{"id":"https://openalex.org/W7138389781","doi":"https://doi.org/10.1609/aaai.v40i8.37542","title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","display_name":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138389781","doi":"https://doi.org/10.1609/aaai.v40i8.37542"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i8.37542","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37542","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37542/41504","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37542/41504","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129670449","display_name":"Jia Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129645335","display_name":"Wenjie Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Zhao","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034946608","display_name":"Ziru Huang","orcid":"https://orcid.org/0009-0006-2380-3676"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziru Huang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685240","display_name":"Yunhui Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunhui Guo","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129650259","display_name":"Yapeng Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yapeng Tian","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6172","last_page":"6180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7347999811172485,"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/T10860","display_name":"Speech and Audio Processing","score":0.7347999811172485,"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/T11309","display_name":"Music and Audio Processing","score":0.18310000002384186,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.01860000006854534,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8009999990463257},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7159000039100647},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4023999869823456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38370001316070557},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.3797000050544739}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8009999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236999869346619},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7159000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4023999869823456},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3797000050544739},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.27320000529289246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i8.37542","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37542","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37542/41504","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37542","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37542","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37542/41504","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138389781.pdf","grobid_xml":"https://content.openalex.org/works/W7138389781.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unlike":[0],"traditional":[1],"visual":[2,70],"segmentation,":[3],"audio-visual":[4,46],"segmentation":[5,65,161],"(AVS)":[6],"requires":[7],"the":[8,74],"model":[9],"not":[10],"only":[11],"to":[12,19,48,63],"identify":[13],"and":[14,105,122,150],"segment":[15,49],"objects":[16],"but":[17],"also":[18,109],"determine":[20],"whether":[21],"they":[22,61],"are":[23,83],"sound":[24],"sources.":[25],"Recent":[26],"AVS":[27,133],"approaches":[28],"have":[29],"achieved":[30],"impressive":[31],"performance":[32],"on":[33,69],"standard":[34,148],"benchmarks.":[35],"Yet,":[36],"an":[37],"important":[38],"question":[39],"remains:":[40],"Do":[41],"these":[42],"models":[43],"genuinely":[44],"integrate":[45],"cues":[47],"sounding":[50],"objects?":[51],"Our":[52,126],"study":[53],"reveals":[54],"a":[55,94,111],"fundamental":[56],"bias":[57],"in":[58,78,146],"current":[59],"methods:":[60],"tend":[62],"generate":[64],"masks":[66],"based":[67],"predominantly":[68],"salience,":[71],"irrespective":[72],"of":[73],"audio":[75,100,139],"context,":[76],"resulting":[77],"unreliable":[79],"predictions":[80],"when":[81],"sounds":[82],"absent":[84],"or":[85],"irrelevant.":[86],"To":[87],"address":[88],"this":[89],"challenge,":[90],"we":[91],"introduce":[92],"AVSBench-Robust,":[93],"comprehensive":[95],"benchmark":[96],"incorporating":[97],"diverse":[98],"negative":[99,120,138],"scenarios,":[101],"including":[102],"silence,":[103],"noise,":[104],"off-screen":[106],"sounds.":[107],"We":[108],"propose":[110],"simple":[112],"yet":[113],"effective":[114],"approach":[115,142],"combining":[116],"balanced":[117],"training":[118],"with":[119],"samples":[121],"classifier-guided":[123],"similarity":[124],"learning.":[125],"extensive":[127],"experiments":[128],"show":[129],"that":[130],"while":[131,158],"state-of-the-art":[132],"methods":[134],"consistently":[135],"fail":[136],"under":[137],"conditions,":[140],"our":[141],"achieves":[143],"remarkable":[144],"improvements":[145],"both":[147],"metrics":[149],"robustness":[151],"measures,":[152],"maintaining":[153],"near-perfect":[154],"false":[155],"positive":[156],"rates":[157],"preserving":[159],"high-quality":[160],"performance.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}