{"id":"https://openalex.org/W4407638717","doi":"https://doi.org/10.1109/tmm.2025.3542995","title":"AVS-Mamba: Exploring Temporal and Multi-Modal Mamba for Audio-Visual Segmentation","display_name":"AVS-Mamba: Exploring Temporal and Multi-Modal Mamba for Audio-Visual Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407638717","doi":"https://doi.org/10.1109/tmm.2025.3542995"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3542995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3542995","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":null,"display_name":"Sitong Gong","orcid":"https://orcid.org/0009-0001-8661-1093"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitong Gong","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0001-8661-1093","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048521072","display_name":"Yunzhi Zhuge","orcid":"https://orcid.org/0000-0002-4288-4516"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhi Zhuge","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-4288-4516","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087681764","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0003-4648-4437"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-4648-4437","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398548","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0002-1911-2526"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-1911-2526","affiliations":[{"raw_affiliation_string":"School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451855","display_name":"Pingping Zhang","orcid":"https://orcid.org/0000-0003-1206-1444"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingping Zhang","raw_affiliation_strings":["School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1206-1444","affiliations":[{"raw_affiliation_string":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318892","display_name":"Lijun Wang","orcid":"https://orcid.org/0000-0003-2538-8358"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wang","raw_affiliation_strings":["School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-2538-8358","affiliations":[{"raw_affiliation_string":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":9.9268,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98524882,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"5413","last_page":"5425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9954000115394592,"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":0.9354000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7677687406539917},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.46580132842063904},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.45089036226272583},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18349072337150574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677687406539917},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.46580132842063904},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.45089036226272583},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18349072337150574},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3542995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3542995","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/G1358076444","display_name":null,"funder_award_id":"DUT24YG119","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3080167161","display_name":null,"funder_award_id":"62206039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4319081443","display_name":null,"funder_award_id":"DUT24RC(3)025","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4585823974","display_name":null,"funder_award_id":"62441231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6387696347","display_name":null,"funder_award_id":"62406053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6732593181","display_name":null,"funder_award_id":"62106149","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2105934661","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W3015785290","https://openalex.org/W3138516171","https://openalex.org/W3175515048","https://openalex.org/W3214311327","https://openalex.org/W4211154280","https://openalex.org/W4221167476","https://openalex.org/W4291920479","https://openalex.org/W4312380001","https://openalex.org/W4367146821","https://openalex.org/W4379619455","https://openalex.org/W4385767885","https://openalex.org/W4386072368","https://openalex.org/W4386230985","https://openalex.org/W4387682108","https://openalex.org/W4387969495","https://openalex.org/W4389065381","https://openalex.org/W4390872864","https://openalex.org/W4391953443","https://openalex.org/W4393159092","https://openalex.org/W4393160420","https://openalex.org/W4394007483","https://openalex.org/W4396528950","https://openalex.org/W4398249074","https://openalex.org/W4399146361","https://openalex.org/W4399154429","https://openalex.org/W4399618753","https://openalex.org/W4400410003","https://openalex.org/W4400519485","https://openalex.org/W4402952320","https://openalex.org/W4403010118","https://openalex.org/W4403386295","https://openalex.org/W4403758862","https://openalex.org/W4403791582","https://openalex.org/W4403842425","https://openalex.org/W4403977303","https://openalex.org/W4403998622","https://openalex.org/W4405386924","https://openalex.org/W4406457474","https://openalex.org/W4409365576","https://openalex.org/W4409367296","https://openalex.org/W4410915127","https://openalex.org/W4411550739"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"The":[0],"essence":[1],"of":[2,25,106,114],"audio-visual":[3],"segmentation":[4],"(AVS)":[5],"lies":[6],"in":[7,37],"locating":[8],"and":[9,44,74,84,116,144,173],"delineating":[10],"sound-emitting":[11],"objects":[12],"within":[13],"a":[14,35,55],"video":[15,72,82],"stream.":[16],"While":[17],"Transformer-based":[18],"methods":[19],"have":[20],"shown":[21],"promise,":[22],"their":[23],"handling":[24],"long-range":[26],"dependencies":[27],"struggles":[28],"due":[29],"to":[30,60,134,154],"quadratic":[31],"computational":[32],"costs,":[33],"presenting":[34],"bottleneck":[36],"complex":[38,46],"scenarios.":[39],"To":[40,119],"overcome":[41],"this":[42],"limitation":[43],"facilitate":[45],"multi-modal":[47,121],"comprehension":[48],"with":[49],"linear":[50],"complexity,":[51],"we":[52,95,123,148],"introduce":[53],"AVS-Mamba,":[54],"selective":[56],"state":[57],"space":[58],"model":[59],"address":[61],"the":[62,97,104,112,125,130,150,171],"AVS":[63],"task.":[64],"Our":[65],"framework":[66],"incorporates":[67],"two":[68],"key":[69],"components":[70],"for":[71,80,88],"understanding":[73],"cross-modal":[75],"learning:":[76],"Temporal":[77,99],"Mamba":[78],"Block":[79,87,133],"sequential":[81],"processing":[83],"Vision-to-Audio":[85,131],"Fusion":[86,132],"advanced":[89],"audio-vision":[90],"integration.":[91],"Building":[92],"on":[93,170],"this,":[94],"develop":[96],"Multi-scale":[98],"Encoder,":[100],"aimed":[101],"at":[102],"enhancing":[103],"learning":[105],"visual":[107,136],"features":[108,137,140],"across":[109,141],"scales,":[110],"facilitating":[111],"perception":[113],"intra-":[115],"inter-frame":[117],"information.":[118],"perform":[120,155],"fusion,":[122],"propose":[124],"Modality":[126],"Aggregation":[127],"Decoder,":[128],"leveraging":[129],"integrate":[135],"into":[138],"audio":[139],"both":[142],"frame":[143],"temporal":[145],"levels.":[146],"Further,":[147],"adopt":[149],"Contextual":[151],"Integration":[152],"Pyramid":[153],"audio-to-vision":[156],"spatial-temporal":[157],"context":[158],"collaboration.":[159],"Through":[160],"these":[161],"innovative":[162],"contributions,":[163],"our":[164],"approach":[165],"achieves":[166],"new":[167],"state-of-the-art":[168],"results":[169],"AVSBench-object":[172],"AVSBench-semantic":[174],"datasets.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
