{"id":"https://openalex.org/W2786273134","doi":"https://doi.org/10.18653/v1/w17-3529","title":"Data Augmentation for Visual Question Answering","display_name":"Data Augmentation for Visual Question Answering","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2786273134","doi":"https://doi.org/10.18653/v1/w17-3529","mag":"2786273134"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-3529","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3529","pdf_url":"https://www.aclweb.org/anthology/W17-3529.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-3529.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047193437","display_name":"Kushal Kafle","orcid":"https://orcid.org/0000-0002-0847-7861"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kushal Kafle","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029359575","display_name":"Mohammed Yousefhussien","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Yousefhussien","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046979072","display_name":"Christopher Kanan","orcid":"https://orcid.org/0000-0002-6412-995X"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher Kanan","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046979072"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":128,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"198","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8768130540847778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8463084697723389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6825778484344482},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5352737307548523},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5072221755981445},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4976222813129425},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48812398314476013},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.47352027893066406},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4730193614959717},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43134722113609314},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42762964963912964},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4256021976470947},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3992346525192261},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0904935896396637}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8768130540847778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8463084697723389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6825778484344482},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5352737307548523},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5072221755981445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4976222813129425},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48812398314476013},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.47352027893066406},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4730193614959717},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43134722113609314},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42762964963912964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4256021976470947},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3992346525192261},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0904935896396637}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-3529","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3529","pdf_url":"https://www.aclweb.org/anthology/W17-3529.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Natural Language Generation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-3529","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3529","pdf_url":"https://www.aclweb.org/anthology/W17-3529.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2786273134.pdf","grobid_xml":"https://content.openalex.org/works/W2786273134.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2121056381","https://openalex.org/W2163605009","https://openalex.org/W2170240176","https://openalex.org/W2190656909","https://openalex.org/W2194775991","https://openalex.org/W2256357568","https://openalex.org/W2293453011","https://openalex.org/W2442626797","https://openalex.org/W2463565445","https://openalex.org/W2529436507","https://openalex.org/W2962762541","https://openalex.org/W2963012544","https://openalex.org/W2963143606","https://openalex.org/W2963351776","https://openalex.org/W2963383024","https://openalex.org/W2963579811","https://openalex.org/W2963954913","https://openalex.org/W2964138343","https://openalex.org/W4298392976"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W4220955952","https://openalex.org/W1566366091","https://openalex.org/W3209772662","https://openalex.org/W2908402521","https://openalex.org/W4200629926"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,34,50],"is":[2,39,69],"widely":[3],"used":[4],"to":[5,62],"train":[6],"deep":[7],"neural":[8,75],"networks":[9],"for":[10,48,51],"image":[11],"classification":[12],"tasks.":[13],"Simply":[14],"flipping":[15],"images":[16,26],"can":[17],"help":[18],"learning":[19],"by":[20,27],"increasing":[21],"the":[22,79],"number":[23],"of":[24,30,84],"training":[25],"a":[28,70],"factor":[29],"two.":[31],"However,":[32],"data":[33,49],"in":[35],"natural":[36],"language":[37],"processing":[38],"much":[40],"less":[41],"studied.":[42],"Here,":[43],"we":[44],"describe":[45],"two":[46],"methods":[47],"Visual":[52],"Question":[53],"Answering":[54],"(VQA).":[55],"The":[56,66],"first":[57],"uses":[58],"existing":[59],"semantic":[60],"annotations":[61],"generate":[63],"new":[64],"questions.":[65],"second":[67],"method":[68],"generative":[71],"approach":[72],"using":[73],"recurrent":[74],"networks.":[76],"Experiments":[77],"show":[78],"proposed":[80],"schemes":[81],"improve":[82],"performance":[83],"baseline":[85],"and":[86],"state-of-the-art":[87],"VQA":[88],"algorithms.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}