{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:29:16Z","timestamp":1750220956697,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T00:00:00Z","timestamp":1558656000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,5,24]]},"DOI":"10.1145\/3339363.3339389","type":"proceedings-article","created":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T16:54:49Z","timestamp":1562604889000},"page":"108-113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Semantic BI-Embedded GRU for Fill-in-the-Blank Image Question Answering"],"prefix":"10.1145","author":[{"given":"Jun","family":"Hu","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}]},{"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}]}],"member":"320","published-online":{"date-parts":[[2019,5,24]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"3156","volume-title":"A neural image caption generator,\" IEEE Conference on Computer Vision and Pattern Recognition","author":"Vinyals O.","year":"2015","unstructured":"O. Vinyals , A. Toshev , S. Bengio , D. Erhan , \" Show and tell : A neural image caption generator,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 3156 -- 3164 , 2015 . O. Vinyals, A. Toshev, S. Bengio, D. Erhan, \"Show and tell: A neural image caption generator,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156--3164, 2015."},{"key":"e_1_3_2_1_2_1","first-page":"7215","volume-title":"Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning,\" IEEE Conference on Computer Vision and Pattern Recognition","author":"Sun Q.","year":"2017","unstructured":"Q. Sun , S. Lee , D. Batra , \" Bidirectional Beam Search : Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 7215 -- 7223 , 2017 . Q. Sun, S. Lee, D. Batra, \"Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 7215--7223, 2017."},{"key":"e_1_3_2_1_3_1","first-page":"2422","volume-title":"A Recurrent Visual Representation for Image Caption Generation,\" IEEE Conference on Computer Vision and Pattern Recognition","author":"Chen X.","year":"2015","unstructured":"X. Chen , C.L. Zitnick , \" Mind's Eye : A Recurrent Visual Representation for Image Caption Generation,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 2422 -- 2431 , 2015 . X. Chen, C.L. Zitnick, \"Mind's Eye: A Recurrent Visual Representation for Image Caption Generation,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 2422--2431, 2015."},{"key":"e_1_3_2_1_4_1","first-page":"3128","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Karpathy A.","year":"2015","unstructured":"A. Karpathy , F.F. Li , \" Deep Visual-Semantic Alignments for Generating Image Descriptions ,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 3128 -- 3137 , 2015 . A. Karpathy, F.F. Li, \"Deep Visual-Semantic Alignments for Generating Image Descriptions,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128--3137, 2015."},{"key":"e_1_3_2_1_5_1","unstructured":"K. Simonyan A. Zisserman \"Very deep convolutional networks for large-scale image recognition \" Computer Science pp. 1409--1556 2014.  K. Simonyan A. Zisserman \"Very deep convolutional networks for large-scale image recognition \" Computer Science pp. 1409--1556 2014."},{"key":"e_1_3_2_1_6_1","unstructured":"M. Ren R. Kiros R. Zemel \"Exploring models and data for image question answering \" International Conference on Neural Information Processing Systems 2015.   M. Ren R. Kiros R. Zemel \"Exploring models and data for image question answering \" International Conference on Neural Information Processing Systems 2015."},{"key":"e_1_3_2_1_7_1","first-page":"4622","volume-title":"Free-form visual question answering based on knowledge from external sources,\" IEEE Conference on Computer Vision and Pattern Recognition","author":"Wu Q.","year":"2017","unstructured":"Q. Wu , P. Wang , C. Shen , A. Dick , A. van den Hengel , \" Ask me anything : Free-form visual question answering based on knowledge from external sources,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 4622 -- 4630 , 2017 . Q. Wu, P. Wang, C. Shen, A. Dick, A. van den Hengel, \"Ask me anything: Free-form visual question answering based on knowledge from external sources,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 4622--4630, 2017."},{"key":"e_1_3_2_1_8_1","unstructured":"H.Y. Gao J. Mao J. Zhou Z. Huang A. Yuille \"Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering \" International Conference on Neural Information Processing Systems 2015.   H.Y. Gao J. Mao J. Zhou Z. Huang A. Yuille \"Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering \" International Conference on Neural Information Processing Systems 2015."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"S. Hochreiter J. Schmidhuber \"Long short-term memory \" Neural Computation pp. 1735--1780 1997.  S. Hochreiter J. Schmidhuber \"Long short-term memory \" Neural Computation pp. 1735--1780 1997.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"e_1_3_2_1_13_1","unstructured":"M. Malinowski M. Fritz \"A multi-world approach to question answering about real-world scenes based on uncertain input \" International Conference on Neural Information Processing Systems 2014.   M. Malinowski M. Fritz \"A multi-world approach to question answering about real-world scenes based on uncertain input \" International Conference on Neural Information Processing Systems 2014."