{"id":"https://openalex.org/W4400679824","doi":"https://doi.org/10.1109/taffc.2024.3428704","title":"Integrating Visual Context Into Language Models for Situated Social Conversation Starters","display_name":"Integrating Visual Context Into Language Models for Situated Social Conversation Starters","publication_year":2024,"publication_date":"2024-07-16","ids":{"openalex":"https://openalex.org/W4400679824","doi":"https://doi.org/10.1109/taffc.2024.3428704"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2024.3428704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3428704","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01JTFYW2NVSHMD3Q6ZWC94VM91/file/01JTFZ154PY4KB799BMA4MWD65.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027249654","display_name":"Ruben Janssens","orcid":"https://orcid.org/0000-0002-1790-9531"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ruben Janssens","raw_affiliation_strings":["IDLab-AIRO, Ghent University - imec, Gent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-1790-9531","affiliations":[{"raw_affiliation_string":"IDLab-AIRO, Ghent University - imec, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053778039","display_name":"Pieter Wolfert","orcid":"https://orcid.org/0000-0002-7420-7181"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Pieter Wolfert","raw_affiliation_strings":["Radboud University, Nijmegen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-7420-7181","affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075509168","display_name":"Thomas Demeester","orcid":"https://orcid.org/0000-0002-9901-5768"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thomas Demeester","raw_affiliation_strings":["IDLab-T2K, Ghent University - imec, Gent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab-T2K, Ghent University - imec, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035627933","display_name":"Tony Belpaeme","orcid":"https://orcid.org/0000-0001-5207-7745"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tony Belpaeme","raw_affiliation_strings":["IDLab-AIRO, Ghent University - imec, Gent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-5207-7745","affiliations":[{"raw_affiliation_string":"IDLab-AIRO, Ghent University - imec, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9903,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87364703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"223","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.9969000220298767,"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/T12128","display_name":"AI in Service Interactions","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/T12031","display_name":"Speech and dialogue systems","score":0.9901000261306763,"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/conversation","display_name":"Conversation","score":0.8474123477935791},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.8396723866462708},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5851349234580994},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5838316679000854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5346810817718506},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4608032703399658},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3418693542480469},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32267749309539795},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.32200878858566284},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.3140368163585663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3015674948692322}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8474123477935791},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.8396723866462708},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5851349234580994},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5838316679000854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5346810817718506},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4608032703399658},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3418693542480469},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32267749309539795},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32200878858566284},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3140368163585663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3015674948692322},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taffc.2024.3428704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3428704","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"},{"id":"pmh:oai:archive.ugent.be:01JTFYW2NVSHMD3Q6ZWC94VM91","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JTFYW2NVSHMD3Q6ZWC94VM91","pdf_url":"https://biblio.ugent.be/publication/01JTFYW2NVSHMD3Q6ZWC94VM91/file/01JTFZ154PY4KB799BMA4MWD65.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1949-3045","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/319121","is_oa":true,"landing_page_url":"https://hdl.handle.net/2066/319121","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/319121/319121.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article / Letter to editor"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01JTFYW2NVSHMD3Q6ZWC94VM91","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JTFYW2NVSHMD3Q6ZWC94VM91","pdf_url":"https://biblio.ugent.be/publication/01JTFYW2NVSHMD3Q6ZWC94VM91/file/01JTFZ154PY4KB799BMA4MWD65.