{"id":"https://openalex.org/W7152741628","doi":"https://doi.org/10.1016/j.eswa.2026.132367","title":"A collaborative optimization framework for efficient long-sequence Audio-Visual understanding","display_name":"A collaborative optimization framework for efficient long-sequence Audio-Visual understanding","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152741628","doi":"https://doi.org/10.1016/j.eswa.2026.132367"},"language":"en","primary_location":{"id":"doi:10.1016/j.eswa.2026.132367","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132367","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.eswa.2026.132367","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101903007","display_name":"Yiqun Ma","orcid":"https://orcid.org/0009-0005-9567-7771"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Ma","raw_affiliation_strings":["School of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, 571126, China","Xi\u2019an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-9567-7771","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, 571126, China","institution_ids":[]},{"raw_affiliation_string":"Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Bai","orcid":"https://orcid.org/0009-0005-7801-5071"},"institutions":[{"id":"https://openalex.org/I4210145393","display_name":"Hainan Agricultural School","ror":"https://ror.org/04p8ncq94","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210145393"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Bai","raw_affiliation_strings":["Brisight (Hainan) Technology and Development CO., LTD., Haikou, 570216, China","School of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, 571126, China"],"raw_orcid":"https://orcid.org/0009-0005-7801-5071","affiliations":[{"raw_affiliation_string":"Brisight (Hainan) Technology and Development CO., LTD., Haikou, 570216, China","institution_ids":["https://openalex.org/I4210145393"]},{"raw_affiliation_string":"School of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, 571126, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133244524","display_name":"Xueren Li","orcid":"https://orcid.org/0009-0004-8828-3726"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Xueren Li","raw_affiliation_strings":["School of Engineering, RMIT University, PO Box 71, Bundoora, VIC, 3083, Australia","School of Safety Engineering, China University of Mining and Technology, Xuzhou, 221116, China"],"raw_orcid":"https://orcid.org/0009-0004-8828-3726","affiliations":[{"raw_affiliation_string":"School of Engineering, RMIT University, PO Box 71, Bundoora, VIC, 3083, Australia","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Safety Engineering, China University of Mining and Technology, Xuzhou, 221116, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133280877","display_name":"Bichen Shang","orcid":"https://orcid.org/0009-0000-2552-4159"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bichen Shang","raw_affiliation_strings":["School of Mechanical Engineering, Purdue University, West Lafayette, 47906, USA"],"raw_orcid":"https://orcid.org/0009-0000-2552-4159","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Purdue University, West Lafayette, 47906, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liwei Zhang","orcid":"https://orcid.org/0009-0009-9057-7519"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liwei Zhang","raw_affiliation_strings":["School of Mechanical Engineering, Purdue University, West Lafayette, 47906, USA"],"raw_orcid":"https://orcid.org/0009-0009-9057-7519","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Purdue University, West Lafayette, 47906, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059121720","display_name":"Weijie Sun","orcid":"https://orcid.org/0000-0003-3099-0298"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Weijie Sun","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2R3, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3099-0298","affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2R3, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059121720"],"corresponding_institution_ids":["https://openalex.org/I154425047","https://openalex.org/I4210145393"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":{"value":3220,"currency":"USD","value_usd":3220},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45456775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"323","issue":null,"first_page":"132367","last_page":"132367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6430000066757202,"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":0.6430000066757202,"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":0.26190000772476196,"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/T11439","display_name":"Video Analysis and Summarization","score":0.021400000900030136,"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/optimization-problem","display_name":"Optimization problem","score":0.26420000195503235},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.26080000400543213},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25450000166893005},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.24580000340938568},{"id":"https://openalex.org/keywords/optimization-algorithm","display_name":"Optimization