{"id":"https://openalex.org/W4414359875","doi":"https://doi.org/10.24963/ijcai.2025/601","title":"MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion","display_name":"MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359875","doi":"https://doi.org/10.24963/ijcai.2025/601"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/601","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-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/A5100677195","display_name":"Wei Hua","orcid":"https://orcid.org/0000-0001-9124-4868"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hua","raw_affiliation_strings":["China Nanhu Academy of Electronics and Information Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Nanhu Academy of Electronics and Information Technology","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030207073","display_name":"Chenlin Zhou","orcid":"https://orcid.org/0000-0001-6510-1417"},"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":"Chenlin Zhou","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018341980","display_name":"Jibin Wu","orcid":"https://orcid.org/0000-0003-0135-4188"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jibin Wu","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066851412","display_name":"Yansong Chua","orcid":"https://orcid.org/0000-0002-3133-843X"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Chua","raw_affiliation_strings":["China Nanhu Academy of Electronics and Information Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Nanhu Academy of Electronics and Information Technology","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005217555","display_name":"Yangyang Shu","orcid":"https://orcid.org/0000-0001-6319-6037"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yangyang Shu","raw_affiliation_strings":["The University of New South Wales"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5352,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70875883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5399","last_page":"5407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6694999933242798},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6306999921798706},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.5162000060081482},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4246000051498413},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.384799987077713},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3799000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718500018119812},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6694999933242798},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5776000022888184},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.5162000060081482},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35269999504089355},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/601","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,110,130],"combination":[1],"of":[2,97],"Spiking":[3],"Neural":[4],"Networks":[5],"(SNNs)":[6],"with":[7,50],"Vision":[8],"Transformer":[9,84],"architectures":[10,54],"has":[11],"attracted":[12],"significant":[13],"attention":[14,91,99],"due":[15],"to":[16,93],"the":[17,52,95],"great":[18],"potential":[19],"for":[20],"energy-efficient":[21],"and":[22,35,78],"high-performance":[23],"computing":[24],"paradigms.":[25],"However,":[26],"a":[27,61,81,124],"substantial":[28],"performance":[29],"gap":[30],"still":[31],"exists":[32],"between":[33],"SNN-based":[34,119],"ANN-based":[36],"transformer":[37],"architectures.":[38,129],"While":[39],"existing":[40,118],"methods":[41,58],"propose":[42,79],"spiking":[43,90,98],"self-attention":[44],"mechanisms":[45],"that":[46,114],"are":[47,132],"successfully":[48],"combined":[49],"SNNs,":[51],"overall":[53],"proposed":[55],"by":[56],"these":[57],"suffer":[59],"from":[60,67],"bottleneck":[62],"in":[63],"effectively":[64],"extracting":[65],"features":[66],"different":[68],"image":[69],"scales.":[70],"In":[71],"this":[72,76],"paper,":[73],"we":[74],"address":[75],"issue":[77],"MSVIT,":[80],"novel":[82],"spike-driven":[83],"architecture,":[85],"which":[86],"firstly":[87],"uses":[88],"multi-scale":[89],"(MSSA)":[92],"enrich":[94],"capability":[96],"blocks.":[100],"We":[101],"validate":[102],"our":[103,115],"approach":[104],"across":[105],"various":[106],"main":[107],"data":[108],"sets.":[109],"experimental":[111],"results":[112],"indicate":[113],"MSVIT":[116],"outperforms":[117],"models,":[120],"positioning":[121],"itself":[122],"as":[123],"state-of-the-art":[125],"solution":[126],"among":[127],"NN-transformer":[128],"codes":[131],"available":[133],"at":[134],"https://github.com/Nanhu-AI-Lab/MSViT.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}