{"id":"https://openalex.org/W4414360578","doi":"https://doi.org/10.24963/ijcai.2025/65","title":"Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network","display_name":"Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360578","doi":"https://doi.org/10.24963/ijcai.2025/65"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/65","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/65","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5101741886","display_name":"Junyan Wu","orcid":"https://orcid.org/0000-0003-2692-5928"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyan Wu","raw_affiliation_strings":["MoE Key Laboratory of Information Technology, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Information Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720681","display_name":"Wenbo Xu","orcid":"https://orcid.org/0000-0001-8704-1937"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Xu","raw_affiliation_strings":["MoE Key Laboratory of Information Technology, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Information Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083054357","display_name":"Wei Lu","orcid":"https://orcid.org/0000-0002-4068-1766"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lu","raw_affiliation_strings":["MoE Key Laboratory of Information Technology, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Information Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018721","display_name":"Xiangyang Luo","orcid":"https://orcid.org/0000-0001-6062-2950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyang Luo","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010069292","display_name":"Rui Yang","orcid":"https://orcid.org/0009-0008-7446-7216"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Yang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102312791","display_name":"Shize Guo","orcid":"https://orcid.org/0009-0002-9718-1321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shize Guo","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27388471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"574","last_page":"582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9559000134468079,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9509000182151794,"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/leverage","display_name":"Leverage (statistics)","score":0.7786999940872192},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6007000207901001},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4034000039100647},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3352999985218048},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.2955999970436096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2921000123023987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7786999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6007000207901001},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2687999904155731}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/65","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/65","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio":[0],"temporal":[1,87,112],"forgery":[2,10,80,119,126],"localization":[3,64,120],"(ATFL)":[4],"aims":[5],"to":[6,62,78,124,141,152],"find":[7],"the":[8,13,154,171],"precise":[9],"regions":[11],"of":[12],"partial":[14],"spoof":[15],"audio":[16],"that":[17,56,170],"is":[18,75,122,139],"purposefully":[19],"modified.":[20],"Existing":[21],"ATFL":[22],"methods":[23],"rely":[24],"on":[25,129,177],"training":[26],"efficient":[27],"networks":[28],"using":[29,99],"fine-grained":[30],"annotations,":[31],"which":[32,106],"are":[33,96],"obtained":[34],"costly":[35],"and":[36,59,88,146,159],"challenging":[37],"in":[38,45],"real-world":[39],"scenarios.":[40,69],"To":[41],"meet":[42],"this":[43,46,92],"challenge,":[44],"paper,":[47],"we":[48],"propose":[49],"a":[50,118,135],"progressive":[51,136],"audio-language":[52,72],"co-learning":[53,58,73],"network":[54],"(LOCO)":[55],"adopts":[57],"self-supervision":[60],"manners":[61],"prompt":[63],"performance":[65,176],"under":[66],"weak":[67],"supervision":[68],"Specifically,":[70],"an":[71],"module":[74,121],"first":[76],"designed":[77],"capture":[79],"consensus":[81],"features":[82,114],"by":[83,98],"aligning":[84],"semantics":[85],"from":[86],"global":[89],"perspectives.":[90],"In":[91,116],"module,":[93],"forgery-aware":[94,165],"prompts":[95],"constructed":[97],"utterance-level":[100],"annotations":[101],"together":[102],"with":[103],"learnable":[104],"prompts,":[105],"can":[107],"incorporate":[108],"semantic":[109,149,155],"priors":[110],"into":[111],"content":[113],"dynamically.":[115],"addition,":[117],"applied":[123],"produce":[125],"proposals":[127],"based":[128],"fused":[130],"forgery-class":[131],"activation":[132],"sequences.":[133],"Finally,":[134],"refinement":[137],"strategy":[138],"introduced":[140],"generate":[142],"pseudo":[143],"frame-level":[144],"labels":[145],"leverage":[147],"supervised":[148],"contrastive":[150],"learning":[151],"amplify":[153],"distinction":[156],"between":[157],"real":[158],"fake":[160],"content,":[161],"thereby":[162],"continuously":[163],"optimizing":[164],"features.":[166],"Extensive":[167],"experiments":[168],"show":[169],"proposed":[172],"LOCO":[173],"achieves":[174],"SOTA":[175],"three":[178],"public":[179],"benchmarks.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}