algorithm","score":0.24289999902248383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657999992370605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37630000710487366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.24580000340938568},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.24289999902248383},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.23729999363422394}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.eswa.2026.132367","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132367","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.eswa.2026.132367","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132367","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2789394792","display_name":null,"funder_award_id":"Hnky2025ZD-17","funder_id":"https://openalex.org/F4320326677","funder_display_name":"Education Department of Hainan Province"},{"id":"https://openalex.org/G3906099836","display_name":null,"funder_award_id":"625RC794","funder_id":"https://openalex.org/F4320322866","funder_display_name":"Natural Science Foundation of Hainan Province"}],"funders":[{"id":"https://openalex.org/F4320322866","display_name":"Natural Science Foundation of Hainan Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326677","display_name":"Education Department of Hainan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W4226065230","https://openalex.org/W4309660795","https://openalex.org/W4402671518","https://openalex.org/W4403063511","https://openalex.org/W4404207656","https://openalex.org/W4404317174","https://openalex.org/W4404625362","https://openalex.org/W4404876617","https://openalex.org/W4405028135","https://openalex.org/W4406062792","https://openalex.org/W4406890739","https://openalex.org/W4409189413","https://openalex.org/W4409474127","https://openalex.org/W4410476912","https://openalex.org/W4410638721","https://openalex.org/W4411006449","https://openalex.org/W4411957315","https://openalex.org/W4411975722","https://openalex.org/W4413146548","https://openalex.org/W4413147704","https://openalex.org/W4413216838","https://openalex.org/W4413386499","https://openalex.org/W4413479711","https://openalex.org/W4413655311","https://openalex.org/W7133227460","https://openalex.org/W7133239857"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,7,34,47,73,81,113,118,121,129,185],"advancement":[2],"of":[3,37,76,120,131,181],"large":[4],"multimodal":[5,137],"models,":[6],"demand":[8],"for":[9,140],"processing":[10],"long-sequence":[11],"audio-visual":[12,53,150],"content":[13],"has":[14],"become":[15],"increasingly":[16],"urgent.":[17],"However,":[18],"mainstream":[19,149],"Transformer-based":[20],"models":[21],"face":[22],"significant":[23],"computational":[24],"and":[25,85,89,157,203],"memory":[26],"challenges":[27],"when":[28],"handling":[29],"long":[30],"sequences":[31],"due":[32],"to":[33,92,168],"quadratic":[35],"complexity":[36,119],"their":[38],"self-attention":[39],"mechanism.":[40],"This":[41],"issue":[42],"is":[43],"further":[44,100],"exacerbated":[45],"by":[46,107],"substantial":[48],"spatiotemporal":[49],"redundancy":[50],"prevalent":[51],"in":[52],"streams.":[54],"To":[55],"address":[56],"this":[57,125],"challenge,":[58],"we":[59],"propose":[60],"a":[61,198],"collaborative":[62],"optimization":[63],"framework":[64,99],"named":[65],"CG-ATP":[66,79,127,164],"(Cross-modal":[67],"Guided":[68],"Adaptive":[69],"Token":[70],"Pruning).":[71],"In":[72,124],"early":[74],"stages":[75],"feature":[77],"encoding,":[78],"leverages":[80],"inherent":[82],"semantic":[83],"alignment":[84],"complementarity":[86],"between":[87,201],"audio":[88],"visual":[90],"modalities":[91],"perform":[93],"bi-directionally":[94],"guided,":[95],"information-theoretic":[96],"pruning.":[97],"The":[98,160],"introduces":[101],"an":[102],"adaptive":[103],"gating":[104],"mechanism":[105],"inspired":[106],"Mixture-of-Experts":[108],"(MoE)":[109],"which":[110],"dynamically":[111],"adjusts":[112],"compression":[114,175,195],"rate":[115],"based":[116],"on":[117,147],"input":[122],"content.":[123],"way,":[126],"maximizes":[128],"removal":[130],"redundant":[132],"computations":[133],"while":[134,183],"precisely":[135],"preserving":[136],"information":[138],"crucial":[139],"downstream":[141],"tasks.":[142],"We":[143],"conducted":[144],"extensive":[145],"experiments":[146],"four":[148],"tasks:":[151],"event":[152],"localization,":[153],"video":[154],"parsing,":[155],"segmentation,":[156],"question":[158],"answering.":[159],"results":[161],"demonstrate":[162],"that":[163],"can":[165],"achieve":[166],"up":[167],"8.9x":[169],"inference":[170],"acceleration":[171],"at":[172],"extremely":[173],"high":[174],"rates":[176],"(e.g.,":[177],"retaining":[178],"only":[179],"10%":[180],"tokens)":[182],"keeping":[184],"performance":[186,202],"degradation":[187],"within":[188],"5%.":[189],"It":[190],"significantly":[191],"outperforms":[192],"existing":[193],"token":[194],"methods,":[196],"achieving":[197],"Pareto-optimal":[199],"trade-off":[200],"efficiency.":[204]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-04-10T00:00:00"}
