{"id":"https://openalex.org/W4379382445","doi":"https://doi.org/10.1109/tpami.2023.3282631","title":"UniFormer: Unifying Convolution and Self-Attention for Visual Recognition","display_name":"UniFormer: Unifying Convolution and Self-Attention for Visual Recognition","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4379382445","doi":"https://doi.org/10.1109/tpami.2023.3282631","pmid":"https://pubmed.ncbi.nlm.nih.gov/37276098"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3282631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3282631","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5078355895","display_name":"Kunchang Li","orcid":"https://orcid.org/0000-0001-5612-0341"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kunchang Li","raw_affiliation_strings":["ShenZhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5612-0341","affiliations":[{"raw_affiliation_string":"ShenZhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335705","display_name":"Yali Wang","orcid":"https://orcid.org/0000-0002-2999-7428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Wang","raw_affiliation_strings":["ShenZhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-7428","affiliations":[{"raw_affiliation_string":"ShenZhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664140","display_name":"Junhao Zhang","orcid":"https://orcid.org/0000-0002-7512-7562"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junhao Zhang","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106667221","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0005-7881-712X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laborator, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laborator, Shanghai, China","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033877290","display_name":"Guanglu Song","orcid":"https://orcid.org/0000-0001-5391-5712"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglu Song","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092088665","display_name":"Yu Liu","orcid":"https://orcid.org/0009-0008-4087-1026"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2664-7975","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["ShenZhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","Shanghai AI Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-1889-2567","affiliations":[{"raw_affiliation_string":"ShenZhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078355895"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":58.8833,"has_fulltext":false,"cited_by_count":538,"citation_normalized_percentile":{"value":0.99937452,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"45","issue":"10","first_page":"12581","last_page":"12600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7196322679519653},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6917072534561157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6402108669281006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4584289789199829},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43429329991340637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1710973083972931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196322679519653},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6917072534561157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6402108669281006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4584289789199829},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43429329991340637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1710973083972931}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3282631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3282631","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37276098","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37276098","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G3908541760","display_name":null,"funder_award_id":"2020355","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G5087484788","display_name":null,"funder_award_id":"62272450","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/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":167,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W2097117768","https://openalex.org/W2105101328","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2507296351","https://openalex.org/W2549139847","https://openalex.org/W2616247523","https://openalex.org/W2622263826","https://openalex.org/W2625366777","https://openalex.org/W2765407302","https://openalex.org/W2768282280","https://openalex.org/W2883780447","https://openalex.org/W2884822772","https://openalex.org/W2887051120","https://openalex.org/W2910628332","https://openalex.org/W2948048211","https://openalex.org/W2955425717","https://openalex.org/W2962843773","https://openalex.org/W2963091558","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963155035","https://openalex.org/W2963163009","https://openalex.org/W2963263347","https://openalex.org/W2963402313","https://openalex.org/W2963446712","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2981385151","https://openalex.org/W2982083293","https://openalex.org/W2984287396","https://openalex.org/W2988630963","https://openalex.org/W2989676862","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2992308087","https://openalex.org/W2996901793","https://openalex.org/W3014641072","https://openalex.org/W3016719260","https://openalex.org/W3034429256","https://openalex.org/W3034572008","https://openalex.org/W3034600407","https://openalex.org/W3035303837","https://openalex.org/W3035619757","https://openalex.org/W3043840704","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3096833468","https://openalex.org/W3102564565","https://openalex.org/W3109635183","https://openalex.org/W3117707723","https://openalex.org/W3121523901","https://openalex.org/W3122239467","https://openalex.org/W3124692185","https://openalex.org/W3126721948","https://openalex.org/W3130071011","https://openalex.org/W3131500599","https://openalex.org/W3136416617","https://openalex.org/W3137120824","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3145444543","https://openalex.org/W3157525179","https://openalex.org/W3157528469","https://openalex.org/W3167536469","https://openalex.org/W3168101492","https://openalex.org/W3168124404","https://openalex.org/W3169612303","https://openalex.org/W3170630188","https://openalex.org/W3170860705","https://openalex.org/W3170874841","https://openalex.org/W3170974475","https://openalex.org/W3171087525","https://openalex.org/W3171