{"id":"https://openalex.org/W3205084812","doi":"https://doi.org/10.1145/3474085.3475452","title":"Question-controlled Text-aware Image Captioning","display_name":"Question-controlled Text-aware Image Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205084812","doi":"https://doi.org/10.1145/3474085.3475452","mag":"3205084812"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-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/A5019498452","display_name":"Anwen Hu","orcid":"https://orcid.org/0000-0001-8839-4996"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anwen Hu","raw_affiliation_strings":["Renming University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renming University of China, Beijing, China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["INRIA, Paris, France"],"affiliations":[{"raw_affiliation_string":"INRIA, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019498452"],"corresponding_institution_ids":["https://openalex.org/I146071755"],"apc_list":null,"apc_paid":null,"fwci":1.0567,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79300654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3097","last_page":"3105"},"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":0.9907000064849854,"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":0.968999981880188,"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":0.9857524633407593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8564605712890625},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6929399371147156},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5803980231285095},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5564090013504028},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5547189712524414},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5311362147331238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5195518136024475},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48579859733581543},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4410632848739624},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43610459566116333},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07323694229125977}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9857524633407593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8564605712890625},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6929399371147156},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5803980231285095},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5564090013504028},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5547189712524414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5311362147331238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195518136024475},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48579859733581543},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4410632848739624},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43610459566116333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07323694229125977},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2789636240","https://openalex.org/W2963084599","https://openalex.org/W2972897806","https://openalex.org/W2981852735","https://openalex.org/W2986670728","https://openalex.org/W3034336960","https://openalex.org/W3034984754","https://openalex.org/W3039677769","https://openalex.org/W3093272873","https://openalex.org/W3110661548","https://openalex.org/W3112075608","https://openalex.org/W4288089799","https://openalex.org/W4297909472","https://openalex.org/W4299128829"],"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/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"For":[0],"an":[1],"image":[2,18],"with":[3,73,125,152],"multiple":[4],"scene":[5,67,122],"texts,":[6],"different":[7,13],"people":[8],"may":[9],"be":[10],"interested":[11],"in":[12,76],"text":[14,123],"information.":[15],"Current":[16],"text-aware":[17,39,83,150,190],"captioning":[19,84,160,191],"models":[20,61],"are":[21,197],"not":[22],"able":[23],"to":[24,29,36,62,94,115,135],"generate":[25,37],"distinctive":[26],"captions":[27,186],"according":[28],"various":[30],"information":[31],"needs.":[32],"To":[33],"explore":[34],"how":[35],"personalized":[38,149],"captions,":[40],"we":[41,86,130],"define":[42],"a":[43,100,111,132,148,153],"new":[44],"challenging":[45],"task,":[46],"namely":[47],"Question-controlled":[48],"Text-aware":[49],"Image":[50],"Captioning":[51],"(Qc-TextCap).":[52],"With":[53,174],"questions":[54,175],"as":[55,176],"control":[56,177],"signals,":[57,178],"this":[58],"task":[59],"requires":[60],"understand":[63],"questions,":[64],"find":[65],"related":[66],"texts":[68],"and":[69,92,103,120,162,184,195],"describe":[70],"them":[71],"together":[72],"objects":[74],"fluently":[75],"human":[77],"language.":[78],"Based":[79],"on":[80,170],"two":[81,89,172],"existing":[82],"datasets,":[85,90],"automatically":[87],"construct":[88],"ControlTextCaps":[91],"ControlVizWiz":[93],"support":[95],"the":[96,137,188],"task.":[97],"We":[98],"propose":[99],"novel":[101],"Geometry":[102],"Question":[104],"Aware":[105],"Model":[106],"(GQAM).":[107],"GQAM":[108,146],"first":[109],"applies":[110],"Geometry-informed":[112],"Visual":[113],"Encoder":[114,134],"fuse":[116],"region-level":[117,121],"object":[118],"features":[119,124,141],"considering":[126],"spatial":[127],"relationships.":[128],"Then,":[129],"design":[131],"Question-guided":[133],"select":[136],"most":[138],"relevant":[139],"visual":[140],"for":[142],"each":[143],"question.":[144],"Finally,":[145],"generates":[147,181],"caption":[151],"Multimodal":[154],"Decoder.":[155],"Our":[156,193],"model":[157,180],"achieves":[158],"better":[159],"performance":[161],"question":[163],"answering":[164],"ability":[165],"than":[166,187],"carefully":[167],"designed":[168],"baselines":[169],"both":[171],"datasets.":[173],"our":[179],"more":[182],"informative":[183],"diverse":[185],"state-of-the-art":[189],"model.":[192],"code":[194],"datasets":[196],"publicly":[198],"available":[199],"at":[200],"https://github.com/HAWLYQ/Qc-TextCap.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}