{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:58Z","timestamp":1783439938308,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2021J01003"],"award-info":[{"award-number":["2021J01003"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702432"],"award-info":[{"award-number":["61702432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531724","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"2924-2938","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["OVQA"],"prefix":"10.1145","author":[{"given":"Yefan","family":"Huang","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoli","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guofeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Affiliated Southeast Hospital of Xiamen University, Zhangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"CLEF (Working Notes)","author":"Abacha A. B.","year":"2020","unstructured":"A. B. Abacha , V. V. Datla , S. A. Hasan , D. Demner-Fushman , and H. M\u00fcller . Overview of the vqa-med task at imageclef 2020: Visual question answering and generation in the medical domain . In CLEF (Working Notes) , 2020 . A. B. Abacha, V. V. Datla, S. A. Hasan, D. Demner-Fushman, and H. M\u00fcller. Overview of the vqa-med task at imageclef 2020: Visual question answering and generation in the medical domain. In CLEF (Working Notes), 2020."},{"key":"e_1_3_2_2_2_1","volume-title":"Vqa-med: Overview of the medical visual question answering task at imageclef","author":"Abacha A. B.","year":"2019","unstructured":"A. B. Abacha , S. A. Hasan , V. V. Datla , J. Liu , D. Demner-Fushman , and H. M\u00fcller . Vqa-med: Overview of the medical visual question answering task at imageclef 2019 . In CLEF (Working Notes) , 2019. A. B. Abacha, S. A. Hasan, V. V. Datla, J. Liu, D. Demner-Fushman, and H. M\u00fcller. Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In CLEF (Working Notes), 2019."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"e_1_3_2_2_4_1","volume-title":"CLEF 2021 Working Notes, CEUR Workshop Proceedings","author":"Abacha A. Ben","year":"2021","unstructured":"A. Ben Abacha , M. Sarrouti , D. Demner-Fushman , S. A. Hasan , and H. M\u00fcller . Overview of the vqa-med task at imageclef 2021: Visual question answering and generation in the medical domain . In CLEF 2021 Working Notes, CEUR Workshop Proceedings , Bucharest, Romania, September 21--24 2021 . CEUR-WS.org. A. Ben Abacha, M. Sarrouti, D. Demner-Fushman, S. A. Hasan, and H. M\u00fcller. Overview of the vqa-med task at imageclef 2021: Visual question answering and generation in the medical domain. In CLEF 2021 Working Notes, CEUR Workshop Proceedings, Bucharest, Romania, September 21--24 2021. CEUR-WS.org."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_3_2_2_6_1","first-page":"4171","volume-title":"NAACL","author":"Devlin J.","year":"2019","unstructured":"J. Devlin , M.-W. Chang , K. Lee , and K. Toutanova . Bert: Pre-training of deep bidirectional transformers for language understanding . In NAACL , pages 4171 -- 4186 , 2019 . J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL, pages 4171-- 4186, 2019."},{"key":"e_1_3_2_2_7_1","volume-title":"Multiple meta-model quantifying for medical visual question answering. arXiv preprint arXiv:2105.08913","author":"Do T.","year":"2021","unstructured":"T. Do , B. X. Nguyen , E. Tjiputra , M. Tran , Q. D. Tran , and A. Nguyen . Multiple meta-model quantifying for medical visual question answering. arXiv preprint arXiv:2105.08913 , 2021 . T. Do, B. X. Nguyen, E. Tjiputra, M. Tran, Q. D. Tran, and A. Nguyen. Multiple meta-model quantifying for medical visual question answering. arXiv preprint arXiv:2105.08913, 2021."},{"key":"e_1_3_2_2_8_1","first-page":"1126","volume-title":"ICML","author":"Finn C.","year":"2017","unstructured":"C. Finn , P. Abbeel , and S. Levine . Model-agnostic meta-learning for fast adaptation of deep networks . In ICML , pages 1126 -- 1135 . PMLR, 2017 . C. Finn, P. Abbeel, and S. Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML, pages 1126--1135. PMLR, 2017."},{"key":"e_1_3_2_2_9_1","volume-title":"A k-means clustering algorithm","author":"Hartigan J. A.","year":"1979","unstructured":"J. A. Hartigan and M. A. Wong . A k-means clustering algorithm . 1979 . J. A. Hartigan and M. A. Wong. A k-means clustering algorithm. 1979."},{"key":"e_1_3_2_2_10_1","volume-title":"CLEF (Working Notes)","author":"Hasan S. A.","year":"2018","unstructured":"S. A. Hasan , Y. Ling , O. Farri , J. Liu , H. M\u00fcller , and M. P. Lungren . Overview of imageclef 2018 medical domain visual question answering task . In CLEF (Working Notes) , 2018 . S. A. Hasan, Y. Ling, O. Farri, J. Liu, H. M\u00fcller, and M. P. Lungren. Overview of imageclef 2018 medical domain visual question answering task. In CLEF (Working Notes), 2018."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_13_1","volume-title":"Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286","author":"He X.","year":"2020","unstructured":"X. He , Y. Zhang , L. Mou , E. Xing , and P. Xie . Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286 , 2020 . X. He, Y. Zhang, L. Mou, E. Xing, and P. Xie. Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286, 2020."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_15_1","first-page":"101950","article-title":"Chaos challenge-combined (ct-mr) healthy abdominal organ segmentation","volume":"69","author":"Kavur A. E.","year":"2021","unstructured":"A. E. Kavur , N. S. Gezer S. Aslan , P.