{"id":"https://openalex.org/W4393148653","doi":"https://doi.org/10.1609/aaai.v38i5.28216","title":"ConVQG: Contrastive Visual Question Generation with Multimodal Guidance","display_name":"ConVQG: Contrastive Visual Question Generation with Multimodal Guidance","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393148653","doi":"https://doi.org/10.1609/aaai.v38i5.28216"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i5.28216","doi":"https://doi.org/10.1609/aaai.v38i5.28216","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28216","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28216/28427","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28216/28427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li Mi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Li Mi","raw_affiliation_strings":["EPFL","EPFL, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073430314","display_name":"Syrielle Montariol","orcid":"https://orcid.org/0000-0003-1355-8778","observed_orcids":["https://orcid.org/0000-0003-1355-8778"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Syrielle Montariol","raw_affiliation_strings":["EPFL","EPFL, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059674545","display_name":"Javiera Castillo-Navarro","orcid":"https://orcid.org/0000-0003-4917-5103","observed_orcids":["https://orcid.org/0000-0003-4917-5103"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Javiera Castillo Navarro","raw_affiliation_strings":["EPFL","EPFL, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105892725","display_name":"Xianjie Dai","orcid":"https://orcid.org/0009-0006-2842-611X","observed_orcids":["https://orcid.org/0009-0006-2842-611X"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Xianjie Dai","raw_affiliation_strings":["EPFL","EPFL, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088410008","display_name":"Antoine Bosselut","orcid":"https://orcid.org/0000-0001-8968-9649","observed_orcids":["https://orcid.org/0000-0001-8968-9649"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Antoine Bosselut","raw_affiliation_strings":["EPFL","EPFL, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005192117","display_name":"Devis Tuia","orcid":"https://orcid.org/0000-0003-0374-2459","observed_orcids":["https://orcid.org/0000-0003-0374-2459"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Devis Tuia","raw_affiliation_strings":["EPFL","EPFL, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.8409,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80675051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"38","issue":"5","first_page":"4207","last_page":"4215"},"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/T10028","display_name":"Topic Modeling","score":0.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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/visual-question-generation","display_name":"visual question generation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9750000238418579},{"id":"https://openalex.org/keywords/multimodal-grounding","display_name":"multimodal grounding","score":0.8999999761581421},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"commonsense knowledge","score":0.6340000033378601},{"id":"https://openalex.org/keywords/question-generation","display_name":"question generation","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4681091010570526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44129228591918945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33891379833221436},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3368212580680847},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13595223426818848}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1609/aaai.v38i5.28216","doi":"https://doi.org/10.1609/aaai.v38i5.28216","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28216","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28216/28427","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2402.12846","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.12846","pdf_url":"https://arxiv.org/pdf/2402.12846","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/248141","doi":null,"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/248141","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},{"id":"pmh:oai:ojs.aaai.org:article/28216","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/28216","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2402.12846","doi":"https://doi.org/10.48550/arxiv.2402.12846","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.12846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i5.28216","doi":"https://doi.org/10.1609/aaai.v38i5.28216","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28216","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28216/28427","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3056497733","display_name":"Interfacing