{"id":"https://openalex.org/W4415708394","doi":"https://doi.org/10.1109/icme59968.2025.11209953","title":"Vote & Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer","display_name":"Vote & Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708394","doi":"https://doi.org/10.1109/icme59968.2025.11209953"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5061781593","display_name":"Shuai Peng","orcid":"https://orcid.org/0000-0002-9828-806X"},"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":"Shuai Peng","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207941","display_name":"Di Fu","orcid":"https://orcid.org/0000-0002-5385-2982"},"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":"Di Fu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113407653","display_name":"Baole Wei","orcid":null},"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":"Baole Wei","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004474713","display_name":"Liangcai Gao","orcid":"https://orcid.org/0000-0001-9444-1568"},"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":"Liangcai Gao","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103175239","display_name":"Zhi Tang","orcid":"https://orcid.org/0000-0002-6021-8357"},"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":"Zhi Tang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.3009999990463257,"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":0.3009999990463257,"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/T11019","display_name":"Image Enhancement Techniques","score":0.1599999964237213,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.13899999856948853,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6100000143051147},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4677000045776367},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3517000079154968},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.3353999853134155},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.2842000126838684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508000135421753},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6100000143051147},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4424000084400177},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3517000079154968},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3483000099658966},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.25459998846054077},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W3094502228","https://openalex.org/W3126721948","https://openalex.org/W3216553632","https://openalex.org/W4214633470","https://openalex.org/W4312290555","https://openalex.org/W4312560592","https://openalex.org/W4312769131","https://openalex.org/W4312777209","https://openalex.org/W4312849330","https://openalex.org/W4312872526","https://openalex.org/W4312910119","https://openalex.org/W4312980231","https://openalex.org/W4313156423","https://openalex.org/W4319300012","https://openalex.org/W4386076562","https://openalex.org/W4390190626","https://openalex.org/W4390872092","https://openalex.org/W4394593136","https://openalex.org/W4402716428"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,48,67,73,85],"remarkable":[2],"success":[3],"of":[4,51,88,105,116],"Vision":[5],"Transformers":[6],"(ViTs)":[7],"in":[8,103,114,128],"various":[9],"visual":[10,78],"tasks,":[11],"they":[12],"are":[13,70],"often":[14],"hindered":[15],"by":[16,53],"substantial":[17],"computational":[18,49],"cost.":[19],"In":[20],"this":[21],"work,":[22],"we":[23],"introduce":[24],"Vote&Mix":[25],"(VoMix),":[26],"a":[27,60,100,111,124],"plug-and-play":[28],"and":[29,93,110],"parameter-free":[30],"token":[31,62],"reduction":[32],"method,":[33],"which":[34],"can":[35],"be":[36],"readily":[37],"applied":[38],"to":[39],"off-the-shelf":[40],"ViT":[41],"models":[42],"without":[43],"any":[44,96],"training.":[45],"VoMix":[46,82,98],"tackles":[47],"redundancy":[50],"ViTs":[52,89],"identifying":[54],"tokens":[55,69],"with":[56,123],"high":[57],"homogeneity":[58],"through":[59],"layer-wise":[61],"similarity":[63],"voting":[64],"mechanism.":[65],"Subsequently,":[66],"selected":[68],"mixed":[71],"into":[72],"retained":[74],"set,":[75],"thereby":[76],"preserving":[77],"information.":[79],"Experiments":[80],"demonstrate":[81],"significantly":[83],"improves":[84],"speed-accuracy":[86],"tradeoff":[87],"on":[90,108,119],"both":[91],"images":[92],"videos.":[94],"Without":[95],"training,":[97],"achieves":[99],"2\u00d7":[101],"increase":[102,113],"throughput":[104,115],"existing":[106,117],"ViT-H":[107],"ImageNet-1K":[109],"2.4\u00d7":[112],"ViT-L":[118],"Kinetics-400":[120],"video":[121],"dataset,":[122],"mere":[125],"0.3%":[126],"drop":[127],"top-1":[129],"accuracy.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}