{"status": "ok", "message-type": "work", "message-version": "1.0.0", "message": {"indexed": {"date-parts": [[2026, 10, 15]], "date-time": "2026-10-15T13:27:02Z", "timestamp": 1792070822403, "version": "4.4.0"}, "reference-count": 50, "publisher": "IEEE", "content-domain": {"domain": [], "crossmark-restriction": false}, "short-container-title": [], "published-print": {"date-parts": [[2015, 12]]}, "DOI": "10.1109/iccv.2015.279", "type": "proceedings-article", "created": {"date-parts": [[2016, 2, 19]], "date-time": "2016-02-19T23:23:49Z", "timestamp": 1455924229000}, "page": "2425-2433", "source": "Crossref", "is-referenced-by-count": 3252, "title": ["VQA: Visual Question Answering"], "prefix": "10.1109", "author": [{"given": "Stanislaw", "family": "Antol", "sequence": "first", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Aishwarya", "family": "Agrawal", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Jiasen", "family": "Lu", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Margaret", "family": "Mitchell", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Dhruv", "family": "Batra", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "C. Lawrence", "family": "Zitnick", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Devi", "family": "Parikh", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}], "member": "263", "reference": [{"key": "ref39", "doi-asserted-by": "publisher", "DOI": "10.1109/ICCV.2013.61"}, {"key": "ref38", "article-title": "MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text", "author": "richardson", "year": "2013", "journal-title": "EMNLP"}, {"key": "ref33", "article-title": "Distributed Representations of Words and Phrases and their Compositionality", "author": "mikolov", "year": "2013", "journal-title": "NIPS"}, {"key": "ref32", "article-title": "Explain Images with Multimodal Recurrent Neural Networks", "author": "mao", "year": "2014", "journal-title": "CoRR abs/1410 1090"}, {"key": "ref31", "doi-asserted-by": "publisher", "DOI": "10.1109/ICCV.2015.9"}, {"key": "ref30", "article-title": "A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input", "author": "malinowski", "year": "2014", "journal-title": "NIPS"}, {"key": "ref37", "article-title": "Exploring models and data for image question answering", "author": "ren", "year": "2015", "journal-title": "NIPS"}, {"key": "ref36", "article-title": "Linking People with “Their” Names using Coreference Resolution", "author": "ramanathan", "year": "2014", "journal-title": "ECCV"}, {"key": "ref35", "article-title": "Generating Expressions that Refer to Visible Objects", "author": "mitchell", "year": "2013", "journal-title": "HLT-NAACL"}, {"key": "ref34", "article-title": "Generating Image Descriptions From Computer Vision Detections", "author": "mitchell", "year": "2012", "journal-title": "ACL"}, {"key": "ref28", "article-title": "Don't just listen, use your imagination: Leveraging visual common sense for non-visual tasks", "author": "lin", "year": "2015", "journal-title": "CVPR"}, {"key": "ref27", "doi-asserted-by": "publisher", "DOI": "10.1109/CVPR.2015.7298917"}, {"key": "ref29", "doi-asserted-by": "publisher", "DOI": "10.1023/B:BTTJ.0000047600.45421.6d"}, {"key": "ref2", "article-title": "VizWiz: Nearly Real-time Answers to Visual Questions", "volume": "2010", "author": "bigham", "year": "0", "journal-title": "User Interface Software and Technology"}, {"key": "ref1", "doi-asserted-by": "publisher", "DOI": "10.1007/978-3-319-10593-2_27"}, {"key": "ref20", "article-title": "Refer-ItGame: Referring to Objects in Photographs of Natural Scenes", "author": "kazemzadeh", "year": "2014", "journal-title": "EMNLP"}, {"key": "ref22", "doi-asserted-by": "publisher", "DOI": "10.1109/CVPR.2014.455"}, {"key": "ref21", "article-title": "Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models", "author": "kiros", "year": "2015", "journal-title": "TACL"}, {"key": "ref24", "doi-asserted-by": "publisher", "DOI": "10.1109/CVPR.2011.5995466"}, {"key": "ref23", "article-title": "ImageNet Classification with Deep Convolutional Neural Networks", "author": "krizhevsky", "year": "2012", "journal-title": "NIPS"}, {"key": "ref26", "article-title": "Microsoft COCO: Common Objects in Context", "volume": "2014", "author": "lin", "year": "0", "journal-title": "ECCV"}, {"key": "ref25", "author": "lenat", "year": "1989", "journal-title": "Building Large Knowledge-Based Systems Representation and Inference in the CYC Project"}, {"key": "ref50", "article-title": "Adopting Abstract Images for Semantic Scene Understanding", "author": "zitnick", "year": "2015", "journal-title": "PAMI"}, {"key": "ref10", "doi-asserted-by": "publisher", "DOI": "10.3115/v1/P14-2074"}, {"key": "ref11", "article-title": "Paraphrase-Driven