{"id":"https://openalex.org/W4387968093","doi":"https://doi.org/10.1145/3581783.3612388","title":"Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner","display_name":"Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968093","doi":"https://doi.org/10.1145/3581783.3612388"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5008547683","display_name":"Zikang Liu","orcid":"https://orcid.org/0000-0002-8947-7053"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zikang Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067083698","display_name":"Sihan Chen","orcid":"https://orcid.org/0009-0001-3539-8085"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihan Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030312893","display_name":"H. Li","orcid":"https://orcid.org/0009-0004-2473-2561"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Handong Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777772","display_name":"Xingjian He","orcid":"https://orcid.org/0000-0001-5396-6253"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjian He","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008547683"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.1186,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42732812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5120","last_page":"5131"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9909999966621399,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9764999747276306,"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":0.9783146381378174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8865200281143188},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.552127480506897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5417519211769104},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.524279773235321},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5141323208808899},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5040601491928101},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.49928760528564453},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45929473638534546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44380804896354675},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41787663102149963},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4134829342365265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3268366754055023},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22345730662345886}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9783146381378174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8865200281143188},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.552127480506897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5417519211769104},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.524279773235321},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5141323208808899},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5040601491928101},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49928760528564453},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45929473638534546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44380804896354675},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41787663102149963},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4134829342365265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3268366754055023},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22345730662345886},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1283858192","display_name":null,"funder_award_id":"U21B2043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1508456709","display_name":null,"funder_award_id":"62102416","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1614471940","display_name":null,"funder_award_id":"2020AAA0","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4467203512","display_name":null,"funder_award_id":"62102419","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5577970204","display_name":null,"funder_award_id":"2020AAA0106400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G691641063","display_name":null,"funder_award_id":"U21B2043, 62102419, 62102416","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7424057548","display_name":null,"funder_award_id":"No. 2020AAA0106400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2552002300","https://openalex.org/W2786273134","https://openalex.org/W2886641317","https://openalex.org/W2903617461","https://openalex.org/W2963084599","https://openalex.org/W2963351776","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W2963758027","https://openalex.org/W2963976294","https://openalex.org/W2965628639","https://openalex.org/W2970231061","https://openalex.org/W2979987972","https://openalex.org/W3019023591","https://openalex.org/W3035497460","https://openalex.org/W3138516171","https://openalex.org/W3176641147","https://openalex.org/W3199231060","https://openalex.org/W3204588463","https://openalex.org/W3208314443","https://openalex.org/W3213050770","https://openalex.org/W3213454282","https://openalex.org/W4220899212","https://openalex.org/W4225323055","https://openalex.org/W4225512839","https://openalex.org/W4226278401","https://openalex.org/W4287887134","https://openalex.org/W4386065836","https://openalex.org/W6600175266","https://openalex.org/W6600339457"],"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/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Large":[0],"pre-trained":[1,127],"multimodal":[2,128],"models":[3,204],"have":[4],"demonstrated":[5],"significant":[6],"success":[7],"in":[8,99,169],"a":[9,114,126,157,170],"range":[10],"of":[11,26,58],"downstream":[12,183],"tasks,":[13],"including":[14],"image":[15],"captioning,":[16],"image-text":[17,31,132,194],"retrieval,":[18],"visual":[19],"question":[20],"answering":[21],"(VQA),":[22],"etc.":[23],"However,":[24],"many":[25],"these":[27],"methods":[28],"rely":[29],"on":[30,181],"pairs":[32,133],"collected":[33],"from":[34],"the":[35,43,150,176],"web":[36],"as":[37,78,80],"pre-training":[38,71,168],"data":[39,104],"and":[40,51,60,66,85,93,106,120,130,137,141,198,210],"unfortunately":[41],"overlook":[42],"need":[44],"for":[45,91,167],"fine-grained":[46],"feature":[47],"alignment":[48],"between":[49],"vision":[50],"language":[52,61],"modalities,":[53],"which":[54,124],"requires":[55],"detailed":[56],"understanding":[57],"images":[59],"expressions.":[62],"While":[63],"integrating":[64],"VQA":[65,92,140],"dense":[67,94,142],"captioning":[68,95,143],"(DC)":[69],"into":[70],"can":[72,174,189],"address":[73],"this":[74,110,147],"issue,":[75],"acquiring":[76],"image-question-answer":[77],"well":[79],"image-location-caption":[81],"triplets":[82],"is":[83],"challenging":[84],"time-consuming.":[86],"Additionally,":[87],"publicly":[88],"available":[89,213],"datasets":[90,195],"are":[96,212],"typically":[97],"limited":[98],"scale":[100],"due":[101],"to":[102,134,149,155],"manual":[103],"collection":[105],"labeling":[107],"efforts.":[108],"In":[109],"paper,":[111],"we":[112],"propose":[113],"novel":[115],"method":[116,148],"called":[117,160],"Joint":[118],"QA":[119],"DC":[121],"GEneration":[122],"(JADE),":[123],"utilizes":[125],"model":[129],"easily-crawled":[131],"automatically":[135],"generate":[136,156],"filter":[138],"large-scale":[139],"datasets.":[144],"We":[145],"apply":[146],"Conceptual":[151],"Caption":[152],"(CC3M)":[153],"dataset":[154,159,211],"new":[158],"CC3M-QA-DC.":[161],"Experiments":[162],"show":[163],"that":[164],"when":[165],"used":[166],"multi-task":[171],"manner,":[172],"CC3M-QA-DC":[173,188],"improve":[175],"performance":[177],"with":[178,192,203],"various":[179,182],"backbones":[180],"tasks.":[184],"Furthermore,":[185],"our":[186],"generated":[187],"be":[190],"combined":[191],"larger":[193],"(e.g.,":[196],"CC15M)":[197],"achieve":[199],"competitive":[200],"results":[201],"compared":[202],"using":[205],"much":[206],"more":[207],"data.":[208],"Code":[209],"at":[214],"https://github.com/johncaged/OPT_Questioner.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}