{"id":"https://openalex.org/W4378783728","doi":"https://doi.org/10.3389/frai.2023.1048874","title":"Image\u2013text coherence and its implications for multimodal AI","display_name":"Image\u2013text coherence and its implications for multimodal AI","publication_year":2023,"publication_date":"2023-05-15","ids":{"openalex":"https://openalex.org/W4378783728","doi":"https://doi.org/10.3389/frai.2023.1048874","pmid":"https://pubmed.ncbi.nlm.nih.gov/37255946"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2023.1048874","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1048874","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1048874/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1048874/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025559955","display_name":"Malihe Alikhani","orcid":"https://orcid.org/0000-0002-1315-2228"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Malihe Alikhani","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, United States","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075684583","display_name":"Baber Khalid","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baber Khalid","raw_affiliation_strings":["Department of Computer Science, Rutgers University, Piscataway, NJ, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, Piscataway, NJ, United States","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086088412","display_name":"Matthew Stone","orcid":"https://orcid.org/0000-0003-3629-2941"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Stone","raw_affiliation_strings":["Department of Computer Science, Rutgers University, Piscataway, NJ, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, Piscataway, NJ, United States","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025559955"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":0.6766,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.65425743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"6","issue":null,"first_page":"1048874","last_page":"1048874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.992900013923645,"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":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.7776501178741455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6775073409080505},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6249421834945679},{"id":"https://openalex.org/keywords/pragmatics","display_name":"Pragmatics","score":0.5787420868873596},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5206598043441772},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.489624559879303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48667460680007935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46689069271087646},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.44081926345825195},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3670015335083008},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.33345934748649597},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.18501484394073486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16077739000320435},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09448179602622986},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.07726168632507324}],"concepts":[{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.7776501178741455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775073409080505},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6249421834945679},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.5787420868873596},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5206598043441772},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.489624559879303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48667460680007935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46689069271087646},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.44081926345825195},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3670015335083008},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33345934748649597},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.18501484394073486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16077739000320435},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09448179602622986},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.07726168632507324},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2023.1048874","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1048874","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1048874/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:37255946","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37255946","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10226667","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10226667","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10226667/pdf/frai-06-1048874.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:c70dd77197d94b4a84f161f7364011bf","is_oa":true,"landing_page_url":"https://doaj.org/article/c70dd77197d94b4a84f161f7364011bf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 6 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2023.1048874","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1048874","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1048874/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G3621817804","display_name":"CHS: Medium: Data Driven Biomechanically Accurate Modeling of Human Gait on Unconstrained Terrain","funder_award_id":"1703883","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6979405372","display_name":"EAGER: SAI: Cognitive Models of Human Social Wayfinding for the Redesign of Public Spaces","funder_award_id":"2122119","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7133055043","display_name":"HDR TRIPODS: Data Science Principles