Learning for Open Question Answering", "author": "fader", "year": "2013", "journal-title": "ACL"}, {"key": "ref40", "article-title": "Viske: Visual knowledge extraction and question answering by visual verification of relation phrases", "author": "sadeghi", "year": "2015", "journal-title": "CVPR"}, {"key": "ref12", "doi-asserted-by": "publisher", "DOI": "10.1145/2623330.2623677"}, {"key": "ref13", "article-title": "From Captions to Visual Concepts and Back", "volume": "2015", "author": "fang", "year": "0", "journal-title": "CVPR"}, {"key": "ref14", "article-title": "Every Picture Tells a Story: Generating Sentences for Images", "author": "farhadi", "year": "2010", "journal-title": "ECCV"}, {"key": "ref15", "article-title": "Are you talking to a machine? dataset and methods for multilingual image question answering", "author": "gao", "year": "2015", "journal-title": "NIPS"}, {"key": "ref16", "doi-asserted-by": "publisher", "DOI": "10.1073/pnas.1422953112"}, {"key": "ref17", "doi-asserted-by": "publisher", "DOI": "10.1109/ICCV.2013.337"}, {"key": "ref18", "article-title": "Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics", "volume": "2013", "author": "hodosh", "year": "0", "journal-title": "JAIR"}, {"key": "ref19", "article-title": "Deep Visual-Semantic Alignments for Generating Image Descriptions", "volume": "2015", "author": "karpathy", "year": "0", "journal-title": "CVPR"}, {"key": "ref4", "article-title": "Toward an Architecture for Never-Ending Language Learning", "author": "carlson", "year": "2010", "journal-title": "inAAAI/IAAI"}, {"key": "ref3", "article-title": "Free-base: A Collaboratively Created Graph Database for Structuring Human Knowledge", "author": "bollacker", "year": "2008", "journal-title": "International Conference on Management of Data"}, {"key": "ref6", "doi-asserted-by": "publisher", "DOI": "10.1109/ICCV.2013.178"}, {"key": "ref5", "article-title": "Microsoft COCO Captions: Data Collection and Evaluation Server", "author": "chen", "year": "2015", "journal-title": "arXiv preprint arXiv 1504 00325"}, {"key": "ref8", "article-title": "Hierarchical Semantic Indexing for Large Scale Image Retwfdrieval", "author": "deng", "year": "2011", "journal-title": "CVPR"}, {"key": "ref7", "doi-asserted-by": "publisher", "DOI": "10.1109/CVPR.2015.7298856"}, {"key": "ref49", "doi-asserted-by": "publisher", "DOI": "10.1109/ICCV.2013.211"}, {"key": "ref9", "first-page": "2l", "article-title": "Long-term Recurrent Convolutional Networks for Visual Recognition and Description", "volume": "2015", "author": "donahue", "year": "0", "journal-title": "CVPR"}, {"key": "ref46", "article-title": "Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks", "author": "weston", "year": "2015", "journal-title": "CoRR abs/1502 05698"}, {"key": "ref45", "article-title": "Show and Tell: A Neural Image Caption Generator", "volume": "2015", "author": "vinyals", "year": "0", "journal-title": "CVPR"}, {"key": "ref48", "doi-asserted-by": "publisher", "DOI": "10.1109/CVPR.2013.387"}, {"key": "ref47", "doi-asserted-by": "publisher", "DOI": "10.1109/ICCV.2015.283"}, {"key": "ref42", "article-title": "Joint Video and Text Parsing for Understanding Events and Answering Queries", "volume": "2014", "author": "tu", "year": "0", "journal-title": "IEEE Multimedia"}, {"key": "ref41", "article-title": "Very deep convolutional networks for large-scale image recognition", "author": "simonyan", "year": "2014", "journal-title": "CoRR abs/1409 1556"}, {"key": "ref44", "article-title": "Learning common sense through visual abstraction", "author": "vendantam", "year": "2015", "journal-title": "ICCV"}, {"key": "ref43", "article-title": "CIDEr: Consensus-based Image Description Evaluation", "author": "vedantam", "year": "2015", "journal-title": "CVPR"}], "event": {"name": "2015 IEEE International Conference on Computer Vision (ICCV)", "location": "Santiago, Chile", "start": {"date-parts": [[2015, 12, 7]]}, "end": {"date-parts": [[2015, 12, 13]]}}, "container-title": ["2015 IEEE International Conference on Computer Vision (ICCV)"], "original-title": [], "link": [{"URL": "http://xplorestaging.ieee.org/ielx7/7407725/7410356/07410636.pdf?arnumber=7410636", "content-type": "unspecified", "content-version": "vor", "intended-application": "similarity-checking"}], "deposited": {"date-parts": [[2017, 3, 23]], "date-time": "2017-03-23T17:39:07Z", "timestamp": 1490290747000}, "score": 1, "resource": {"primary": {"URL": "http://ieeexplore.ieee.org/document/7410636/"}}, "subtitle": [], "short-title": [], "issued": {"date-parts": [[2015, 12]]}, "references-count": 50, "URL": "https://doi.org/10.1109/iccv.2015.279", "relation": {}, "subject": [], "published": {"date-parts": [[2015, 12]]}}}