{"id":"https://openalex.org/W4403791349","doi":"https://doi.org/10.1145/3664647.3681586","title":"Open-Vocabulary Audio-Visual Semantic Segmentation","display_name":"Open-Vocabulary Audio-Visual Semantic Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791349","doi":"https://doi.org/10.1145/3664647.3681586"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681586","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681586?download=true","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681586?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088611866","display_name":"Ruohao Guo","orcid":"https://orcid.org/0000-0002-1091-272X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruohao Guo","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1091-272X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046273191","display_name":"Liao Qu","orcid":"https://orcid.org/0000-0001-5228-0348"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liao Qu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5228-0348","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021184639","display_name":"Dantong Niu","orcid":"https://orcid.org/0009-0006-7421-5858"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dantong Niu","raw_affiliation_strings":["Berkeley AI Research, University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-7421-5858","affiliations":[{"raw_affiliation_string":"Berkeley AI Research, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054577986","display_name":"Yanyu Qi","orcid":"https://orcid.org/0009-0008-9931-7855"},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyu Qi","raw_affiliation_strings":["College of Information and Electrical Engineering, China Agricultural University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9931-7855","affiliations":[{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, China","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033503889","display_name":"Wenzhen Yue","orcid":"https://orcid.org/0000-0002-5165-0869"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhen Yue","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5165-0869","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113749469","display_name":"Shi Jun Ji","orcid":"https://orcid.org/0009-0009-4584-4569"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Shi","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4584-4569","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028438544","display_name":"Bowei Xing","orcid":"https://orcid.org/0009-0001-3254-3902"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowei Xing","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3254-3902","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015981200","display_name":"Xianghua Ying","orcid":"https://orcid.org/0000-0002-9785-0727"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghua Ying","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9785-0727","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5088611866"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.9865,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76164979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7533","last_page":"7541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8029007911682129},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6553006768226624},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6102386713027954},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5989450812339783},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5724959373474121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5284050703048706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.431761771440506},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4305749535560608},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3249261975288391},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15776866674423218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029007911682129},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6553006768226624},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6102386713027954},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5989450812339783},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5724959373474121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5284050703048706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.431761771440506},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4305749535560608},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3249261975288391},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15776866674423218},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681586","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681586?download=true","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":{"id":"doi:10.1145/3664647.3681586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681586","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681586?download=true","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1021494965","display_name":null,"funder_award_id":"62371009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4268905062","display_name":null,"funder_award_id":"61971008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403791349.pdf","grobid_xml":"https://content.openalex.org/works/W4403791349.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2596164567","https://openalex.org/W2604292070","https://openalex.org/W2948672349","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3180659539","https://openalex.org/W3213165621","https://openalex.org/W4214654781","https://openalex.org/W4234552385","https://openalex.org/W4301409532","https://openalex.org/W4310557340","https://openalex.org/W4312458986","https://openalex.org/W4312815172","https://openalex.org/W4313123347","https://openalex.org/W4387969151","https://openalex.org/W4387969495","https://openalex.org/W4390872864","https://openalex.org/W4390874578","https://openalex.org/W4393159433","https://openalex.org/W4393160420","https://openalex.org/W4402660154","https://openalex.org/W4403386295"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Audio-visual":[0],"semantic":[1,53],"segmentation":[2,166],"(AVSS)":[3],"aims":[4],"to":[5,36,58,110,126],"segment":[6],"and":[7,24,114,120,151,167,188,201],"classify":[8],"sounding":[9,118],"objects":[10,119],"in":[11,40],"videos":[12],"with":[13,129],"acoustic":[14],"cues.":[15],"However,":[16],"most":[17],"approaches":[18],"operate":[19],"on":[20,155,174,185,191],"the":[21,33,62,91,130,133,144,156,164,178,195],"close-set":[22],"assumption":[23],"only":[25],"identify":[26],"pre-defined":[27],"categories":[28,39,128,187],"from":[29,136],"training":[30,150],"data,":[31],"lacking":[32],"generalization":[34,169],"ability":[35,170],"detect":[37],"novel":[38,192],"practical":[41],"applications.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,89,147],"introduce":[47],"a":[48,68,104],"new":[49],"task:":[50],"open-vocabulary":[51,93,123,145,202],"audio-visual":[52,112],"segmentation,":[54],"extending":[55],"AVSS":[56,94],"task":[57,71],"open-world":[59],"scenarios":[60],"beyond":[61],"annotated":[63],"label":[64],"space.":[65],"This":[66],"is":[67,208],"more":[69],"challenging":[70],"that":[72,79],"requires":[73],"recognizing":[74],"all":[75,116,175],"categories,":[76,193],"even":[77],"those":[78],"have":[80],"never":[81],"been":[82],"seen":[83],"nor":[84],"heard":[85],"during":[86],"training.":[87],"Moreover,":[88],"propose":[90],"first":[92],"framework,":[95],"OV-AVSS,":[96],"which":[97],"mainly":[98],"consists":[99],"of":[100,132,171],"two":[101],"parts:":[102],"1)":[103],"universal":[105],"sound":[106],"source":[107],"localization":[108],"module":[109,125],"perform":[111],"fusion":[113],"locate":[115],"potential":[117],"2)":[121],"an":[122],"classification":[124],"predict":[127],"help":[131],"prior":[134],"knowledge":[135],"large-scale":[137],"pre-trained":[138],"vision-language":[139],"models.":[140],"To":[141],"properly":[142],"evaluate":[143],"AVSS,":[146],"split":[148],"zero-shot":[149,168,197],"testing":[152],"subsets":[153],"based":[154],"AVSBench-semantic":[157],"benchmark,":[158],"namely":[159],"AVSBench-OV.":[160],"Extensive":[161],"experiments":[162],"demonstrate":[163],"strong":[165],"our":[172],"model":[173],"categories.":[176],"On":[177],"AVSBench-OV":[179],"dataset,":[180],"OV-AVSS":[181],"achieves":[182],"55.43%":[183],"mIoU":[184,190],"base":[186],"29.14%":[189],"exceeding":[194],"state-of-the-art":[196],"method":[198,203],"by":[199,204],"41.88%/20.61%":[200],"10.2%/11.6%.":[205],"The":[206],"code":[207],"available":[209],"at":[210],"https://github.com/ruohaoguo/ovavss.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}