{"id":"https://openalex.org/W4387969495","doi":"https://doi.org/10.1145/3581783.3611724","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","display_name":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969495","doi":"https://doi.org/10.1145/3581783.3611724"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611724","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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":"https://openalex.org/A5103066100","display_name":"Kexin Li","orcid":"https://orcid.org/0009-0001-4479-5920"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kexin Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020316185","display_name":"Zongxin Yang","orcid":"https://orcid.org/0000-0001-8783-8313"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongxin Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064062823","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-4912-3293"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Finvolution Group, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Finvolution Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103066100"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":9.5441,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.98794436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1485","last_page":"1494"},"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":0.9991999864578247,"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":0.9890000224113464,"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/computer-science","display_name":"Computer science","score":0.8811572790145874},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6092472076416016},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6023736596107483},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5766467452049255},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5323970913887024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48486456274986267},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.46659234166145325},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43710488080978394},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42213329672813416},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4181341528892517},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4049258530139923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34466809034347534},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3191004693508148},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.1660085916519165},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.09044307470321655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8811572790145874},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6092472076416016},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6023736596107483},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5766467452049255},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5323970913887024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48486456274986267},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46659234166145325},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43710488080978394},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42213329672813416},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4181341528892517},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4049258530139923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34466809034347534},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3191004693508148},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.1660085916519165},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.09044307470321655},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611724","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G297858759","display_name":null,"funder_award_id":"U19B2043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3466144234","display_name":null,"funder_award_id":"61976185","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7732546948","display_name":null,"funder_award_id":"226-2023-00048","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8513333314","display_name":null,"funder_award_id":"2021ZD01","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2412782625","https://openalex.org/W2526050071","https://openalex.org/W2565639579","https://openalex.org/W2593116425","https://openalex.org/W2747329762","https://openalex.org/W2931433835","https://openalex.org/W2963351448","https://openalex.org/W2964109005","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3021321555","https://openalex.org/W3092944026","https://openalex.org/W3093287838","https://openalex.org/W3096609285","https://openalex.org/W3108367559","https://openalex.org/W3117097536","https://openalex.org/W3118120400","https://openalex.org/W3118366136","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3160550216","https://openalex.org/W3170088426","https://openalex.org/W3170264469","https://openalex.org/W3170630188","https://openalex.org/W3170841864","https://openalex.org/W3171516518","https://openalex.org/W3175335326","https://openalex.org/W3175514052","https://openalex.org/W3211993051","https://openalex.org/W3212022073","https://openalex.org/W3214328324","https://openalex.org/W3214586131","https://openalex.org/W4205474609","https://openalex.org/W4214759957","https://openalex.org/W4225495512","https://openalex.org/W4226024706","https://openalex.org/W4226206782","https://openalex.org/W4303449836","https://openalex.org/W4313123347","https://openalex.org/W4382657968","https://openalex.org/W4386065959","https://openalex.org/W4386076516","https://openalex.org/W4390874575","https://openalex.org/W4403386295","https://openalex.org/W6922057760"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519","https://openalex.org/W2801048620"],"abstract_inverted_index":{"Audio-visual":[0],"video":[1,45,102],"segmentation":[2,79],"(AVVS)":[3],"aims":[4],"to":[5,21,83,155],"generate":[6],"pixel-level":[7],"maps":[8,18],"of":[9,58],"sound-producing":[10],"objects":[11],"within":[12],"image":[13],"frames":[14],"and":[15,28,48,61,63,70,101,108],"ensure":[16],"the":[17,22,54,74,141,151,156],"faithfully":[19],"adheres":[20,154],"given":[23],"audio,":[24],"such":[25],"as":[26],"identifying":[27],"segmenting":[29],"a":[30,34,94,121,132,168],"singing":[31],"person":[32],"in":[33,78,131],"video.":[35],"However,":[36],"existing":[37],"methods":[38],"exhibit":[39],"two":[40,177],"limitations:":[41],"1)":[42],"they":[43,65],"address":[44],"temporal":[46,107],"features":[47,51,103],"audio-visual":[49,128],"interactive":[50],"separately,":[52],"disregarding":[53],"inherent":[55],"spatial-temporal":[56],"dependence":[57],"combined":[59,113],"audio":[60,68,86,100],"video,":[62],"2)":[64],"inadequately":[66],"introduce":[67,137],"constraints":[69],"object-level":[71,148],"information":[72],"during":[73,140],"decoding":[75,142],"stage,":[76],"resulting":[77],"outcomes":[80],"that":[81,98],"fail":[82],"comply":[84],"with":[85,164],"directives.":[87],"To":[88,115],"tackle":[89],"these":[90],"issues,":[91],"we":[92,119,136],"propose":[93],"decoupled":[95],"audio-video":[96],"transformer":[97],"combines":[99],"from":[104],"their":[105,112],"respective":[106],"spatial":[109],"dimensions,":[110],"capturing":[111,127],"dependence.":[114],"optimize":[116],"memory":[117],"consumption,":[118],"design":[120],"block,":[122],"which,":[123],"when":[124],"stacked,":[125],"enables":[126],"fine-grained":[129],"combinatorial-dependence":[130],"memory-efficient":[133],"manner.":[134],"Additionally,":[135],"audio-constrained":[138],"queries":[139,145],"phase.":[143],"These":[144],"contain":[146],"rich":[147],"information,":[149],"ensuring":[150],"decoded":[152],"mask":[153],"sounds.":[157],"Experimental":[158],"results":[159],"confirm":[160],"our":[161,165],"approach's":[162],"effectiveness,":[163],"framework":[166],"achieving":[167],"new":[169],"SOTA":[170],"performance":[171],"on":[172],"all":[173],"three":[174],"datasets":[175],"using":[176],"backbones.":[178],"The":[179],"code":[180],"is":[181],"available":[182],"at":[183],"https://github.com/aspirinone/CATR.github.io.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}