{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:35:03Z","timestamp":1777487703067,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819913534","type":"print"},{"value":"9789819913541","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\/978-981-99-1354-1_1","type":"book-chapter","created":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T14:03:27Z","timestamp":1680098607000},"page":"3-9","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Knowledge-Enhanced Medical Visual Question Answering: A Survey (Invited Talk Summary)"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3018-3824","authenticated-orcid":false,"given":"Haofen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5241-7620","authenticated-orcid":false,"given":"Huifang","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,30]]},"reference":[{"key":"1_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"issue":"1","key":"1_CR2","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11633-022-1369-5","volume":"20","author":"FL Chen","year":"2023","unstructured":"Chen, F.L., et al.: VLP: a survey on vision-language pre-training. Mach. Intell. Res. 20(1), 38\u201356 (2023)","journal-title":"Mach. Intell. Res."},{"key":"1_CR3","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NIPS (2017)"},{"issue":"9","key":"1_CR4","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","volume":"41","author":"Y Xian","year":"2018","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2251\u20132265 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"1_CR5","doi-asserted-by":"publisher","first-page":"334","DOI":"10.3390\/info12080334","volume":"12","author":"M Sarrouti","year":"2021","unstructured":"Sarrouti, M., Ben Abacha, A., Demner-Fushman, D.: Goal-driven visual question generation from radiology images. Information 12(8), 334 (2021). https:\/\/doi.org\/10.3390\/info12080334","journal-title":"Information"},{"key":"1_CR6","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. arXiv:2111.10056 (2021)"},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Sengar, N., Joshi, R.C., Dutta, M.K., Burget, R.: EyeDeep-Net: a multi-class diagnosis of retinal diseases using deep neural network. Neural Comput. Appl. 1\u201321 (2023). https:\/\/doi.org\/10.1007\/s00521-023-08249-x","DOI":"10.1007\/s00521-023-08249-x"},{"issue":"1","key":"1_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12938-022-01018-2","volume":"21","author":"R Liu","year":"2022","unstructured":"Liu, R., et al.: Application of artificial intelligence-based dual-modality analysis combining fundus photography and optical coherence tomography in diabetic retinopathy screening in a community hospital. Biomed. Eng. Online 21(1), 1\u201311 (2022). https:\/\/doi.org\/10.1186\/s12938-022-01018-2","journal-title":"Biomed. Eng. Online"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"1_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108153","volume":"120","author":"W Zheng","year":"2021","unstructured":"Zheng, W., Yin, L., Chen, X., Ma, Z., Liu, S., Yang, B.: Knowledge base graph embedding module design for Visual question answering model. Pattern Recogn. 120, 108153 (2021). https:\/\/doi.org\/10.1016\/j.patcog.2021.108153","journal-title":"Pattern Recogn."},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-VQA: a visual question answering benchmark requiring external knowledge. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Ravi, S., Chinchure, A., Sigal, L., Liao, R., Shwartz, V.: VLC-BERT: visual question answering with contextualized commonsense knowledge. In: WACV (2023)","DOI":"10.1109\/WACV56688.2023.00121"},{"key":"1_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109015","volume":"133","author":"L Song","year":"2023","unstructured":"Song, L., Li, J., Liu, J., Yang, Y., Shang, X., Sun, M.: Answering knowledge-based visual questions via the exploration of question purpose. Pattern Recogn. 133, 109015 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2022.109015","journal-title":"Pattern Recogn."},{"issue":"2","key":"1_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103241","volume":"60","author":"J Huang","year":"2023","unstructured":"Huang, J., et al.: Medical knowledge-based network for patient-oriented visual question answering. Inf. Process. Manag. 60(2), 103241 (2023). https:\/\/doi.org\/10.1016\/j.ipm.2022.103241","journal-title":"Inf. Process. Manag."