{"id":"https://openalex.org/W4385767885","doi":"https://doi.org/10.24963/ijcai.2023/97","title":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","display_name":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767885","doi":"https://doi.org/10.24963/ijcai.2023/97"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/97","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/97","pdf_url":"https://www.ijcai.org/proceedings/2023/0097.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0097.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024226895","display_name":"Shaofei Huang","orcid":"https://orcid.org/0000-0001-8996-9907"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaofei Huang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences","School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452620","display_name":"Han Li","orcid":"https://orcid.org/0000-0003-1983-5158"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461350","display_name":"Yuqing Wang","orcid":"https://orcid.org/0009-0006-3161-0364"},"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":"Yuqing Wang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113972354","display_name":"Hongji Zhu","orcid":null},"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":"Hongji Zhu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031794241","display_name":"Jiao Dai","orcid":"https://orcid.org/0000-0003-3559-8009"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Dai","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences","School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112539471","display_name":"Jizhong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhong Han","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences","School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055420596","display_name":"Wenge Rong","orcid":"https://orcid.org/0000-0002-4229-7215"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenge Rong","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Hangzhou Innovation Institute, Beihang University","Institute of Artificial Intelligence, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I4210105595"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5024226895"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.7444,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94503656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"875","last_page":"883"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9850000143051147,"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/computer-science","display_name":"Computer science","score":0.7966971397399902},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6512649655342102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5867603421211243},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5404738783836365},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5304913520812988},{"id":"https://openalex.org/keywords/depth-sounding","display_name":"Depth sounding","score":0.5058836340904236},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4978141784667969},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49364909529685974},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.4463613033294678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36199864745140076},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12666887044906616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966971397399902},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6512649655342102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867603421211243},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5404738783836365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5304913520812988},{"id":"https://openalex.org/C55510283","wikidata":"https://www.wikidata.org/wiki/Q1382947","display_name":"Depth sounding","level":2,"score":0.5058836340904236},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4978141784667969},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49364909529685974},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.4463613033294678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36199864745140076},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12666887044906616},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/97","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/97","pdf_url":"https://www.ijcai.org/proceedings/2023/0097.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/97","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/97","pdf_url":"https://www.ijcai.org/proceedings/2023/0097.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2540017325","display_name":null,"funder_award_id":"LDT23F02022F02","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G5696407354","display_name":null,"funder_award_id":"62122010","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"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767885.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2470139095","https://openalex.org/W2517503862","https://openalex.org/W2526050071","https://openalex.org/W2552900565","https://openalex.org/W2561585794","https://openalex.org/W2630837129","https://openalex.org/W2955058313","https://openalex.org/W2962699416","https://openalex.org/W2962914239","https://openalex.org/W2964199361","https://openalex.org/W2982619606","https://openalex.org/W2990205821","https://openalex.org/W2990408345","https://openalex.org/W3094502228","https://openalex.org/W3094664776","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3108367559","https://openalex.org/W3165745140","https://openalex.org/W3170630188","https://openalex.org/W3175515048","https://openalex.org/W3211993051","https://openalex.org/W3213165621","https://openalex.org/W3215899623","https://openalex.org/W4214893857","https://openalex.org/W4226024706","https://openalex.org/W4284898017","https://openalex.org/W4307004479","https://openalex.org/W4308909683","https://openalex.org/W4312690830","https://openalex.org/W4312815172","https://openalex.org/W4313123347"],"related_works":["https://openalex.org/W2809612451","https://openalex.org/W1974079146","https://openalex.org/W2373976954","https://openalex.org/W2616411725","https://openalex.org/W2271369634","https://openalex.org/W2474955975","https://openalex.org/W2383251271","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2386558711"],"abstract_inverted_index":{"Audio":[0],"visual":[1,49,99,108],"segmentation":[2],"(AVS)":[3],"aims":[4],"to":[5,41,88,122,144],"segment":[6],"the":[7,19,131,160],"sounding":[8,20,90,124],"objects":[9,21],"for":[10],"each":[11,85],"frame":[12],"of":[13,51,76,86,133],"a":[14,74],"given":[15],"video.":[16],"To":[17],"distinguish":[18],"from":[22,107],"silent":[23],"ones,":[24],"both":[25,57],"audio-visual":[26],"semantic":[27,94],"correspondence":[28,95],"and":[29,48,59,83,98,155],"temporal":[30],"interaction":[31],"are":[32,138],"required.":[33],"The":[34],"previous":[35],"method":[36,148],"applies":[37],"multi-frame":[38],"cross-modal":[39],"attention":[40],"conduct":[42],"pixel-level":[43],"interactions":[44],"between":[45,96],"audio":[46,81,97,112,134],"features":[47,50,109],"multiple":[52,128],"frames":[53,129],"simultaneously,":[54],"which":[55],"is":[56,101,120],"redundant":[58],"implicit.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,72],"propose":[65],"an":[66,115],"Audio-Queried":[67],"Transformer":[68],"architecture,":[69],"AQFormer,":[70],"where":[71],"define":[73],"set":[75],"object":[77,105],"queries":[78],"conditioned":[79],"on":[80,140,159],"information":[82,106,126],"associate":[84],"them":[87],"particular":[89],"objects.":[91],"Explicit":[92],"object-level":[93],"modalities":[100],"established":[102],"by":[103],"gathering":[104],"with":[110,130],"predefined":[111],"queries.":[113],"Besides,":[114],"Audio-Bridged":[116],"Temporal":[117],"Interaction":[118],"module":[119],"proposed":[121],"exchange":[123],"object-relevant":[125],"among":[127],"bridge":[132],"features.":[135],"Extensive":[136],"experiments":[137],"conducted":[139],"two":[141],"AVS":[142],"benchmarks":[143],"show":[145],"that":[146],"our":[147],"achieves":[149],"state-of-the-art":[150],"performances,":[151],"especially":[152],"7.1%":[153],"M_J":[154],"7.6%":[156],"M_F":[157],"gains":[158],"MS3":[161],"setting.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