of the Human-Machine Convergence","funder_award_id":"1934924","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7338372148","display_name":"Collaborative Research: RI: Medium: Learning Joint Crowd-Space Embeddings for Cross-Modal Crowd Behavior Prediction","funder_award_id":"1955404","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7523493800","display_name":"RI: Small: Bayesian Modeling of Situated Communicative Goals","funder_award_id":"1526723","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7641858014","display_name":"NRT-FW-HTF: Socially Cognizant Robotics for a Technology Enhanced Society (SOCRATES)","funder_award_id":"2021628","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8492113617","display_name":"The Role of Agency and Interactivity in Embodied Conversational Agents to Support Teacher Training in High Poverty Schools","funder_award_id":"2119265","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8816859997","display_name":"Collaborative Research: RI: Medium: Learning Joint Crowd-Space Embeddings for Cross-Modal Crowd Behavior Prediction","funder_award_id":"1955365","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4378783728.pdf"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W658868551","https://openalex.org/W1498883201","https://openalex.org/W1560265695","https://openalex.org/W1586232984","https://openalex.org/W1605174196","https://openalex.org/W1974257828","https://openalex.org/W1985661114","https://openalex.org/W1991145433","https://openalex.org/W1995258346","https://openalex.org/W2057342209","https://openalex.org/W2084617042","https://openalex.org/W2109783296","https://openalex.org/W2118163921","https://openalex.org/W2120691627","https://openalex.org/W2132623301","https://openalex.org/W2143385847","https://openalex.org/W2146615318","https://openalex.org/W2150421899","https://openalex.org/W2167569123","https://openalex.org/W2185175083","https://openalex.org/W2252200119","https://openalex.org/W2322065245","https://openalex.org/W2482303859","https://openalex.org/W2602331152","https://openalex.org/W2612039655","https://openalex.org/W2798324445","https://openalex.org/W2809742878","https://openalex.org/W2810161883","https://openalex.org/W2886641317","https://openalex.org/W2890399523","https://openalex.org/W2903580678","https://openalex.org/W2915085887","https://openalex.org/W2952314184","https://openalex.org/W2953072307","https://openalex.org/W2964127652","https://openalex.org/W2966715458","https://openalex.org/W2970217405","https://openalex.org/W2999872742","https://openalex.org/W3035532688","https://openalex.org/W3045519025","https://openalex.org/W3111014400","https://openalex.org/W3112993007","https://openalex.org/W3200873909","https://openalex.org/W4236965008","https://openalex.org/W4241595053","https://openalex.org/W4288083516","https://openalex.org/W4288122175","https://openalex.org/W4288373474","https://openalex.org/W4301045096","https://openalex.org/W4385245566","https://openalex.org/W6630038781","https://openalex.org/W6639102338","https://openalex.org/W6640123859","https://openalex.org/W6684468177","https://openalex.org/W6737899427","https://openalex.org/W6739901393","https://openalex.org/W6755592957","https://openalex.org/W6761644171","https://openalex.org/W6765515772","https://openalex.org/W6766904570","https://openalex.org/W6783420912","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6804422790"],"related_works":["https://openalex.org/W1898246925","https://openalex.org/W2375878451","https://openalex.org/W4254159134","https://openalex.org/W4385582530","https://openalex.org/W1535074856","https://openalex.org/W2359993012","https://openalex.org/W3094205063","https://openalex.org/W2292366555","https://openalex.org/W2903036871","https://openalex.org/W2350073238"],"abstract_inverted_index":{"Human":[0],"communication":[1],"often":[2],"combines":[3],"imagery":[4],"and":[5,83,116,131,158,168],"text":[6],"into":[7],"integrated":[8],"presentations,":[9],"especially":[10],"online.":[11],"In":[12,34],"this":[13],"paper,":[14],"we":[15,143],"show":[16],"how":[17,100],"image-text":[18,29,41,150,162],"coherence":[19,55,122,148,154,159],"relations":[20,68],"can":[21],"be":[22],"used":[23],"to":[24,36,69,112],"model":[25],"the":[26,46,73,97,101,106,113],"pragmatics":[27],"of":[28,45,51,61,72,109,121,134,161],"presentations":[30,42],"in":[31,43,65,96,149],"AI":[32],"systems.":[33],"contrast":[35],"alternative":[37],"frameworks":[38],"that":[39,58,125],"characterize":[40,93],"terms":[44],"priority,":[47],"relevance,":[48],"or":[49,110],"overlap":[50],"information":[52,81],"across":[53],"modalities,":[54],"theory":[56,123],"postulates":[57],"each":[59,76],"unit":[60],"a":[62,128],"discourse":[63],"stands":[64],"specific":[66],"pragmatic":[67],"other":[70],"parts":[71],"discourse,":[74],"with":[75],"relation":[77],"involving":[78],"its":[79],"own":[80],"goals":[82,136],"inferential":[84],"connections.":[85],"Text":[86],"accompanying":[87],"an":[88],"image":[89,102],"may,":[90],"for":[91,137],"example,":[92],"what's":[94],"visible":[95],"image,":[98],"explain":[99],"was":[103],"obtained,":[104],"offer":[105],"author's":[107],"appraisal":[108],"reaction":[111],"depicted":[114],"situation,":[115],"so":[117],"forth.":[118],"The":[119],"advantage":[120],"is":[124],"it":[126],"provides":[127],"simple,":[129],"robust,":[130],"effective":[132],"abstraction":[133],"communicative":[135],"practical":[138],"applications.":[139],"To":[140],"argue":[141],"this,":[142],"review":[144],"case":[145],"studies":[146],"describing":[147],"data":[151],"sets,":[152],"predicting":[153],"from":[155],"few-shot":[156],"annotations,":[157],"models":[160],"tasks":[163],"such":[164],"as":[165],"caption":[166,169],"generation":[167],"evaluation.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}