{"id":"https://openalex.org/W4414587896","doi":"https://doi.org/10.48550/arxiv.2505.19938","title":"Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning","display_name":"Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4414587896","doi":"https://doi.org/10.48550/arxiv.2505.19938"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.19938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.19938","pdf_url":"https://arxiv.org/pdf/2505.19938","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.19938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100739626","display_name":"Wenrui Li","orcid":"https://orcid.org/0000-0003-0635-7919"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Wenrui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033038967","display_name":"Penghong Wang","orcid":"https://orcid.org/0000-0002-5401-5676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Penghong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022103187","display_name":"Xingtao Wang","orcid":"https://orcid.org/0000-0002-5763-2493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xingtao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Wangmeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Xiaopeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Yonghong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100739626"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.993399977684021,"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"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.993399977684021,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9882000088691711,"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":0.9842000007629395,"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/robustness","display_name":"Robustness (evolution)","score":0.5924000144004822},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4959999918937683},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49059998989105225},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4458000063896179},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.3882000148296356},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.36309999227523804},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.3546999990940094},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.3402999937534332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6459000110626221},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5924000144004822},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49869999289512634},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49059998989105225},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.19938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.19938","pdf_url":"https://arxiv.org/pdf/2505.19938","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.19938","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.19938","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.19938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.19938","pdf_url":"https://arxiv.org/pdf/2505.19938","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1492706270","display_name":null,"funder_award_id":"02402","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5410805085","display_name":null,"funder_award_id":"62402138","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7374398270","display_name":null,"funder_award_id":"HIT.DZJJ.2024025","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8685418503","display_name":null,"funder_award_id":"624B2049","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414587896.pdf","grobid_xml":"https://content.openalex.org/works/W4414587896.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-visual":[0],"zero-shot":[1],"learning":[2,57],"(ZSL)":[3],"has":[4],"been":[5],"extensively":[6],"researched":[7],"for":[8],"its":[9],"capability":[10],"to":[11,61,73,83,104],"classify":[12],"video":[13],"data":[14],"from":[15],"unseen":[16],"classes":[17],"during":[18],"training.":[19],"Nevertheless,":[20],"current":[21],"methodologies":[22],"often":[23],"struggle":[24],"with":[25],"background":[26,94],"scene":[27,95],"biases":[28],"and":[29,49,66,92,118,134,158,164,169],"inadequate":[30],"motion":[31,52,88,107,119,133,157],"detail.":[32],"This":[33],"paper":[34],"proposes":[35],"a":[36,100],"novel":[37],"dual-stream":[38],"Multi-Timescale":[39],"Motion-Decoupled":[40],"Spiking":[41],"Transformer":[42],"(MDST++),":[43],"which":[44],"decouples":[45],"contextual":[46,63,135],"semantic":[47,64,136],"information":[48,65,89,160],"sparse":[50],"dynamic":[51],"information.":[53,108,137],"The":[54],"recurrent":[55],"joint":[56,68],"unit":[58],"is":[59],"proposed":[60],"extract":[62],"capture":[67],"knowledge":[69],"across":[70],"various":[71],"modalities":[72],"understand":[74],"the":[75,111,124,141],"environment":[76],"of":[77,113,126,143],"actions.":[78],"By":[79],"converting":[80],"RGB":[81],"images":[82],"events,":[84],"our":[85],"method":[86],"captures":[87],"more":[90],"accurately":[91],"mitigates":[93],"biases.":[96],"Moreover,":[97],"we":[98,121],"introduce":[99],"discrepancy":[101],"analysis":[102],"block":[103],"model":[105],"audio":[106],"To":[109],"enhance":[110],"robustness":[112],"SNNs":[114],"in":[115],"extracting":[116],"temporal":[117],"cues,":[120],"dynamically":[122],"adjust":[123],"threshold":[125],"Leaky":[127],"Integrate-and-Fire":[128],"neurons":[129],"based":[130],"on":[131,152],"global":[132],"Our":[138],"experiments":[139],"validate":[140],"effectiveness":[142],"MDST++,":[144],"demonstrating":[145],"their":[146],"consistent":[147],"superiority":[148],"over":[149],"state-of-the-art":[150],"methods":[151],"mainstream":[153],"benchmarks.":[154],"Additionally,":[155],"incorporating":[156],"multi-timescale":[159],"significantly":[161],"improves":[162],"HM":[163],"ZSL":[165],"accuracy":[166],"by":[167],"26.2\\%":[168],"39.9\\%.":[170]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}