-H. Conze , V. Groza , D. D. Pham , S. Chatterjee , P. Ernst , S. \u00d6zkan , Chaos challenge-combined (ct-mr) healthy abdominal organ segmentation . MedIA , 69 : 101950 , 2021 . A. E. Kavur, N. S. Gezer S. Aslan, P.-H. Conze, V. Groza, D. D. Pham, S. Chatterjee, P. Ernst, S. \u00d6zkan, et al. Chaos challenge-combined (ct-mr) healthy abdominal organ segmentation. MedIA, 69:101950, 2021.","journal-title":"MedIA"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"e_1_3_2_2_17_1","volume-title":"NeurIPS","author":"Kim J.-H.","year":"2018","unstructured":"J.-H. Kim , J. Jun , and B.-T. Zhang . Bilinear attention networks . In NeurIPS , 2018 . J.-H. Kim, J. Jun, and B.-T. Zhang. Bilinear attention networks. In NeurIPS, 2018."},{"key":"e_1_3_2_2_18_1","first-page":"115","volume-title":"SPIRE","author":"Kondrak G.","year":"2005","unstructured":"G. Kondrak . N-gram similarity and distance . In SPIRE , pages 115 -- 126 . Springer , 2005 . G. Kondrak. N-gram similarity and distance. In SPIRE, pages 115--126. Springer, 2005."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.bionlp-1.6"},{"key":"e_1_3_2_2_20_1","first-page":"282","volume-title":"ICML","author":"Lafferty J.","year":"2001","unstructured":"J. Lafferty , A. McCallum , and F. Pereira . Conditional random fields: Probabilistic models for segmenting and labeling sequence data . In ICML , pages 282 -- 289 , 2001 . J. Lafferty, A. McCallum, and F. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In ICML, pages 282--289, 2001."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"e_1_3_2_2_22_1","first-page":"1650","volume-title":"ISBI","author":"Liu B.","year":"2021","unstructured":"B. Liu , L.-M. Zhan , L. Xu , L. Ma , Y. Yang , and X.-M. Wu. Slake : A semanticallylabeled knowledge-enhanced dataset for medical visual question answering . In ISBI , pages 1650 -- 1654 . IEEE, 2021 . B. Liu, L.-M. Zhan, L. Xu, L. Ma, Y. Yang, and X.-M. Wu. Slake: A semanticallylabeled knowledge-enhanced dataset for medical visual question answering. In ISBI, pages 1650--1654. IEEE, 2021."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481966"},{"key":"e_1_3_2_2_25_1","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume":"27","author":"Malinowski M.","year":"2014","unstructured":"M. Malinowski and M. Fritz . A multi-world approach to question answering about real-world scenes based on uncertain input . NIPS , 27 : 1682 -- 1690 , 2014 . M. Malinowski and M. Fritz. A multi-world approach to question answering about real-world scenes based on uncertain input. NIPS, 27:1682--1690, 2014.","journal-title":"NIPS"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"e_1_3_2_2_31_1","volume-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063","author":"Simpson A. L.","year":"2019","unstructured":"A. L. Simpson , M. Antonelli , S. Bakas , M. Bilello , K. Farahani , B. Van Ginneken , A. Kopp-Schneider , B. A. Landman , G. Litjens , B. Menze , A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063 , 2019 . A. L. Simpson, M. Antonelli, S. Bakas, M. Bilello, K. Farahani, B. Van Ginneken, A. Kopp-Schneider, B. A. Landman, G. Litjens, B. Menze, et al. A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063, 2019."},{"key":"e_1_3_2_2_32_1","first-page":"75","volume-title":"CVIP","author":"Srivastava Y.","year":"2020","unstructured":"Y. Srivastava , V. Murali , S. R. Dubey , and S. Mukherjee . Visual question answering using deep learning: A survey and performance analysis . In CVIP , pages 75 -- 86 . Springer , 2020 . Y. Srivastava, V. Murali, S. R. Dubey, and S. Mukherjee. Visual question answering using deep learning: A survey and performance analysis. In CVIP, pages 75--86. Springer, 2020."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1610"},{"key":"e_1_3_2_2_34_1","first-page":"5998","volume-title":"NIPS","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani , N. Shazeer , N. Parmar , J. Uszkoreit , L. Jones , A. N. Gomez , ?. Kaiser, and I. Polosukhin . Attention is all you need . In NIPS , pages 5998 -- 6008 , 2017 . A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, ?. Kaiser, and I. Polosukhin. Attention is all you need. In NIPS, pages 5998--6008, 2017."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331350"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","first-page":"14076","DOI":"10.1609\/aaai.v35i16.17657","article-title":"Melinda: A multimodal dataset for biomedical experiment method classification","volume":"35","author":"Wu T.-L.","year":"2021","unstructured":"T.-L. Wu , S. Singh , S. Paul , G. Burns , and N. Peng . Melinda: A multimodal dataset for biomedical experiment method classification . AAAI , 35 : 14076 -- 14084 , 2021 . T.-L. Wu, S. Singh, S. Paul, G. Burns, and N. Peng. Melinda: A multimodal dataset for biomedical experiment method classification. AAAI, 35:14076--14084, 2021.","journal-title":"AAAI"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531724","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:07Z","timestamp":1750186927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531724"}},"subtitle":["A Clinically Generated Visual Question Answering Dataset"],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":40,"alternative-id":["10.1145\/3477495.3531724","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531724","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}