},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, G., Wan, X.: Reason and learn: enhancing medical vision-and-language pre-training with knowledge. In: ACM Multimedia (2022)","DOI":"10.1145\/3503161.3547948"},{"key":"1_CR17","unstructured":"Hasan, S.A., Ling, Y., Farri, O., Liu, J., M\u00fcller, H., Lungren, M.P.: Overview of ImageCLEF 2018 medical domain visual question answering task. In: CLEF (Working Notes) (2018)"},{"key":"1_CR18","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., Abacha, A.B., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5, 1\u201310 (2018). https:\/\/doi.org\/10.1038\/sdata.2018.251","journal-title":"Sci. Data"},{"key":"1_CR19","unstructured":"Abacha, A.B., Hasan, S.A., Datla, V.V., Liu, J., Demner-Fushman, D., M\u00fcller, H.: VQA-med: overview of the medical visual question answering task at ImageCLEF 2019. In: CLEF (working notes) (2019)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Kovaleva, O., et al.: Towards visual dialog for radiology. In: Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing (2020)","DOI":"10.18653\/v1\/2020.bionlp-1.6"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537"},{"key":"1_CR22","unstructured":"Abacha, A.B., Datla, V.V., Hasan, S.A., Demner-Fushman, D., M\u00fcller, H.: Overview of the VQA-med task at ImageCLEF 2020: visual question answering and generation in the medical domain. In: CLEF (working notes) (2020)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: ISBI (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"1_CR24","unstructured":"Abacha, A.B., et al.: Overview of the VQA-med task at ImageCLEF 2021: visual question answering and generation in the medical domain. In: CLEF (working notes) (2021)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, X., Liu, F., Huang, G.: OVQA: a clinically generated visual question answering dataset. In: SIGIR (2022)","DOI":"10.1145\/3477495.3531724"},{"key":"1_CR26","unstructured":"Narasimhan, M., Lazebnik, S., Schwing, A.: Out of the box: reasoning with graph convolution nets for factual visual question answering. In: NIPS (2018)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Narasimhan, M., Schwing, A.G.: Straight to the facts: learning knowledge base retrieval for factual visual question answering. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"1_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109015","volume":"133","author":"L Song","year":"2023","unstructured":"Song, L., Li, J., Liu, J., Yang, Y., Shang, X., Sun, M.: Answering knowledge-based visual questions via the exploration of question purpose. Pattern Recogn. 133, 109015 (2023)","journal-title":"Pattern Recogn."},{"key":"1_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"issue":"8","key":"1_CR31","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1_CR32","unstructured":"Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS (2013)"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Luo, F., Zhang, Y., Wang, X.: IMAS++: an intelligent medical analysis system enhanced with deep graph neural networks. In: CIKM (2021)","DOI":"10.1145\/3459637.3481966"},{"key":"1_CR34","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: ACMMM (2021)","DOI":"10.1145\/3503161.3547948"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, W., Yan, L., Wang, F.Y., Gou, C.: Learning from the guidance: knowledge embedded meta-learning for medical visual question answering. In: ICONIP (2020)","DOI":"10.1007\/978-3-030-63820-7_22"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, X., Liu, F., Huang, G.: OVQA: a clinically generated visual question answering dataset. In: SIGIR (2022)","DOI":"10.1145\/3477495.3531724"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Nguyen, B.D., Do, T.T., Nguyen, B.X., Do, T., Tjiputra, E., Tran, Q.D.: Overcoming data limitation in medical visual question answering. In: MICCAI (2019)","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"1_CR38","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Masci, J., Meier, U., Cire\u015fan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: ICANN (2011)","DOI":"10.1007\/978-3-642-21735-7_7"}],"container-title":["Communications in Computer and Information Science","Web and Big Data. APWeb-WAIM 2022 International Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1354-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T14:03:46Z","timestamp":1680098626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1354-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819913534","9789819913541"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1354-1_1","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/apweb-waim2022.com\/proceedings","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":"297","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":"75","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":"45","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":"25% - 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)"}},{"value":"5 Demo papers + 23 workshop papers","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)"}}]}}