{"id":"https://openalex.org/W4396528950","doi":"https://doi.org/10.1109/tmm.2024.3394682","title":"Each Performs Its Functions: Task Decomposition and Feature Assignment for Audio-Visual Segmentation","display_name":"Each Performs Its Functions: Task Decomposition and Feature Assignment for Audio-Visual Segmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396528950","doi":"https://doi.org/10.1109/tmm.2024.3394682"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3394682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3394682","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5103085039","display_name":"Sen Xu","orcid":"https://orcid.org/0000-0002-4522-5460"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Xu","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4522-5460","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006854141","display_name":"Shikui Wei","orcid":"https://orcid.org/0000-0003-3803-9763"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikui Wei","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3803-9763","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005868375","display_name":"Tao Ruan","orcid":"https://orcid.org/0000-0002-6718-7223"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ruan","raw_affiliation_strings":["School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6718-7223","affiliations":[{"raw_affiliation_string":"School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080547175","display_name":"Lixin Liao","orcid":"https://orcid.org/0009-0004-6712-5729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lixin Liao","raw_affiliation_strings":["DaoAI Robotics Inc., Vancouver, BC, Canada"],"raw_orcid":"https://orcid.org/0009-0004-6712-5729","affiliations":[{"raw_affiliation_string":"DaoAI Robotics Inc., Vancouver, BC, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5631,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59644558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"26","issue":null,"first_page":"9489","last_page":"9498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9900000095367432,"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":0.8790282011032104},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7189157009124756},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5691453814506531},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.566330075263977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5270479321479797},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5123971104621887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48713061213493347},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45755186676979065},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42201513051986694},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40368738770484924},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39803484082221985},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2123766839504242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8790282011032104},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7189157009124756},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5691453814506531},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.566330075263977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5270479321479797},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5123971104621887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48713061213493347},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45755186676979065},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42201513051986694},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40368738770484924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39803484082221985},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2123766839504242},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3394682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3394682","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3467075038","display_name":null,"funder_award_id":"52202486","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G361765533","display_name":null,"funder_award_id":"2018AAA0102100","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5655896502","display_name":null,"funder_award_id":"62120106009","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/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2250539671","https://openalex.org/W2526050071","https://openalex.org/W2560023338","https://openalex.org/W2593116425","https://openalex.org/W2605127024","https://openalex.org/W2619383789","https://openalex.org/W2619697695","https://openalex.org/W2795437830","https://openalex.org/W2908510526","https://openalex.org/W2945161979","https://openalex.org/W2962699416","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2967957126","https://openalex.org/W2982619606","https://openalex.org/W2989980422","https://openalex.org/W3007589762","https://openalex.org/W3015371781","https://openalex.org/W3021321555","https://openalex.org/W3035358681","https://openalex.org/W3035749845","https://openalex.org/W3048048346","https://openalex.org/W3108367559","https://openalex.org/W3116298410","https://openalex.org/W3153167542","https://openalex.org/W3154852953","https://openalex.org/W3170088426","https://openalex.org/W3170630188","https://openalex.org/W3171638247","https://openalex.org/W3173382920","https://openalex.org/W3175515048","https://openalex.org/W3176232375","https://openalex.org/W3182657421","https://openalex.org/W3187664142","https://openalex.org/W3188558905","https://openalex.org/W3196056489","https://openalex.org/W3214311327","https://openalex.org/W3216551675","https://openalex.org/W4206517532","https://openalex.org/W4210416950","https://openalex.org/W4211154280","https://openalex.org/W4214681287","https://openalex.org/W4214759869","https://openalex.org/W4225986494","https://openalex.org/W4284898017","https://openalex.org/W4312356258","https://openalex.org/W4312707458","https://openalex.org/W4312711418","https://openalex.org/W4312886874","https://openalex.org/W4312999114","https://openalex.org/W4313123347","https://openalex.org/W6636510571","https://openalex.org/W6729831399","https://openalex.org/W6757817989","https://openalex.org/W6766904570","https://openalex.org/W6791353385"],"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/W1997170567"],"abstract_inverted_index":{"Audio-visual":[0],"segmentation":[1,95,154],"(AVS)":[2],"aims":[3,102],"to":[4,30,49,103,129,142,152,163],"segment":[5,36],"the":[6,13,16,40,105,114,131,159,190],"object":[7],"instances":[8],"that":[9,172],"produce":[10],"sound":[11,108],"at":[12],"time":[14],"of":[15,149],"video":[17],"frames.":[18],"Existing":[19],"related":[20,176],"solutions":[21],"focus":[22],"on":[23,75,120,169,189],"designing":[24],"cross-modal":[25,139],"interaction":[26,140],"mechanisms,":[27],"which":[28,73],"try":[29],"learn":[31,104],"audio-visual":[32,209],"correlations":[33],"and":[34,47,78,94,109,112,186],"simultaneously":[35],"objects.":[37],"Despite":[38],"effectiveness,":[39],"close-coupling":[41],"network":[42],"structures":[43],"become":[44],"increasingly":[45],"complex":[46],"hard":[48],"analyze.":[50],"To":[51],"address":[52],"these":[53],"problems,":[54],"we":[55,124,157],"propose":[56,158],"a":[57,180,205],"simple":[58],"but":[59],"effective":[60],"method,":[61],"\u2018Each":[62],"<underline":[63,66,69],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[64,67,70],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">P</u>erforms":[65],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">I</u>ts":[68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">F</u>unctions":[71],"(PIF),\u2019":[72],"focuses":[74,119],"task":[76],"decomposition":[77],"feature":[79],"assignment.":[80],"Inspired":[81],"by":[82,179,195],"human":[83],"sensory":[84],"experiences,":[85],"PIF":[86],"decouples":[87],"AVS":[88],"into":[89],"two":[90,98],"subtasks,":[91],"correlation":[92],"learning,":[93],"refinement,":[96],"via":[97],"branches.":[99],"Correlation":[100],"learning":[101],"correspondence":[106],"between":[107],"visible":[110],"individuals":[111],"provide":[113],"positional":[115],"prior.":[116],"Segmentation":[117],"refinement":[118],"fine":[121],"segmentation.":[122,210],"Then":[123],"assign":[125],"different":[126],"level":[127],"features":[128,137,151],"perform":[130],"appropriate":[132],"duties,":[133],"i.e.,":[134],"using":[135,146],"deep":[136],"for":[138,208],"due":[141],"their":[143],"semantic":[144],"advantages;":[145],"rich":[147],"textures":[148],"shallow":[150],"improve":[153],"results.":[155],"Moreover,":[156],"recurrent":[160],"collaboration":[161],"block":[162],"enhance":[164],"interbranch":[165],"communication.":[166],"Experimental":[167],"results":[168],"AVSBench":[170],"show":[171],"our":[173,200],"method":[174],"outperforms":[175],"state-of-the-art":[177],"methods":[178],"large":[181],"margin":[182],"(e.g.,":[183],"+6.0%":[184],"mIoU":[185],"+7.6%":[187],"F-score":[188],"Multi-Source":[191],"subset).":[192],"In":[193],"addition,":[194],"purposely":[196],"boosting":[197],"subtasks'":[198],"performance,":[199],"approach":[201],"can":[202],"serve":[203],"as":[204],"strong":[206],"baseline":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2024-05-01T00:00:00"}