},{"key":"e_1_3_2_1_14_1","first-page":"909","volume-title":"Learning How to Use Existing Vision Algorithms to Answer New Questions,\" IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang P.","year":"2017","unstructured":"P. Wang , Q. Wu , C. Shen , A. van den Hengel , \" The VQA- Machine : Learning How to Use Existing Vision Algorithms to Answer New Questions,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 909 -- 3918 , 2017 . P. Wang, Q. Wu, C. Shen, A. van den Hengel, \"The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 909--3918, 2017."},{"key":"e_1_3_2_1_15_1","first-page":"170","volume-title":"IEEE Conference on Multimedia Information Processing and Retrieval","author":"Ruwa N.","year":"2018","unstructured":"N. Ruwa , Q.R. Mao , L.J. Wang , M. Dong , \" Affective Visual Question Answering Network ,\" IEEE Conference on Multimedia Information Processing and Retrieval , pp. 170 -- 173 , 2018 . N. Ruwa, Q.R. Mao, L.J. Wang, M. Dong, \"Affective Visual Question Answering Network,\" IEEE Conference on Multimedia Information Processing and Retrieval, pp. 170--173, 2018."},{"key":"e_1_3_2_1_16_1","first-page":"6325","volume-title":"Elevating the Role of Image Understanding in Visual Question Answering,\" IEEE Conference on Computer Vision and Pattern Recognition","author":"Goyal Y.","year":"2017","unstructured":"Y. Goyal , T. Khot , D. Summers-Stay , D. Batra , D. Parikh , \" Making the V in VQA Matter : Elevating the Role of Image Understanding in Visual Question Answering,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 6325 -- 6334 , 2017 . Y. Goyal, T. Khot, D. Summers-Stay, D. Batra, D. Parikh, \"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 6325--6334, 2017."},{"key":"e_1_3_2_1_17_1","first-page":"1852","volume-title":"IEEE Winter Conference on Applications of Computer Vision","author":"Zhao H.D.","year":"2018","unstructured":"H.D. Zhao , Q.F. Fan , D. Gutfreund , Y. Fu , \" Semantically Guided Visual Question Answering ,\" IEEE Winter Conference on Applications of Computer Vision , pp. 1852 -- 1860 , 2018 . H.D. Zhao, Q.F. Fan, D. Gutfreund, Y. Fu, \"Semantically Guided Visual Question Answering,\" IEEE Winter Conference on Applications of Computer Vision, pp. 1852--1860, 2018."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1096-0"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"K. Tu M. Meng M.W. Lee T.E. Choe S.C. Zhu \"Joint Video and Text Parsing for Understanding Events and Answering Queries \" IEEE MultiMedia pp. 42--70 2014.  K. Tu M. Meng M.W. Lee T.E. Choe S.C. Zhu \"Joint Video and Text Parsing for Understanding Events and Answering Queries \" IEEE MultiMedia pp. 42--70 2014.","DOI":"10.1109\/MMUL.2014.29"},{"key":"e_1_3_2_1_20_1","volume-title":"A Challenge Dataset for the Open-Domain Machine Comprehension of Text,\" Conference on Empirical Methods in Natural Language Processing","author":"Richardson M.","year":"2013","unstructured":"M. Richardson , C.J. Burges , E. Renshaw , \"MCTest : A Challenge Dataset for the Open-Domain Machine Comprehension of Text,\" Conference on Empirical Methods in Natural Language Processing , 2013 . M. Richardson, C.J. Burges, E. Renshaw, \"MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text,\" Conference on Empirical Methods in Natural Language Processing, 2013."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"e_1_3_2_1_23_1","first-page":"248","volume-title":"A large-scale hierarchical image database,\" IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009","unstructured":"Deng J, Dong W, Socher R, L.J. Li , K. Li , F.F. Li , \"Imagenet : A large-scale hierarchical image database,\" IEEE Conference on Computer Vision and Pattern Recognition , pp. 248 -- 255 , 2009 . Deng J, Dong W, Socher R, L.J. Li, K. Li, F.F. Li, \"Imagenet: A large-scale hierarchical image database,\" IEEE Conference on Computer Vision and Pattern Recognition, pp. 248--255, 2009."},{"key":"e_1_3_2_1_24_1","first-page":"722","volume-title":"A nucleus for a web of open data,\" The semantic web","author":"Auer S.","year":"2007","unstructured":"S. Auer , C. Bizer , G. Kobilarov , J. Lehmann , R. Cyganiak , Z. Ives , \"Dbpedia : A nucleus for a web of open data,\" The semantic web . Springer , Berlin, Heidelberg , pp. 722 -- 735 , 2007 . S. Auer, C. Bizer, G. Kobilarov, J. Lehmann, R. Cyganiak, Z. Ives, \"Dbpedia: A nucleus for a web of open data,\" The semantic web. Springer, Berlin, Heidelberg, pp. 722--735, 2007."}],"event":{"name":"CSSE 2019: 2019 2nd International Conference on Computer Science and Software Engineering","sponsor":["Research Center for Science and Technology for Learning, National Central University, Taiwan"],"location":"Xi'an China","acronym":"CSSE 2019"},"container-title":["Proceedings of the 2nd International Conference on Computer Science and Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3339363.3339389","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3339363.3339389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:07Z","timestamp":1750204447000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3339363.3339389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,24]]},"references-count":24,"alternative-id":["10.1145\/3339363.3339389","10.1145\/3339363"],"URL":"https:\/\/doi.org\/10.1145\/3339363.3339389","relation":{},"subject":[],"published":{"date-parts":[[2019,5,24]]},"assertion":[{"value":"2019-05-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}