{"id":"https://openalex.org/W4415708119","doi":"https://doi.org/10.1109/icme59968.2025.11209503","title":"Mutual Semantic Bridged Tri-Tower Fusion for Audio-Visual Segmentation","display_name":"Mutual Semantic Bridged Tri-Tower Fusion for Audio-Visual Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708119","doi":"https://doi.org/10.1109/icme59968.2025.11209503"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101309771","display_name":"Jingqi Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqi Qu","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033237183","display_name":"Hui Yu","orcid":"https://orcid.org/0000-0002-6927-4451"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078385469","display_name":"Dongchen Zhu","orcid":"https://orcid.org/0000-0002-1579-3942"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchen Zhu","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035418350","display_name":"Jiamao Li","orcid":"https://orcid.org/0000-0002-7478-4544"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamao Li","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34734502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5490999817848206,"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":0.5490999817848206,"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":0.3621000051498413,"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":0.014100000262260437,"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":0.692799985408783},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6344000101089478},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6111000180244446},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5333999991416931},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5042999982833862},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.436599999666214},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3937999904155731},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.36250001192092896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587000131607056},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.692799985408783},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6344000101089478},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3937999904155731},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35659998655319214},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2091744413","https://openalex.org/W2138913276","https://openalex.org/W2221370326","https://openalex.org/W2526050071","https://openalex.org/W2997747012","https://openalex.org/W3121523901","https://openalex.org/W3132252581","https://openalex.org/W3138516171","https://openalex.org/W3175515048","https://openalex.org/W4313123347","https://openalex.org/W4385767885","https://openalex.org/W4387969151","https://openalex.org/W4387969495","https://openalex.org/W4390872864","https://openalex.org/W4390873486","https://openalex.org/W4393159092","https://openalex.org/W4393159433","https://openalex.org/W4393160420","https://openalex.org/W4394625876","https://openalex.org/W4399146361","https://openalex.org/W4400070365","https://openalex.org/W4402703118","https://openalex.org/W4402716319","https://openalex.org/W4402727087","https://openalex.org/W4403791579","https://openalex.org/W4404531452","https://openalex.org/W4404970580","https://openalex.org/W4405717843"],"related_works":[],"abstract_inverted_index":{"Community":[0],"researchers":[1],"have":[2],"developed":[3],"various":[4],"advanced":[5],"audio-visual":[6],"segmentation":[7],"(AVS)":[8],"models":[9],"to":[10,89,119],"accurately":[11],"segment":[12],"sound-producing":[13,101,130],"objects.":[14,102],"However,":[15],"existing":[16],"methods":[17],"face":[18],"two":[19],"key":[20],"limitations:":[21],"1)":[22],"they":[23,41],"lack":[24],"effective":[25],"extraction":[26],"of":[27,65,100,129],"audio":[28,57,66,124],"semantics,":[29],"resulting":[30,61],"in":[31,62],"an":[32,117],"insufficiently":[33],"accurate":[34],"reference":[35],"guidance":[36],"for":[37],"segmentation,":[38],"and":[39,53,58,123],"2)":[40],"directly":[42],"align":[43],"cross-modal":[44,54],"information":[45],"without":[46],"adequately":[47],"considering":[48],"the":[49,106],"significant":[50],"semantic":[51,93,98],"gaps":[52],"noise":[55],"between":[56],"visual":[59],"features,":[60],"catastrophic":[63],"forgetting":[64],"information.":[67],"To":[68],"address":[69],"these":[70],"challenges,":[71],"we":[72,82,104],"propose":[73],"a":[74,84],"novel":[75],"Mutual":[76,85],"Semantic-Bridged":[77],"Tri-Tower":[78,107],"Fusion":[79,109],"Network.":[80],"First,":[81],"introduce":[83],"Semantic":[86,108],"Encoder":[87],"(MSE)":[88],"extract":[90],"global":[91],"mutual":[92,114],"embeddings,":[94],"enabling":[95],"more":[96],"robust":[97],"representations":[99],"Second,":[103],"design":[105],"(TTSF)":[110],"mechanism,":[111],"which":[112],"leverages":[113],"semantics":[115],"as":[116],"anchor":[118],"integrate":[120],"visual,":[121],"semantic,":[122],"information,":[125],"facilitating":[126],"deeper":[127],"interactions":[128],"object":[131],"features":[132],"across":[133],"modalities.":[134],"Experimental":[135],"results":[136],"demonstrate":[137],"that":[138],"our":[139],"approach":[140],"significantly":[141],"improves":[142],"performance":[143],"on":[144],"AVS":[145],"benchmarks.":[146]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}