{"id":"https://openalex.org/W4387969040","doi":"https://doi.org/10.1145/3581783.3611759","title":"Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning","display_name":"Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969040","doi":"https://doi.org/10.1145/3581783.3611759"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046442204","display_name":"Wenrui Li","orcid":"https://orcid.org/0000-0002-2393-9016"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Li","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-2393-9016","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011715660","display_name":"Xi-Le Zhao","orcid":"https://orcid.org/0000-0002-6540-946X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi-Le Zhao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-6540-946X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079107646","display_name":"Zhengyu Ma","orcid":"https://orcid.org/0000-0003-0799-440X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyu Ma","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0799-440X","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022103187","display_name":"Xingtao Wang","orcid":"https://orcid.org/0000-0002-5763-2493"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingtao Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-5763-2493","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-9660-3636","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2978-5935","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3994","last_page":"4002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8350549936294556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6007363200187683},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4732799232006073},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4431800842285156},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4323854446411133},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38301390409469604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3365318775177002},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32086557149887085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350549936294556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007363200187683},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4732799232006073},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4431800842285156},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4323854446411133},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38301390409469604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3365318775177002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32086557149887085},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G124397460","display_name":null,"funder_award_id":"62236009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1774558579","display_name":null,"funder_award_id":"62206141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2354529456","display_name":null,"funder_award_id":"2021YFF0900500, 2020YFA0714001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3778334585","display_name":null,"funder_award_id":"12171072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4587952244","display_name":null,"funder_award_id":"62027804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5430980299","display_name":null,"funder_award_id":"U22B2035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5938326874","display_name":null,"funder_award_id":"U22B2035, 62272128, 62206141, 62236009, 62131005, 12171072, 61825101 and 62027804","funder_id":"https://openalex.org/F4320334062","funder_display_name":"National Natural Science Foundation of China-Liaoning Joint Fund"},{"id":"https://openalex.org/G6569862357","display_name":null,"funder_award_id":"62272128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6662223526","display_name":null,"funder_award_id":"61825101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6863986931","display_name":null,"funder_award_id":"62131005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7886604513","display_name":null,"funder_award_id":"2020YFA0714001","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/F4320334062","display_name":"National Natural Science Foundation of China-Liaoning Joint