041"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"35_CR35","unstructured":"Zhang, C., Platt, J., Viola, P.: Multiple instance boosting for object detection. In: NIPS (2005)"},{"key":"35_CR36","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: MLHC (2022)"},{"key":"35_CR37","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.1016\/j.artint.2011.10.002","volume":"176","author":"ZH Zhou","year":"2012","unstructured":"Zhou, Z.H., Zhang, M.L., Huang, S.J., Li, Y.F.: Multi-instance multi-label learning. Artif. Intell. 176, 2291\u20132320 (2012)","journal-title":"Artif. Intell."}],"container-title":["Lecture Notes in Computer Science","Information Processing in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-34048-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T12:08:44Z","timestamp":1686139724000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34048-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031340475","9783031340482"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34048-2_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":"8 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IPMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information Processing in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Carlos de Bariloche","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Argentina","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":"12 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ipmi2023","order":10,"name":"conference_id","label":"Conference ID","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":"169","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":"63","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":"37% - 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)"}}]}}