{"id":"https://openalex.org/W4385486227","doi":"https://doi.org/10.1109/tcsvt.2023.3301176","title":"Voxel-Based Multi-Scale Transformer Network for Event Stream Processing","display_name":"Voxel-Based Multi-Scale Transformer Network for Event Stream Processing","publication_year":2023,"publication_date":"2023-08-02","ids":{"openalex":"https://openalex.org/W4385486227","doi":"https://doi.org/10.1109/tcsvt.2023.3301176"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3301176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3301176","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","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/A5036594305","display_name":"Daikun Liu","orcid":"https://orcid.org/0000-0001-6344-2517"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Daikun Liu","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506354","display_name":"Teng Wang","orcid":"https://orcid.org/0000-0002-1802-0435"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Wang","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Automation, and the Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, and the Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036594305"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":1.4337,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81688831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"34","issue":"4","first_page":"2112","last_page":"2124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9929999709129333,"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/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular 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/computer-science","display_name":"Computer science","score":0.8360508680343628},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.7317476272583008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6344674825668335},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47076988220214844},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4257073402404785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41393908858299255},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38217049837112427},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16185173392295837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360508680343628},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.7317476272583008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6344674825668335},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47076988220214844},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4257073402404785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41393908858299255},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38217049837112427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16185173392295837}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3301176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3301176","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5686492328","display_name":null,"funder_award_id":"62273093","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/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1967377294","https://openalex.org/W2016574277","https://openalex.org/W2020096355","https://openalex.org/W2469278928","https://openalex.org/W2513853720","https://openalex.org/W2563042993","https://openalex.org/W2565755350","https://openalex.org/W2619510810","https://openalex.org/W2745933219","https://openalex.org/W2766013930","https://openalex.org/W2783185291","https://openalex.org/W2788172931","https://openalex.org/W2796402180","https://openalex.org/W2806043570","https://openalex.org/W2904275768","https://openalex.org/W2922107638","https://openalex.org/W2955504279","https://openalex.org/W2962804204","https://openalex.org/W2963127485","https://openalex.org/W2963402313","https://openalex.org/W2963420686","https://openalex.org/W2963510238","https://openalex.org/W2979969178","https://openalex.org/W3010268791","https://openalex.org/W3035137671","https://openalex.org/W3087591564","https://openalex.org/W3092083701","https://openalex.org/W3097883549","https://openalex.org/W3102178346","https://openalex.org/W3106188738","https://openalex.org/W3111548021","https://openalex.org/W3122048951","https://openalex.org/W3153096694","https://openalex.org/W3155332028","https://openalex.org/W3163388905","https://openalex.org/W3178904088","https://openalex.org/W3202138477","https://openalex.org/W3202353648","https://openalex.org/W4205262662","https://openalex.org/W4214588794","https://openalex.org/W4214755140","https://openalex.org/W4214777292","https://openalex.org/W4214881917","https://openalex.org/W4221138238","https://openalex.org/W4285187202","https://openalex.org/W4292787316","https://openalex.org/W4293731929","https://openalex.org/W4295909205","https://openalex.org/W4308235769","https://openalex.org/W4312281374","https://openalex.org/W4312501532","https://openalex.org/W4313153644","https://openalex.org/W4321512628","https://openalex.org/W4379382445","https://openalex.org/W4382465451","https://openalex.org/W4401806108","https://openalex.org/W6739778489","https://openalex.org/W6798292908","https://openalex.org/W6809816361","https://openalex.org/W6850943842"],"related_works":["https://openalex.org/W3027020613","https://openalex.org/W2016533837","https://openalex.org/W3167885074","https://openalex.org/W2892386716","https://openalex.org/W4306164210","https://openalex.org/W1998563493","https://openalex.org/W4313316311","https://openalex.org/W4362608745","https://openalex.org/W2383143032","https://openalex.org/W2148204638"],"abstract_inverted_index":{"Event":[0],"cameras":[1,12],"are":[2,8],"bio-inspired":[3],"dynamic":[4,20],"vision":[5,28],"sensors":[6],"that":[7,106,134,195],"superior":[9],"to":[10,88,112,141,147,161],"frame-based":[11],"in":[13,26,32,50,116,172,208],"terms":[14],"of":[15,41,180],"low":[16,44,202],"power":[17],"consumption,":[18],"high":[19,23],"range,":[21],"and":[22,56,76,158,205,218],"temporal":[24],"resolution":[25],"computer":[27],"tasks.":[29],"Recent":[30],"advances":[31,198],"voxel-based":[33,83],"representation":[34,65],"learning":[35],"have":[36],"successfully":[37],"exploited":[38],"the":[39,102,150,178,184],"sparsity":[40],"events":[42,95],"with":[43,128,154,201],"computational":[45,156,206],"complexity,":[46],"but":[47],"face":[48],"challenges":[49],"extracting":[51],"spatio-temporal":[52,114],"features":[53,115,153,165,171],"within":[54,96,138],"voxels":[55,97],"representative":[57],"global":[58,164],"dependencies":[59],"between":[60,74],"voxels,":[61],"thus":[62],"limiting":[63],"their":[64],"power.":[66],"In":[67],"this":[68],"work,":[69],"towards":[70],"a":[71,81,121,129,173],"better":[72],"trade-off":[73],"accuracy":[75,200],"computation":[77],"overhead,":[78],"we":[79,169],"propose":[80],"novel":[82,122],"multi-scale":[84,123,130],"transformer":[85],"network":[86,185],"(VMST-Net)":[87],"process":[89],"event":[90],"streams.":[91],"Specifically,":[92],"VMST-Net":[93,119],"projects":[94],"into":[98],"multi-channel":[99],"frames":[100],"along":[101],"time":[103],"axis,":[104],"such":[105],"2D":[107],"convolutions":[108],"could":[109],"be":[110],"leveraged":[111],"encode":[113],"voxels.":[117],"Then,":[118],"utilizes":[120],"multi-head":[124],"self-attention":[125],"(MSMHSA)":[126],"mechanism":[127],"fusion":[131],"(MSF)":[132],"module":[133],"allows":[135],"different":[136,143],"heads":[137],"each":[139],"layer":[140],"attend":[142],"scale":[144],"3D":[145,181],"neighborhoods":[146,182],"adaptively":[148],"aggregate":[149,170],"coarse-to-fine":[151],"voxel":[152],"little":[155],"costs":[157],"parameters.":[159],"Moreover,":[160],"model":[162,197,203],"effective":[163],"while":[166],"saving":[167],"computations,":[168],"local-to-global":[174],"manner":[175],"by":[176],"enlarging":[177],"coverage":[179],"as":[183],"gets":[186],"deeper.":[187],"Extensive":[188],"experimental":[189],"results":[190],"on":[191],"benchmark":[192],"datasets":[193],"demonstrate":[194],"our":[196],"state-of-the-art":[199],"complexity":[204,207],"all":[209],"three":[210],"visual":[211],"tasks,":[212],"including":[213],"object":[214],"classification,":[215],"action":[216],"recognition,":[217],"human":[219],"pose":[220],"estimation.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}