125843","https://openalex.org/W3172509117","https://openalex.org/W3172801447","https://openalex.org/W3173621652","https://openalex.org/W3175515048","https://openalex.org/W3175528717","https://openalex.org/W3175544090","https://openalex.org/W3176153963","https://openalex.org/W3176892444","https://openalex.org/W3180463990","https://openalex.org/W3188427387","https://openalex.org/W3190492058","https://openalex.org/W3203925315","https://openalex.org/W3206810688","https://openalex.org/W3207918547","https://openalex.org/W3209987414","https://openalex.org/W3210279979","https://openalex.org/W3211490618","https://openalex.org/W3213165621","https://openalex.org/W3216553632","https://openalex.org/W4214493665","https://openalex.org/W4214516465","https://openalex.org/W4214588794","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214634256","https://openalex.org/W4214736485","https://openalex.org/W4286910290","https://openalex.org/W4287122452","https://openalex.org/W4288325606","https://openalex.org/W4295308583","https://openalex.org/W4297775537","https://openalex.org/W4298395628","https://openalex.org/W4299802238","https://openalex.org/W4312560592","https://openalex.org/W4312930076","https://openalex.org/W4313007769","https://openalex.org/W4385245566","https://openalex.org/W4402249915","https://openalex.org/W6600983433","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6639102338","https://openalex.org/W6684191040","https://openalex.org/W6726497184","https://openalex.org/W6737664043","https://openalex.org/W6739622702","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6746052068","https://openalex.org/W6750378959","https://openalex.org/W6754337694","https://openalex.org/W6762718338","https://openalex.org/W6763367864","https://openalex.org/W6764322716","https://openalex.org/W6769955919","https://openalex.org/W6778485988","https://openalex.org/W6780226713","https://openalex.org/W6780924892","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6786361841","https://openalex.org/W6787906798","https://openalex.org/W6788135285","https://openalex.org/W6789526315","https://openalex.org/W6790307280","https://openalex.org/W6790375769","https://openalex.org/W6790428460","https://openalex.org/W6792275077","https://openalex.org/W6793164127","https://openalex.org/W6794345597","https://openalex.org/W6794642395","https://openalex.org/W6796237581","https://openalex.org/W6796246584","https://openalex.org/W6796494063","https://openalex.org/W6796568838","https://openalex.org/W6796721132","https://openalex.org/W6796931752","https://openalex.org/W6797153837","https://openalex.org/W6797206543","https://openalex.org/W6797263693","https://openalex.org/W6797399245","https://openalex.org/W6797790494","https://openalex.org/W6798016242","https://openalex.org/W6798837711","https://openalex.org/W6802010497","https://openalex.org/W6802648153"],"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":{"It":[0,216],"is":[1],"a":[2,54,95,111,161,210,267],"challenging":[3],"task":[4],"to":[5,14,64,86,174,179],"learn":[6],"discriminative":[7],"representation":[8,152],"from":[9,116,172,177],"images":[10],"and":[11,18,30,108,132,139,146,150,165,235,252,274],"videos,":[12],"due":[13],"large":[15],"local":[16,49,131],"redundancy":[17,50,145],"complex":[19],"global":[20,66,133],"dependency":[21,74,147],"in":[22,39,110,124,137,209],"these":[23,91],"visual":[24],"data.":[25],"Convolution":[26],"neural":[27],"networks":[28],"(CNNs)":[29],"vision":[31,170],"transformers":[32],"(ViTs)":[33],"have":[34],"been":[35],"two":[36],"dominant":[37],"frameworks":[38],"the":[40,57,83,104,117,121,284],"past":[41],"few":[42],"years.":[43],"Though":[44],"CNNs":[45],"can":[46,70,101,204],"efficiently":[47],"decrease":[48],"by":[51],"convolution":[52,107],"within":[53],"small":[55],"neighborhood,":[56],"limited":[58],"receptive":[59],"field":[60],"makes":[61],"it":[62,167,203],"hard":[63],"capture":[65,72],"dependency.":[67],"Alternatively,":[68],"ViTs":[69],"effectively":[71],"long-range":[73],"via":[75],"self-attention,":[76],"while":[77],"blind":[78],"similarity":[79],"comparisons":[80],"among":[81],"all":[82],"tokens":[84],"lead":[85],"high":[87],"redundancy.":[88],"To":[89],"resolve":[90],"problems,":[92],"we":[93,155,261],"propose":[94],"novel":[96],"Unified":[97],"transFormer":[98],"(UniFormer),":[99],"which":[100,276],"seamlessly":[102],"integrate":[103],"merits":[105],"of":[106,213,271],"self-attention":[109],"concise":[112,268],"transformer":[113,119],"format.":[114],"Different":[115],"typical":[118],"blocks,":[120],"relation":[122],"aggregators":[123],"our":[125,158,187],"UniFormer":[126,188,265],"block":[127],"are":[128],"equipped":[129],"with":[130,266],"token":[134,272],"affinity":[135],"respectively":[136],"shallow":[138],"deep":[140],"layers,":[141],"allowing":[142],"tackling":[143],"both":[144],"for":[148,168],"efficient":[149,264],"effective":[151],"learning.":[153],"Finally,":[154],"flexibly":[156],"stack":[157],"blocks":[159],"into":[160],"new":[162],"powerful":[163],"backbone,":[164],"adopt":[166],"various":[169],"tasks":[171],"image":[173],"video":[175,229],"domain,":[176],"classification":[178,196,230],"dense":[180],"prediction.":[181],"Without":[182],"any":[183],"extra":[184],"training":[185],"data,":[186],"achieves":[189,277],"86.3":[190],"top-1":[191,219,224],"accuracy":[192,220,225],"on":[193,221,226,239,246,255],"ImageNet-1":[194,200],"K":[195,201,248],"task.":[197,259],"With":[198],"only":[199],"pre-training,":[202],"simply":[205],"achieve":[206],"state-of-the-art":[207],"performance":[208],"broad":[211],"range":[212],"downstream":[214],"tasks.":[215],"obtains":[217],"82.9/84.8":[218],"Kinetics-400/600,":[222],"60.9/71.2":[223],"Something-Something":[227],"V1/V2":[228],"tasks,":[231],"53.8":[232],"box":[233],"AP":[234,238,254],"46.4":[236],"mask":[237],"COCO":[240,256],"object":[241],"detection":[242],"task,":[243,251],"50.8":[244],"mIoU":[245],"ADE20":[247],"semantic":[249],"segmentation":[250],"77.4":[253],"pose":[257],"estimation":[258],"Moreover,":[260],"build":[262],"an":[263],"hourglass":[269],"design":[270],"shrinking":[273],"recovering,":[275],"2-4[Formula:":[278],"see":[279],"text]":[280],"higher":[281],"throughput":[282],"than":[283],"recent":[285],"lightweight":[286],"models.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":48},{"year":2025,"cited_by_count":211},{"year":2024,"cited_by_count":185},{"year":2023,"cited_by_count":78},{"year":2022,"cited_by_count":16}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}