{"id":"https://openalex.org/W4410609966","doi":"https://doi.org/10.1145/3735975","title":"ALOHA: Adapting Local Spatio-Temporal Context to Enhance the Audio-Visual Semantic Segmentation","display_name":"ALOHA: Adapting Local Spatio-Temporal Context to Enhance the Audio-Visual Semantic Segmentation","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410609966","doi":"https://doi.org/10.1145/3735975"},"language":"en","primary_location":{"id":"doi:10.1145/3735975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735975","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5068136447","display_name":"Yanghao Zhou","orcid":"https://orcid.org/0009-0001-9401-4432"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang-Hao Zhou","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9401-4432","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087631670","display_name":"Heyan Huang","orcid":"https://orcid.org/0000-0002-0320-7520"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyan Huang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0320-7520","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063010018","display_name":"Cunhan Guo","orcid":"https://orcid.org/0000-0002-4546-3928"},"institutions":[{"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":"Cunhan Guo","raw_affiliation_strings":["School of Emergency Management Science and Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4546-3928","affiliations":[{"raw_affiliation_string":"School of Emergency Management Science and Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008273094","display_name":"Rong-Cheng Tu","orcid":"https://orcid.org/0000-0002-9567-159X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong-Cheng Tu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9567-159X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017155375","display_name":"Zeyu Xiao","orcid":"https://orcid.org/0000-0002-9171-9234"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zeyu Xiao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9171-9234","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039052372","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0001-8102-5346"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8102-5346","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017626590","display_name":"Xian-Ling Mao","orcid":"https://orcid.org/0000-0001-6795-2311"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Ling Mao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6795-2311","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8757,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84871578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"21","issue":"6","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9197046756744385},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6472792625427246},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.584825873374939},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.521033525466919},{"id":"https://openalex.org/keywords/aloha","display_name":"Aloha","score":0.46725910902023315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43576130270957947},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4160645306110382},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35981041193008423},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34304356575012207},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1315394937992096},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.07395419478416443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9197046756744385},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6472792625427246},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.584825873374939},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.521033525466919},{"id":"https://openalex.org/C2776398200","wikidata":"https://www.wikidata.org/wiki/Q508880","display_name":"Aloha","level":4,"score":0.46725910902023315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43576130270957947},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4160645306110382},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35981041193008423},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34304356575012207},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1315394937992096},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.07395419478416443},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3735975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735975","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2046753598","https://openalex.org/W2059809032","https://openalex.org/W2602856279","https://openalex.org/W2619697695","https://openalex.org/W2910628332","https://openalex.org/W2964109005","https://openalex.org/W3042628600","https://openalex.org/W3080686309","https://openalex.org/W3121523901","https://openalex.org/W3138516171","https://openalex.org/W3143835353","https://openalex.org/W3170088426","https://openalex.org/W3170264469","https://openalex.org/W3170630188","https://openalex.org/W3174906557","https://openalex.org/W3175335326","https://openalex.org/W3175515048","https://openalex.org/W3176232375","https://openalex.org/W3211993051","https://openalex.org/W3212022073","https://openalex.org/W3215899623","https://openalex.org/W4212817947","https://openalex.org/W4225495512","https://openalex.org/W4280534475","https://openalex.org/W4293088847","https://openalex.org/W4312380001","https://openalex.org/W4312420092","https://openalex.org/W4312443924","https://openalex.org/W4312815172","https://openalex.org/W4312820606","https://openalex.org/W4365799947","https://openalex.org/W4385767885","https://openalex.org/W4386072368","https://openalex.org/W4386083050","https://openalex.org/W4386113246","https://openalex.org/W4386790226","https://openalex.org/W4387197137","https://openalex.org/W4387968266","https://openalex.org/W4387969495","https://openalex.org/W4387969604","https://openalex.org/W4388191690","https://openalex.org/W4388192054","https://openalex.org/W4388585791","https://openalex.org/W4390873076","https://openalex.org/W4391884092","https://openalex.org/W4393855519","https://openalex.org/W4395470960","https://openalex.org/W4399146361","https://openalex.org/W4401074024","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W3096989448","https://openalex.org/W3107843154","https://openalex.org/W4366501345","https://openalex.org/W2105128603","https://openalex.org/W2373838515","https://openalex.org/W1996652759","https://openalex.org/W3090994729","https://openalex.org/W3192248241","https://openalex.org/W346937928","https://openalex.org/W2151483420"],"abstract_inverted_index":{"Audio-Visual":[0],"Semantic":[1],"Segmentation":[2],"(AVSS)":[3],"plays":[4],"a":[5,193,201],"crucial":[6],"role":[7],"in":[8,38,54,78,200],"pixel-level":[9,40],"multi-modal":[10],"perception":[11],"for":[12,66],"real-world":[13],"applications":[14],"such":[15],"as":[16],"robotic":[17],"navigation":[18],"and":[19,33,115,124,175,178,196,232],"autonomous":[20],"driving.":[21],"Existing":[22],"methods":[23],"typically":[24],"rely":[25],"on":[26,227,236],"global":[27],"spatio-temporal":[28,52,83,99,118,141],"modules":[29],"to":[30,58,68,101,113,164,183,186],"fuse":[31],"audio":[32],"visual":[34,246],"representations,":[35],"which":[36,94],"aids":[37],"generating":[39],"semantic":[41],"masks.":[42],"However,":[43],"these":[44],"approaches":[45],"often":[46],"overlook":[47],"the":[48,82,91,121,125,132,150,155,160,165,169,172,198,208,221,228,237],"importance":[49],"of":[50,210],"local":[51,117,147,151,161],"context":[53,100,119,148,162],"understanding":[55],"semantics,":[56,166],"leading":[57],"suboptimal":[59],"performance.":[60],"This":[61,204],"limitation":[62],"makes":[63],"it":[64,214],"difficult":[65],"models":[67],"accurately":[69],"distinguish":[70],"sound-emitting":[71],"objects":[72],"from":[73],"irrelevant":[74,176],"background":[75,177],"noise,":[76],"resulting":[77],"erroneous":[79],"segmentation":[80,180],"across":[81,140,244],"dimension.":[84],"To":[85],"address":[86],"this":[87],"issue,":[88],"we":[89],"propose":[90],"ALOHA":[92],"framework,":[93],"A":[95],"dapts":[96],"LO":[97],"cal":[98],"en":[102],"HA":[103],"nce":[104],"AVSS.":[105],"The":[106],"framework":[107,191,223],"introduces":[108],"two":[109],"key":[110],"components":[111],"designed":[112],"leverage":[114],"enhance":[116],"information:":[120],"LOHA":[122,133],"adapter":[123,134],"Selective":[126],"Context":[127],"Enhancement":[128],"(SCE)":[129],"module.":[130],"Specifically,":[131],"adaptively":[135],"captures":[136],"essential":[137],"modality":[138],"information":[139],"dimensions,":[142],"while":[143,240],"implicitly":[144],"learning":[145],"fine-grained":[146],"through":[149],"attention":[152],"mechanism.":[153],"Furthermore,":[154],"SCE":[156],"module":[157],"selectively":[158],"enhances":[159],"related":[163],"thereby":[167],"facilitating":[168],"distinction":[170],"between":[171],"sounding":[173],"object":[174],"improving":[179],"accuracy.":[181],"Moreover,":[182],"better":[184],"adapt":[185],"embodied":[187],"AI":[188],"systems,":[189],"our":[190],"utilizes":[192],"parameter-shared":[194],"encoder":[195],"applies":[197],"adapters":[199],"staged":[202],"manner.":[203],"design":[205],"significantly":[206],"reduces":[207],"number":[209],"trainable":[211],"parameters,":[212],"making":[213],"more":[215],"parameter-efficient.":[216],"Experimental":[217],"results":[218,235],"demonstrate":[219],"that":[220],"proposed":[222],"achieves":[224],"state-of-the-art":[225],"performance":[226],"AVSBench-Semantic":[229],"benchmark":[230],"dataset":[231],"shows":[233],"competitive":[234],"AVSBench-Object":[238],"benchmark,":[239],"exhibiting":[241],"broad":[242],"adaptability":[243],"different":[245],"backbone":[247],"networks.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