Neural and Symbolic Knowledge in Natural Language Systems","funder_award_id":"215390","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8503654337","display_name":null,"funder_award_id":"PFFS-21-29","funder_id":"https://openalex.org/F4320327931","funder_display_name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320317052","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734"},{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320327931","display_name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","ror":"https://ror.org/05a2bhn71"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393148653.pdf","grobid_xml":"https://content.openalex.org/works/W4393148653.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1983927101","https://openalex.org/W2133459682","https://openalex.org/W2306876680","https://openalex.org/W2530647954","https://openalex.org/W2560730294","https://openalex.org/W2561296180","https://openalex.org/W2563399268","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2887991371","https://openalex.org/W2896457183","https://openalex.org/W2963087285","https://openalex.org/W2963976294","https://openalex.org/W2964065333","https://openalex.org/W2964303913","https://openalex.org/W2970641574","https://openalex.org/W2981852735","https://openalex.org/W3001952301","https://openalex.org/W3005680577","https://openalex.org/W3009992206","https://openalex.org/W3018378048","https://openalex.org/W3019023591","https://openalex.org/W3030163527","https://openalex.org/W3035524453","https://openalex.org/W3090449556","https://openalex.org/W3093563057","https://openalex.org/W3094502228","https://openalex.org/W3126337491","https://openalex.org/W3135367836","https://openalex.org/W3157509826","https://openalex.org/W3199113016","https://openalex.org/W3206904785","https://openalex.org/W3207071456","https://openalex.org/W3209532394","https://openalex.org/W4221152714","https://openalex.org/W4225832925","https://openalex.org/W4226182655","https://openalex.org/W4226278401","https://openalex.org/W4285280022","https://openalex.org/W4297808394","https://openalex.org/W4312810944","https://openalex.org/W4385573917","https://openalex.org/W6745764446","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4304080600","https://openalex.org/W4413389039","https://openalex.org/W4286903183","https://openalex.org/W4221152714","https://openalex.org/W4414463409","https://openalex.org/W4400448403","https://openalex.org/W4388186932","https://openalex.org/W4407181782","https://openalex.org/W3024316984","https://openalex.org/W2898071615"],"abstract_inverted_index":{"Asking":[0],"questions":[1,79,125,168],"about":[2],"visual":[3],"environments":[4],"is":[5],"a":[6,85,93,116,119,134],"crucial":[7],"way":[8],"for":[9,166],"intelligent":[10],"agents":[11],"to":[12,30,47,56,88,123,170],"understand":[13],"rich":[14],"multi-faceted":[15],"scenes,":[16],"raising":[17],"the":[18,31,58,72,89,149],"importance":[19],"of":[20,104],"Visual":[21,112],"Question":[22,113],"Generation":[23,114],"(VQG)":[24],"systems.":[25],"Apart":[26],"from":[27,71,130],"being":[28],"grounded":[29],"image,":[32],"existing":[33],"VQG":[34,54,96,143],"systems":[35,55,97],"can":[36,67],"use":[37],"textual":[38,81],"constraints,":[39],"such":[40],"as":[41,95],"expected":[42],"answers":[43],"or":[44,61,101],"knowledge":[45,65],"triplets,":[46],"generate":[48],"focused":[49,78],"questions.":[50,158],"These":[51],"constraints":[52,82],"allow":[53],"specify":[57],"question":[59],"content":[60,74,91],"leverage":[62],"external":[63],"commonsense":[64],"that":[66,146],"not":[68],"be":[69],"obtained":[70],"image":[73,90],"only.":[75],"However,":[76],"generating":[77],"using":[80,118,127],"while":[83],"enforcing":[84],"high":[86],"relevance":[87],"remains":[92],"challenge,":[94],"often":[98],"ignore":[99],"one":[100],"both":[102,128,139],"forms":[103],"grounding.":[105],"In":[106],"this":[107],"work,":[108],"we":[109],"propose":[110],"Contrastive":[111],"(ConVQG),":[115],"method":[117],"dual":[120],"contrastive":[121],"objective":[122],"discriminate":[124],"generated":[126],"modalities":[129],"those":[131],"based":[132],"on":[133,138],"single":[135],"one.":[136],"Experiments":[137],"knowledge-aware":[140],"and":[141,152,156],"standard":[142],"benchmarks":[144],"demonstrate":[145],"ConVQG":[147,167],"outperforms":[148],"state-of-the-art":[150],"methods":[151],"generates":[153],"image-grounded,":[154],"text-guided,":[155],"knowledge-rich":[157],"Our":[159],"human":[160],"evaluation":[161],"results":[162],"also":[163],"show":[164],"preference":[165],"compared":[169],"non-contrastive":[171],"baselines.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-03-26T00:00:00"}
