{"id":"https://openalex.org/W2963355794","doi":"https://doi.org/10.1145/3313873","title":"Image Captioning by Asking Questions","display_name":"Image Captioning by Asking Questions","publication_year":2019,"publication_date":"2019-04-30","ids":{"openalex":"https://openalex.org/W2963355794","doi":"https://doi.org/10.1145/3313873","mag":"2963355794"},"language":"en","primary_location":{"id":"doi:10.1145/3313873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3313873","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083991825","display_name":"Xiaoshan Yang","orcid":"https://orcid.org/0000-0001-5453-9755"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoshan Yang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083991825"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.1135,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8207172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"15","issue":"2s","first_page":"1","last_page":"19"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9743000268936157,"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":0.9740999937057495,"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/closed-captioning","display_name":"Closed captioning","score":0.9910895824432373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7842863202095032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6786679029464722},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6633192896842957},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6582105159759521},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6296849846839905},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5626862645149231},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5302383899688721},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5292900204658508},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.516595721244812},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3498914837837219},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1301460862159729}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9910895824432373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842863202095032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6786679029464722},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6633192896842957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6582105159759521},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6296849846839905},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5626862645149231},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5302383899688721},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5292900204658508},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.516595721244812},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3498914837837219},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1301460862159729},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3313873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3313873","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G134077436","display_name":null,"funder_award_id":"61702511, 61720106006, 61620106003, 61432019, 61632007, U1705262, and U1836220","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1488163396","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1666447063","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1895641373","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1983927101","https://openalex.org/W2042708146","https://openalex.org/W2064675550","https://openalex.org/W2070753207","https://openalex.org/W2101105183","https://openalex.org/W2123024445","https://openalex.org/W2123301721","https://openalex.org/W2142192571","https://openalex.org/W2149557440","https://openalex.org/W2154652894","https://openalex.org/W2174492417","https://openalex.org/W2185175083","https://openalex.org/W2266930373","https://openalex.org/W2293453011","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2346425926","https://openalex.org/W2396147015","https://openalex.org/W2412393473","https://openalex.org/W2438044634","https://openalex.org/W2526428212","https://openalex.org/W2558687840","https://openalex.org/W2575842049","https://openalex.org/W2607151106","https://openalex.org/W2620666060","https://openalex.org/W2745461083","https://openalex.org/W2797733588","https://openalex.org/W2808203533","https://openalex.org/W2949447259","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2951619830","https://openalex.org/W2953276893","https://openalex.org/W2962749469","https://openalex.org/W2963084599","https://openalex.org/W2963088515","https://openalex.org/W2963143606","https://openalex.org/W2963175879","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963477107","https://openalex.org/W2963656855","https://openalex.org/W2963672682","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964138017","https://openalex.org/W2964138343","https://openalex.org/W3100115227","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W3009270862","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"and":[2,13,31,64,177],"visual":[3,25,142,152,180],"question":[4],"answering":[5],"are":[6,74,148],"typical":[7],"tasks":[8,48],"that":[9,103,184],"connect":[10],"computer":[11,28],"vision":[12,29],"natural":[14,38],"language":[15,39],"processing.":[16],"Both":[17],"of":[18,45,60],"them":[19],"need":[20],"to":[21,50,87,112,132,138,150],"effectively":[22],"represent":[23],"the":[24,34,52,57,61,65,78,89,98,105,109,113,126,151,164,168,174,178],"content":[26],"using":[27,37],"methods":[30,196],"smoothly":[32],"process":[33],"text":[35],"sentence":[36],"processing":[40],"skills.":[41],"The":[42,145],"key":[43],"problem":[44],"these":[46,93],"two":[47,94],"is":[49,119,130],"infer":[51],"target":[53],"result":[54],"based":[55],"on":[56,122,197],"interactive":[58],"understanding":[59],"word":[62],"sequence":[63],"image.":[66],"Though":[67],"they":[68,73,155],"practically":[69],"use":[70],"similar":[71],"algorithms,":[72],"studied":[75],"independently":[76],"in":[77],"past":[79],"few":[80],"years.":[81],"In":[82],"this":[83],"article,":[84],"we":[85],"attempt":[86],"exploit":[88],"mutual":[90],"correlation":[91],"between":[92],"tasks.":[95],"We":[96,162,182],"propose":[97],"first":[99,120],"VQA-improved":[100,187],"image-captioning":[101,114,169,188,195],"method":[102],"transfers":[104],"knowledge":[106],"learned":[107],"from":[108,158],"VQA":[110,117,128,165],"corpora":[111],"task.":[115],"A":[116],"model":[118,129,166,170],"pretrained":[121,127],"image--question--answer":[123],"instances.":[124],"Then,":[125],"used":[131],"extract":[133],"VQA-grounded":[134,146,175],"semantic":[135],"representations":[136],"according":[137],"selected":[139],"free-form":[140],"open-ended":[141],"question--answer":[143],"pairs.":[144],"features":[147],"complementary":[149],"features,":[153],"because":[154],"interpret":[156],"images":[157],"a":[159],"different":[160],"perspective.":[161],"incorporate":[163],"into":[167],"by":[171],"adaptively":[172],"fusing":[173],"feature":[176],"attended":[179],"feature.":[181],"show":[183],"such":[185],"simple":[186],"(VQA-IIC)":[189],"models":[190],"perform":[191],"better":[192],"than":[193],"conventional":[194],"large-scale":[198],"public":[199],"datasets.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}