{"id":"https://openalex.org/W4403791883","doi":"https://doi.org/10.1145/3664647.3681709","title":"Group Vision Transformer","display_name":"Group Vision Transformer","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791883","doi":"https://doi.org/10.1145/3664647.3681709"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5016417316","display_name":"Yaopeng Peng","orcid":"https://orcid.org/0000-0001-6499-7354"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yaopeng Peng","raw_affiliation_strings":["The University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"The University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018836634","display_name":"Milan Sonka","orcid":"https://orcid.org/0000-0002-9613-9968"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milan Sonka","raw_affiliation_strings":["The University of Iowa, Iowa City, IA, USA"],"affiliations":[{"raw_affiliation_string":"The University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060901632","display_name":"Danny Z. Chen","orcid":"https://orcid.org/0000-0001-6565-2884"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danny Z. Chen","raw_affiliation_strings":["The University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"The University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016417316"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16968851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2623","last_page":"2631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9800999760627747,"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":0.9800999760627747,"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":0.9775999784469604,"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"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9575999975204468,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/computer-science","display_name":"Computer science","score":0.5341626405715942},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42869651317596436},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3764567971229553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3390727639198303},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15358346700668335},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14484214782714844},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09958547353744507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5341626405715942},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42869651317596436},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3764567971229553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3390727639198303},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15358346700668335},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14484214782714844},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09958547353744507}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":26,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2737258237","https://openalex.org/W2884822772","https://openalex.org/W2909680570","https://openalex.org/W2963125010","https://openalex.org/W2989676862","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W2999905431","https://openalex.org/W3035682985","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3195830874","https://openalex.org/W4287022992","https://openalex.org/W4312443924","https://openalex.org/W4313007769","https://openalex.org/W4386075524","https://openalex.org/W4386075553","https://openalex.org/W4386076539","https://openalex.org/W4388145401"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0,86],"Vision":[1,60,69,79],"Transformer":[2,61,70,99],"has":[3],"attained":[4],"remarkable":[5],"success":[6],"in":[7,23,58,164,208,213,217,230],"various":[8],"computer":[9],"vision":[10,167],"applications.":[11],"However,":[12],"the":[13,41,46,55,59,97,104,127,130,138,203],"large":[14,25],"computational":[15,51,122,156,241],"costs":[16],"and":[17,75,95,121,155,183,192,195,225,228,240],"complex":[18],"design":[19],"limit":[20],"its":[21],"ability":[22],"handling":[24],"feature":[26],"maps.":[27],"Existing":[28],"research":[29],"predominantly":[30],"focuses":[31],"on":[32,145,153,178,187,198,220,232],"constraining":[33],"attention":[34,47,84,105],"to":[35,82,93],"small":[36],"local":[37],"regions,":[38],"which":[39],"reduces":[40],"number":[42],"of":[43,78,89,102,129,137,140,143],"tokens":[44],"attending":[45],"computation":[48],"while":[49],"overlooking":[50],"demands":[52],"caused":[53],"by":[54,206],"feed-forward":[56],"layer":[57],"block.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"introduce":[67],"Group":[68],"(GVT),":[71],"a":[72],"relatively":[73],"simple":[74],"efficient":[76],"variant":[77],"Transformer,":[80],"aiming":[81],"improve":[83],"computation.":[85],"core":[87],"idea":[88],"our":[90,171],"model":[91,146,173,205,238],"is":[92,244],"divide":[94],"group":[96],"entire":[98],"layer,":[100],"instead":[101],"only":[103],"part,":[106],"into":[107],"multiple":[108],"independent":[109],"branches.":[110],"This":[111],"approach":[112],"offers":[113],"two":[114],"advantages:":[115],"(1)":[116],"It":[117],"helps":[118],"reduce":[119],"parameters":[120,154,239],"complexity;":[123],"(2)":[124],"it":[125],"enhances":[126],"diversity":[128],"learned":[131],"features.":[132],"We":[133],"conduct":[134],"comprehensive":[135],"analysis":[136],"impact":[139],"different":[141],"numbers":[142],"groups":[144],"performance,":[147],"as":[148,150],"well":[149],"their":[151],"influence":[152],"complexity.":[157,242],"Our":[158],"proposed":[159],"GVT":[160],"demonstrates":[161],"competitive":[162],"performances":[163],"several":[165],"common":[166],"tasks.":[168],"For":[169],"example,":[170],"GVT-Tiny":[172],"achieves":[174],"84.8%":[175],"top-1":[176,210],"accuracy":[177],"ImageNet-1K,":[179],"51.4%":[180],"box":[181,214],"mAP":[182,186,219],"45.2%":[184],"mask":[185,218],"MS":[188,221],"COCO":[189,222],"object":[190,223],"detection":[191,224],"instance":[193,226],"segmentation,":[194,201,227,235],"50.1%":[196],"mIoU":[197,231],"ADE20K":[199,233],"semantic":[200,234],"outperforming":[202],"CAFormer-S36":[204],"0.3%":[207],"ImageNet-1K":[209],"accuracy,":[211],"1.2%":[212,229],"mAP,":[215],"1.0%":[216],"with":[236],"similar":[237],"Code":[243],"accessible":[245],"at":[246],"https://github.com/yaoppeng/GVT.":[247]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}