{"id":"https://openalex.org/W4403922859","doi":"https://doi.org/10.1145/3686215.3688382","title":"Detecting when Users Disagree with Generated Captions","display_name":"Detecting when Users Disagree with Generated Captions","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403922859","doi":"https://doi.org/10.1145/3686215.3688382"},"language":"en","primary_location":{"id":"doi:10.1145/3686215.3688382","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686215.3688382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 26th International Conference on Multimodal Interaction","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/A5006937331","display_name":"Omair Shahzad Bhatti","orcid":"https://orcid.org/0000-0001-7983-2384"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Omair Shahzad Bhatti","raw_affiliation_strings":["Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany"],"raw_orcid":"https://orcid.org/0000-0001-7983-2384","affiliations":[{"raw_affiliation_string":"Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091971477","display_name":"Harshinee Sriram","orcid":"https://orcid.org/0000-0001-8185-3475"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Harshinee Sriram","raw_affiliation_strings":["University of British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8185-3475","affiliations":[{"raw_affiliation_string":"University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032619772","display_name":"Abdulrahman Mohamed Selim","orcid":"https://orcid.org/0000-0002-4984-6686"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Abdulrahman Mohamed Selim","raw_affiliation_strings":["Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany"],"raw_orcid":"https://orcid.org/0000-0002-4984-6686","affiliations":[{"raw_affiliation_string":"Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024712028","display_name":"Cristina Conati","orcid":"https://orcid.org/0000-0002-8434-9335"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cristina Conati","raw_affiliation_strings":["University of British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8434-9335","affiliations":[{"raw_affiliation_string":"University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037664911","display_name":"Michael Barz","orcid":"https://orcid.org/0000-0001-6730-2466"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Barz","raw_affiliation_strings":["Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany and Applied Artificial Intelligence, University of Oldenburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6730-2466","affiliations":[{"raw_affiliation_string":"Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany and Applied Artificial Intelligence, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069432042","display_name":"Daniel Sonntag","orcid":"https://orcid.org/0000-0002-8857-8709"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Sonntag","raw_affiliation_strings":["Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany and Applied Artificial Intelligence, University of Oldenburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8857-8709","affiliations":[{"raw_affiliation_string":"Interactive Machine Learning, German Research Center for Artificial Intelligence (DFKI), Germany and Applied Artificial Intelligence, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5006937331"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53808594,"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":"195","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9991999864578247,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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/T12031","display_name":"Speech and dialogue systems","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.7013056874275208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3254966735839844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013056874275208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3254966735839844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3686215.3688382","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686215.3688382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 26th International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2870026279","display_name":null,"funder_award_id":"101093079","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6210869370","display_name":null,"funder_award_id":"01IW23002","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1501005121","https://openalex.org/W1608118743","https://openalex.org/W1965305672","https://openalex.org/W1973003216","https://openalex.org/W2019312772","https://openalex.org/W2109606373","https://openalex.org/W2131797004","https://openalex.org/W2156503193","https://openalex.org/W2188997013","https://openalex.org/W2580010825","https://openalex.org/W2611009517","https://openalex.org/W2792010632","https://openalex.org/W2794079986","https://openalex.org/W2988053367","https://openalex.org/W3016342473","https://openalex.org/W3020487153","https://openalex.org/W3022720704","https://openalex.org/W3031098130","https://openalex.org/W3080131322","https://openalex.org/W3091793048","https://openalex.org/W3093919292","https://openalex.org/W3095436900","https://openalex.org/W4205678521","https://openalex.org/W4237382646","https://openalex.org/W4387031219","https://openalex.org/W4399523456","https://openalex.org/W4403912776"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,133],"pervasive":[1],"integration":[2],"of":[3,90,135],"artificial":[4],"intelligence":[5],"(AI)":[6],"into":[7],"daily":[8],"life":[9],"has":[10,27],"led":[11],"to":[12,33,57,78,99,139],"a":[13,30,112,118,166,180],"growing":[14],"interest":[15,69],"in":[16,41,62,70,106],"AI":[17],"agents":[18],"that":[19],"can":[20,55,145],"learn":[21],"continuously.":[22],"Interactive":[23],"Machine":[24],"Learning":[25],"(IML)":[26],"emerged":[28],"as":[29,94,128,165],"promising":[31],"approach":[32],"meet":[34],"this":[35],"need,":[36],"essentially":[37],"involving":[38],"human":[39],"experts":[40],"the":[42,63,88,136],"model":[43,174],"training":[44],"process,":[45],"often":[46],"through":[47],"iterative":[48],"user":[49,83,101,147],"feedback.":[50],"However,":[51],"repeated":[52],"feedback":[53,97,168],"requests":[54],"lead":[56],"frustration":[58],"and":[59,122,172],"reduced":[60],"trust":[61],"system.":[64],"Hence,":[65],"there":[66],"is":[67],"increasing":[68],"refining":[71],"how":[72],"these":[73],"systems":[74],"interact":[75],"with":[76,103,114],"users":[77,178],"ensure":[79],"efficiency":[80],"without":[81],"compromising":[82],"experience.":[84],"Our":[85,156],"research":[86],"investigates":[87],"potential":[89],"eye":[91,125,142,161],"tracking":[92,143,162],"data":[93,127,144],"an":[95],"implicit":[96],"mechanism":[98],"detect":[100],"disagreement":[102,150],"AI-generated":[104],"captions":[105],"image":[107],"captioning":[108,120],"systems.":[109],"We":[110],"conducted":[111],"study":[113,137],"30":[115],"participants":[116],"using":[117],"simulated":[119],"interface":[121],"gathered":[123],"their":[124],"movement":[126],"they":[129],"assessed":[130],"caption":[131],"accuracy.":[132],"goal":[134],"was":[138],"determine":[140],"whether":[141],"predict":[146],"agreement":[148],"or":[149],"effectively,":[151],"thereby":[152],"strengthening":[153],"IML":[154],"frameworks.":[155],"findings":[157],"reveal":[158],"that,":[159],"while":[160],"shows":[163],"promise":[164],"valuable":[167],"source,":[169],"ensuring":[170],"consistent":[171],"reliable":[173],"performance":[175],"across":[176],"diverse":[177],"remains":[179],"challenge.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}