{"id":"https://openalex.org/W4403791645","doi":"https://doi.org/10.1145/3664647.3676596","title":"Large Multimodal Models as Social Multimedia Analysis Engines","display_name":"Large Multimodal Models as Social Multimedia Analysis Engines","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791645","doi":"https://doi.org/10.1145/3664647.3676596"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3676596","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3676596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4516-9729","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055469774"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.5299999713897705,"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":0.5299999713897705,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.484499990940094,"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":0.7399541735649109},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5851803421974182},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3559154272079468},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34412848949432373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7399541735649109},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5851803421974182},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3559154272079468},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34412848949432373}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3676596","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3676596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4399722036"],"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":{"Recent":[0],"research":[1],"has":[2,200],"offered":[3],"insights":[4,224],"into":[5],"the":[6,54,66,137,182,205,218,247],"extraordinary":[7],"capabilities":[8,88],"of":[9,136,142,168,239,249],"Large":[10],"Multimodal":[11],"Models":[12],"(LMMs)":[13],"in":[14,25,29,149,159,202,208,235],"various":[15],"general":[16],"vision":[17],"and":[18,42,62,109,139,172,175,199,243],"language":[19],"tasks.":[20,222],"There":[21],"is":[22],"growing":[23],"interest":[24],"how":[26],"LMMs":[27,234],"perform":[28],"more":[30],"specialized":[31],"domains.":[32],"Social":[33],"media":[34,153,241],"content,":[35,49],"inherently":[36],"multimodal,":[37],"blends":[38],"text,":[39],"images,":[40],"videos,":[41],"sometimes":[43],"audio.":[44],"To":[45],"effectively":[46],"understand":[47],"such":[48,164],"models":[50],"need":[51],"to":[52,113,181,204,216],"interpret":[53],"intricate":[55],"interactions":[56],"between":[57],"these":[58,160],"diverse":[59],"communication":[60],"modalities":[61],"their":[63],"impact":[64],"on":[65,220],"conveyed":[67],"message.":[68],"Understanding":[69],"social":[70,90,152,196,209,240],"multimedia":[71,91,197],"content":[72,242],"remains":[73],"a":[74,120,133,140,230],"challenging":[75],"problem":[76],"for":[77,89,124,233],"contemporary":[78],"machine":[79],"learning":[80],"frameworks.":[81],"In":[82,179],"this":[83],"talk,":[84],"we":[85],"evaluate":[86,114],"GPT-4V(ision)'s":[87],"analysis.":[92],"We":[93,211],"select":[94],"five":[95],"representative":[96],"tasks,":[97,161],"including":[98],"sentiment":[99],"analysis,":[100],"hate":[101],"speech":[102],"detection,":[103,112],"fake":[104],"news":[105],"identification,":[106],"demographic":[107],"inference,":[108],"political":[110],"ideology":[111],"GPT-4V.":[115],"Our":[116],"investigation":[117],"begins":[118],"with":[119,192],"preliminary":[121],"quantitative":[122],"analysis":[123,248],"each":[125],"task":[126],"using":[127],"existing":[128],"benchmark":[129],"datasets,":[130],"followed":[131],"by":[132],"careful":[134],"review":[135],"results":[138],"selection":[141],"qualitative":[143],"samples":[144],"that":[145],"illustrate":[146],"GPT-4V's":[147],"potential":[148],"understanding":[150,167],"multimodal":[151,250],"content.":[154],"GPT-4V":[155,190],"demonstrates":[156],"remarkable":[157],"efficacy":[158],"showcasing":[162],"strengths":[163],"as":[165,189],"joint":[166],"image-text":[169],"pairs,":[170],"contextual":[171],"cultural":[173],"awareness,":[174],"extensive":[176],"commonsense":[177],"knowledge.":[178],"addition":[180],"known":[183],"hallucination":[184],"problem,":[185],"notable":[186],"challenges":[187],"remain":[188],"struggles":[191],"tasks":[193],"involving":[194],"multilingual":[195],"comprehension":[198,238],"difficulties":[201],"generalizing":[203],"latest":[206],"trends":[207],"media.":[210],"further":[212],"present":[213],"several":[214],"attempts":[215],"improve":[217],"performance":[219],"some":[221],"The":[223],"gleaned":[225],"from":[226],"our":[227,237],"findings":[228],"underscore":[229],"promising":[231],"future":[232],"enhancing":[236],"its":[244],"users":[245],"through":[246],"information.":[251]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}