Fund","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W652269744","https://openalex.org/W1927052826","https://openalex.org/W2032480650","https://openalex.org/W2513853720","https://openalex.org/W2544224704","https://openalex.org/W2590382526","https://openalex.org/W2606429533","https://openalex.org/W2611632661","https://openalex.org/W2725671465","https://openalex.org/W2799215068","https://openalex.org/W2805693781","https://openalex.org/W2911959490","https://openalex.org/W2938463073","https://openalex.org/W2963283377","https://openalex.org/W2963499153","https://openalex.org/W2963545832","https://openalex.org/W2963960318","https://openalex.org/W2998281665","https://openalex.org/W2998708909","https://openalex.org/W3003262368","https://openalex.org/W3023742835","https://openalex.org/W3025520547","https://openalex.org/W3035254087","https://openalex.org/W3037195468","https://openalex.org/W3100093508","https://openalex.org/W3102040318","https://openalex.org/W3109728025","https://openalex.org/W3119136678","https://openalex.org/W3138521398","https://openalex.org/W3161217709","https://openalex.org/W3163815034","https://openalex.org/W3173623687","https://openalex.org/W3185605671","https://openalex.org/W3188165077","https://openalex.org/W4221141682","https://openalex.org/W4310895557","https://openalex.org/W4312653797","https://openalex.org/W4313126997","https://openalex.org/W4313129750","https://openalex.org/W4313477296","https://openalex.org/W6678470764","https://openalex.org/W6754392867","https://openalex.org/W6755494875","https://openalex.org/W6776074830","https://openalex.org/W6781630272","https://openalex.org/W6796939779"],"related_works":["https://openalex.org/W2372403409","https://openalex.org/W4242726756","https://openalex.org/W2961085424","https://openalex.org/W144832045","https://openalex.org/W1979328687","https://openalex.org/W4224009465","https://openalex.org/W2132049714","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W4386051551"],"abstract_inverted_index":{"Audio-visual":[0],"zero-shot":[1],"learning":[2],"(ZSL)":[3],"has":[4],"attracted":[5],"board":[6],"attention,":[7],"as":[8,49,225],"it":[9,234],"could":[10,90],"classify":[11],"video":[12,230],"data":[13,152],"from":[14],"classes":[15],"that":[16,221],"are":[17,28],"not":[18],"observed":[19],"during":[20],"training.":[21],"However,":[22],"most":[23],"of":[24,127,142,172,186,196,208,238],"the":[25,73,98,125,139,164,170,184,193,206,236],"existing":[26],"methods":[27,214],"restricted":[29],"to":[30,43,70,115,132,147,162],"background":[31,128],"scene":[32,129],"bias":[33],"and":[34,46,77,96,178,199,240,244],"fewer":[35],"motion":[36,47,81,121,166,179,198,222],"details":[37],"by":[38,60,104,242],"employing":[39],"a":[40,50,62,157,226],"single-stream":[41],"network":[42],"process":[44,148],"scenes":[45],"information":[48,76,94,122,223],"unified":[51],"entity.":[52],"In":[53],"this":[54,58],"paper,":[55],"we":[56,155,181,219],"address":[57],"challenge":[59],"proposing":[61],"novel":[63],"dual-stream":[64],"architecture":[65],"Motion-Decoupled":[66],"Spiking":[67,143],"Transformer":[68],"(MDFT)":[69],"explicitly":[71],"decouple":[72],"contextual":[74,92,200],"semantic":[75,93,201],"highly":[78,149],"sparsity":[79,150],"dynamic":[80,176],"information.":[82,202],"Specifically,":[83],"The":[84],"Recurrent":[85],"Joint":[86],"Learning":[87],"Unit":[88],"(RJLU)":[89],"extract":[91],"effectively":[95,119],"understand":[97],"environment":[99],"in":[100,174],"which":[101,210],"actions":[102],"occur":[103],"capturing":[105],"joint":[106],"knowledge":[107],"between":[108],"different":[109],"modalities.":[110],"By":[111],"converting":[112],"RGB":[113],"images":[114],"events,":[116],"our":[117],"approach":[118],"captures":[120],"while":[123],"mitigating":[124],"influence":[126],"biases,":[130],"leading":[131],"more":[133],"accurate":[134],"classification":[135],"results.":[136],"We":[137],"utilize":[138],"inherent":[140],"strengths":[141],"Neural":[144],"Networks":[145],"(SNNs)":[146],"event":[151],"efficiently.":[153],"Additionally,":[154],"introduce":[156],"Discrepancy":[158],"Analysis":[159],"Block":[160],"(DAB)":[161],"model":[163],"audio":[165],"features.":[167],"To":[168],"enhance":[169],"efficiency":[171],"SNNs":[173],"extracting":[175],"temporal":[177],"information,":[180],"dynamically":[182],"adjust":[183],"threshold":[185],"Leaky":[187],"Integrate-and-Fire":[188],"(LIF)":[189],"neurons":[190],"based":[191],"on":[192],"statistical":[194],"cues":[195],"global":[197],"Our":[203],"experiments":[204],"demonstrate":[205],"effectiveness":[207],"MDFT,":[209],"consistently":[211],"outperforms":[212],"state-of-the-art":[213],"across":[215],"mainstream":[216],"benchmarks.":[217],"Moreover,":[218],"find":[220],"serves":[224],"powerful":[227],"regularization":[228],"for":[229],"networks,":[231],"where":[232],"using":[233],"improves":[235],"accuracy":[237],"HM":[239],"ZSL":[241],"19.1%":[243],"38.4%,":[245],"respectively.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}