{"id":"https://openalex.org/W4411550022","doi":"https://doi.org/10.1145/3701716.3715306","title":"RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection","display_name":"RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4411550022","doi":"https://doi.org/10.1145/3701716.3715306"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715306","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715306","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715306","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715306","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108941667","display_name":"Liting Huang","orcid":"https://orcid.org/0009-0008-5585-6363"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Liting Huang","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0008-5585-6363","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038942858","display_name":"Zhihao Zhang","orcid":"https://orcid.org/0000-0002-0166-3442"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhihao Zhang","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0166-3442","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiran Zhang","orcid":"https://orcid.org/0009-0008-2156-3642"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yiran Zhang","raw_affiliation_strings":["Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0008-2156-3642","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089765223","display_name":"Xiyue Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiyue Zhou","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0004-7629-3193","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082317196","display_name":"Shoujin Wang","orcid":"https://orcid.org/0000-0003-1133-9379"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shoujin Wang","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1133-9379","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108941667"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":4.232,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94316511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9927999973297119,"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":0.7334408760070801},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5997933149337769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723854899406433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35371527075767517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32735198736190796},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07076117396354675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334408760070801},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5997933149337769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723854899406433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35371527075767517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32735198736190796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07076117396354675},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715306","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715306","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715306","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715306","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715306","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715306","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411550022.pdf","grobid_xml":"https://content.openalex.org/works/W4411550022.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2015159529","https://openalex.org/W2185175083","https://openalex.org/W3114326827","https://openalex.org/W4312933868","https://openalex.org/W4372266896","https://openalex.org/W4380714711","https://openalex.org/W4386071472","https://openalex.org/W4386071707","https://openalex.org/W4402112533"],"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/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,24,186,227],"recent":[1],"generative":[2,225],"AI":[3,146],"models'":[4],"capability":[5],"of":[6,82,89,117,132,152,163,170,216,224],"creating":[7],"realistic":[8],"and":[9,22,99,114,123,140,197,230],"human-like":[10],"content":[11,26,61,119,218],"is":[12,27,67,127],"significantly":[13],"transforming":[14],"the":[15,37,43,53,80,87,130,164,168,178,214,221],"ways":[16],"in":[17,93,120,149,213],"which":[18],"people":[19],"communicate,":[20],"create":[21],"work.":[23],"machine-generated":[25,77,118,217],"a":[28,107,150],"double-edged":[29],"sword.":[30],"On":[31,42],"one":[32],"hand,":[33,45],"it":[34,46],"can":[35,210],"benefit":[36],"society":[38],"when":[39,56],"used":[40],"appropriately.":[41],"other":[44],"may":[47],"mislead":[48],"people,":[49],"posing":[50],"threats":[51],"to":[52,71,75,194],"society,":[54],"especially":[55],"mixed":[57],"together":[58],"with":[59,177],"natural":[60],"created":[62,158],"by":[63,142],"humans.":[64],"Hence,":[65],"there":[66],"an":[68,159],"urgent":[69],"need":[70],"develop":[72],"effective":[73,115],"methods":[74,182],"detect":[76],"content.":[78],"However,":[79],"lack":[81],"aligned":[83],"multimodal":[84,110],"datasets":[85,231],"inhibited":[86],"development":[88],"such":[90],"methods,":[91],"particularly":[92],"triple-modality":[94],"settings":[95],"(e.g.,":[96],"text,":[97,121],"image,":[98],"voice).":[100],"In":[101,155],"this":[102,206],"paper,":[103],"we":[104,157],"introduce":[105],"RU-AI,":[106],"new":[108,207],"large-scale":[109],"dataset":[111,126,165],"for":[112,166],"robust":[113,198],"detection":[116,171,181,199],"image":[122],"voice.":[124],"Our":[125],"constructed":[128],"on":[129,183,200],"basis":[131],"three":[133],"large":[134],"publicly":[135],"available":[136,233],"datasets:":[137],"Flickr8K,":[138],"COCO":[139],"Places205,":[141],"adding":[143],"their":[144],"corresponding":[145],"duplicates,":[147],"resulting":[148],"total":[151],"1,475,370":[153],"instances.":[154],"addition,":[156],"additional":[160],"noise":[161],"variant":[162],"testing":[167],"robustness":[169],"models.":[172],"We":[173,203],"conducted":[174],"extensive":[175],"experiments":[176],"current":[179],"SOTA":[180],"our":[184,201],"dataset.":[185,202],"results":[187],"reveal":[188],"that":[189,205],"existing":[190],"models":[191],"still":[192],"struggle":[193],"achieve":[195],"accurate":[196],"hope":[204],"data":[208],"set":[209],"promote":[211],"research":[212],"field":[215],"detection,":[219],"fostering":[220],"responsible":[222],"use":[223],"AI.":[226],"source":[228],"code":[229],"are":[232],"at":[234],"https://github.com/ZhihaoZhang97/RU-AI.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2025-10-10T00:00:00"}