{"id":"https://openalex.org/W4415540290","doi":"https://doi.org/10.1145/3746027.3758305","title":"BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos","display_name":"BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540290","doi":"https://doi.org/10.1145/3746027.3758305"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Jiahao Lin","orcid":"https://orcid.org/0009-0002-6004-1325"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahao Lin","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-6004-1325","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weixuan Peng","orcid":"https://orcid.org/0009-0005-9123-5108"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixuan Peng","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-9123-5108","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003572809","display_name":"Bojia Zi","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bojia Zi","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0003-6283-895X","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112472396","display_name":"Yifeng Gao","orcid":"https://orcid.org/0000-0001-5034-1928"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Gao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5034-1928","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020400305","display_name":"Xianbiao Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianbiao Qi","raw_affiliation_strings":["IntelliFusion Inc., Shenzhen City, China"],"raw_orcid":"https://orcid.org/0000-0002-8493-1966","affiliations":[{"raw_affiliation_string":"IntelliFusion Inc., Shenzhen City, China","institution_ids":["https://openalex.org/I4210105229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078711649","display_name":"Xingjun Ma","orcid":"https://orcid.org/0000-0003-2099-4973"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjun Ma","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2099-4973","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28928445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13421","last_page":"13427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994000196456909,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994000196456909,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9991000294685364,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.7797999978065491},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7538999915122986},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7480999827384949},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.49050000309944153},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44999998807907104},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44119998812675476},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821399986743927},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.7797999978065491},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7538999915122986},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7480999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.694599986076355},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44119998812675476},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4239000082015991},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1494182798","https://openalex.org/W2906365278","https://openalex.org/W2963253279","https://openalex.org/W3169396366","https://openalex.org/W4322576459","https://openalex.org/W4385901360","https://openalex.org/W4390874580","https://openalex.org/W4400034303","https://openalex.org/W4413144784"],"related_works":[],"abstract_inverted_index":{"The":[0,248],"field":[1],"of":[2,22,61,65,162,170],"video":[3,126,187,242],"generation":[4,243],"has":[5],"witnessed":[6],"remarkable":[7],"advances":[8],"in":[9,15,114,240],"recent":[10],"years,":[11],"driven":[12],"by":[13],"innovations":[14],"deep":[16],"generative":[17],"models.":[18],"Nevertheless,":[19],"the":[20,102,125,168],"fidelity":[21],"AI-generated":[23,115,154],"videos":[24,155],"remains":[25],"far":[26],"from":[27],"perfect,":[28],"with":[29,156],"synthesized":[30],"content":[31],"frequently":[32],"exhibiting":[33],"visual":[34,163],"artifacts,":[35],"such":[36],"as":[37],"temporally":[38],"inconsistent":[39],"motion,":[40],"physically":[41],"implausible":[42],"trajectories,":[43],"unnatural":[44],"object":[45],"deformations,":[46],"and":[47,53,58,91,97,138,191,213,227,244],"local":[48],"blurring,":[49],"that":[50,78,184,218],"undermine":[51],"realism":[52],"user":[54,80],"trust.":[55],"Precise":[56],"detection":[57,123,189],"spatial":[59,133],"localization":[60,113,140,180,230],"these":[62],"artifacts":[63],"are":[64,70],"critical":[66,222],"importance:":[67],"not":[68],"only":[69],"they":[71,83],"essential":[72],"for":[73,89,111,136,178,224],"automatic":[74],"quality":[75,246],"control":[76],"pipelines":[77],"improves":[79],"experience,":[81],"but":[82],"also":[84],"provide":[85],"actionable":[86],"diagnostic":[87],"signals":[88],"researchers":[90],"practitioners":[92],"to":[93,203],"guide":[94],"model":[95],"development":[96],"evaluation.":[98],"Despite":[99],"its":[100,245],"significance,":[101],"research":[103],"community":[104],"currently":[105],"lacks":[106],"a":[107,149,221],"comprehensive":[108],"benchmark":[109,150],"tailored":[110],"artifact":[112,179,188,229],"videos.":[116],"Existing":[117],"datasets":[118],"either":[119],"focus":[120],"solely":[121],"on":[122,197],"at":[124],"or":[127,130],"frame":[128],"level,":[129],"lack":[131],"fine-grained":[132],"annotations":[134],"necessary":[135],"developing":[137],"benchmarking":[139,226],"methods.":[141],"To":[142],"fill":[143],"this":[144],"gap,":[145],"we":[146,216],"present":[147],"BrokenVideos,":[148],"dataset":[151,235,249],"comprising":[152],"~3,254":[153],"carefully-annotated,":[157],"pixel-level":[158],"masks":[159],"indicating":[160],"regions":[161,206],"corruption.":[164],"Each":[165],"annotation":[166],"is":[167,250],"result":[169],"careful":[171],"human":[172],"inspection,":[173],"ensuring":[174],"high-quality":[175],"ground":[176],"truth":[177],"tasks.":[181],"We":[182,232],"demonstrate":[183],"training":[185],"existing":[186],"models":[190,195],"multi-modal":[192],"large":[193],"language":[194],"(MLLMs)":[196],"BrokenVideos":[198,219],"substantially":[199],"enhances":[200],"their":[201],"ability":[202],"localize":[204],"corrupted":[205],"within":[207],"generated":[208],"content.":[209],"Through":[210],"extensive":[211],"experiments":[212],"cross-model":[214],"evaluations,":[215],"show":[217],"provides":[220],"foundation":[223],"both":[225,241],"advancing":[228],"research.":[231],"hope":[233],"our":[234],"can":[236],"catalyze":[237],"further":[238],"innovation":[239],"assurance.":[247],"available":[251],"at:":[252],"https://broken-video-detection-datetsets.github.io/Broken-Video-Detection-Datasets.github.io/.":[253]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}