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1949-3045","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G5083669671","display_name":null,"funder_award_id":"101070930","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G7646171968","display_name":null,"funder_award_id":"101070596","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400679824.pdf"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W74417651","https://openalex.org/W160135817","https://openalex.org/W632915152","https://openalex.org/W1985945240","https://openalex.org/W2037161066","https://openalex.org/W2041076459","https://openalex.org/W2068418797","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2281859263","https://openalex.org/W2556093109","https://openalex.org/W2583186419","https://openalex.org/W2616867613","https://openalex.org/W2687101809","https://openalex.org/W2795571593","https://openalex.org/W2835434549","https://openalex.org/W2896457183","https://openalex.org/W2899513582","https://openalex.org/W2905180035","https://openalex.org/W2922516980","https://openalex.org/W2938704169","https://openalex.org/W2963351776","https://openalex.org/W2964213933","https://openalex.org/W2982260276","https://openalex.org/W3034999214","https://openalex.org/W3040568028","https://openalex.org/W3087144913","https://openalex.org/W3102260352","https://openalex.org/W3125283999","https://openalex.org/W3156555225","https://openalex.org/W3165912329","https://openalex.org/W3201853009","https://openalex.org/W3205786327","https://openalex.org/W4205119860","https://openalex.org/W4210668510","https://openalex.org/W4211164456","https://openalex.org/W4240195433","https://openalex.org/W4249013746","https://openalex.org/W4285159263","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4309674289","https://openalex.org/W4312810944","https://openalex.org/W4318606124","https://openalex.org/W4318718936","https://openalex.org/W4320458302","https://openalex.org/W4324129606","https://openalex.org/W4378465306","https://openalex.org/W4385245566","https://openalex.org/W4385571466","https://openalex.org/W4388748234","https://openalex.org/W4392657974","https://openalex.org/W4403759910","https://openalex.org/W6733533644","https://openalex.org/W6739915280","https://openalex.org/W6755207826","https://openalex.org/W6756131343","https://openalex.org/W6761551260","https://openalex.org/W6769311223","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6809646742","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6849177959","https://openalex.org/W6850204008","https://openalex.org/W6851275496","https://openalex.org/W6852884379","https://openalex.org/W6858802463"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1600697036","https://openalex.org/W1601337804","https://openalex.org/W4392983437","https://openalex.org/W2035858348","https://openalex.org/W2155106162","https://openalex.org/W2152083270","https://openalex.org/W2010047220","https://openalex.org/W2115777528","https://openalex.org/W2806021742"],"abstract_inverted_index":{"Embodied":[0],"conversational":[1],"agents":[2],"that":[3,142,152],"interact":[4],"socially":[5],"with":[6,83],"people":[7,82],"in":[8,40,44,68,189],"the":[9,45,72,174],"physical":[10,46],"world":[11],"require":[12],"multi-modal":[13],"capabilities,":[14],"such":[15],"as":[16],"appropriately":[17],"responding":[18],"to":[19,65,123],"visual":[20,33,136,165],"features":[21,66],"of":[22,71,78,81,101,176],"users.":[23],"While":[24],"existing":[25],"vision-and-language":[26],"models":[27,97,151,160,179],"can":[28,168],"generate":[29,124],"language":[30,36,134],"based":[31],"on":[32,111,131,155],"input,":[34,109],"this":[35],"is":[37],"not":[38],"situated":[39,181,191],"a":[41,50,61,76],"social":[42,182,193],"interaction":[43],"world.":[47],"We":[48,74],"present":[49],"novel":[51],"task":[52],"called":[53],"Visual":[54],"Conversation":[55],"Starters,":[56],"where":[57],"an":[58,69,185],"agent":[59],"generates":[60,144],"conversation-starting":[62],"question":[63],"referring":[64],"visible":[67],"image":[70,104,108],"user.":[73],"collect":[75],"dataset":[77],"4000":[79],"images":[80],"12000":[84],"crowdsourced":[85,156],"conversation":[86,126],"starters,":[87],"compare":[88],"various":[89],"model":[90],"architectures:":[91],"fine-tuning":[92],"smaller":[93,150],"seq2seq":[94],"or":[95],"image-to-text":[96],"versus":[98,106,114],"zero-shot":[99],"prompting":[100],"GPT-3.5,":[102],"using":[103],"captions":[105],"end-to-end":[107],"training":[110],"human":[112],"data":[113],"synthetic":[115],"questions":[116,148],"generated":[117],"by":[118],"GPT-3.5.":[119],"Models":[120],"were":[121,129],"used":[122],"friendly":[125],"starters":[127],"which":[128],"evaluated":[130],"criteria":[132],"including":[133],"fluency,":[135],"grounding,":[137],"interestingness,":[138],"politeness.":[139],"Results":[140],"show":[141],"GPT-3.5":[143],"more":[145],"interesting,":[146],"polite":[147],"than":[149],"are":[153,161],"fine-tuned":[154],"data,":[157],"but":[158],"vision-to-language":[159],"better":[162],"at":[163],"referencing":[164],"features,":[166],"they":[167],"mimick":[169],"GPT-3.5's":[170],"performance.":[171],"This":[172],"demonstrates":[173],"feasibility":[175],"deep":[177],"visiolinguistic":[178],"for":[180],"agents,":[183],"forming":[184],"important":[186],"first":[187],"stage":[188],"creating":[190],"multimodal":[192],"interaction.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}