{"id":"https://openalex.org/W2947380532","doi":"https://doi.org/10.18653/v1/p19-1348","title":"Generating Question Relevant Captions to Aid Visual Question Answering","display_name":"Generating Question Relevant Captions to Aid Visual Question Answering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2947380532","doi":"https://doi.org/10.18653/v1/p19-1348","mag":"2947380532"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1348","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1348","pdf_url":"https://www.aclweb.org/anthology/P19-1348.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1348.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101825497","display_name":"Jialin Wu","orcid":"https://orcid.org/0000-0003-4684-5212"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jialin Wu","raw_affiliation_strings":["Department of Computer Science University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057474488","display_name":"Zeyuan Hu","orcid":"https://orcid.org/0000-0003-3036-2777"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyuan Hu","raw_affiliation_strings":["Department of Computer Science University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008715111","display_name":"Raymond J. Mooney","orcid":"https://orcid.org/0000-0002-4504-0490"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raymond Mooney","raw_affiliation_strings":["Department of Computer Science University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101825497"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":3.7410015,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":{"value":0.94373124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3585","last_page":"3594"},"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":0.9919000267982483,"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":0.9855999946594238,"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":0.9122609496116638},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8653479814529419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8453359603881836},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6369178891181946},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6157697439193726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5847681760787964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5414310693740845},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44203731417655945},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4411192536354065},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.42992857098579407},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4286535382270813},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06925299763679504}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9122609496116638},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8653479814529419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453359603881836},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6369178891181946},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6157697439193726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5847681760787964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5414310693740845},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44203731417655945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4411192536354065},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.42992857098579407},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4286535382270813},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06925299763679504},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1348","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1348","pdf_url":"https://www.aclweb.org/anthology/P19-1348.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1348","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1348","pdf_url":"https://www.aclweb.org/anthology/P19-1348.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947380532.pdf","grobid_xml":"https://content.openalex.org/works/W2947380532.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1575833922","https://openalex.org/W1677182931","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2143668817","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2481240925","https://openalex.org/W2510318047","https://openalex.org/W2560645892","https://openalex.org/W2560730294","https://openalex.org/W2563399268","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2737766105","https://openalex.org/W2788527488","https://openalex.org/W2803686446","https://openalex.org/W2895230054","https://openalex.org/W2946299408","https://openalex.org/W2949555952","https://openalex.org/W2951183276","https://openalex.org/W2962858109","https://openalex.org/W2962967746","https://openalex.org/W2963084599","https://openalex.org/W2963170456","https://openalex.org/W2963383024","https://openalex.org/W2963448089","https://openalex.org/W2963609017","https://openalex.org/W2963991868","https://openalex.org/W2964061310","https://openalex.org/W2964121744","https://openalex.org/W2964345214","https://openalex.org/W2970548373","https://openalex.org/W2973009097","https://openalex.org/W3016211260","https://openalex.org/W3098019619"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Visual":[0],"question":[1],"answering":[2],"(VQA)":[3],"and":[4,16],"image":[5],"captioning":[6],"require":[7],"a":[8,20,41,86],"shared":[9],"body":[10],"of":[11],"general":[12],"knowledge":[13],"connecting":[14],"language":[15],"vision.":[17],"We":[18],"present":[19],"novel":[21],"approach":[22,74],"to":[23,38],"better":[24],"VQA":[25,68,77],"performance":[26,78],"that":[27,35,72],"exploits":[28],"this":[29],"connection":[30],"by":[31,54,89],"jointly":[32],"generating":[33,91],"captions":[34,58],"are":[36],"targeted":[37],"help":[39],"answer":[40],"specific":[42],"visual":[43],"question.":[44],"The":[45],"model":[46],"is":[47],"trained":[48],"using":[49,59,85],"an":[50,60],"existing":[51],"caption":[52],"dataset":[53],"automatically":[55],"determining":[56],"question-relevant":[57,92],"online":[61],"gradient-based":[62],"method.":[63],"Experimental":[64],"results":[65],"on":[66],"the":[67,82],"v2":[69],"challenge":[70],"demonstrates":[71],"our":[73],"obtains":[75],"state-of-the-art":[76],"(e.g.":[79],"68.4%":[80],"in":[81],"Test-standard":[83],"set":[84],"single":[87],"model)":[88],"simultaneously":[90],"captions.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}