{"id":"https://openalex.org/W3168825659","doi":"https://doi.org/10.1109/icme52920.2022.9859720","title":"CAT: Cross Attention in Vision Transformer","display_name":"CAT: Cross Attention in Vision Transformer","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3168825659","doi":"https://doi.org/10.1109/icme52920.2022.9859720","mag":"3168825659"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859720","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5071301036","display_name":"Hezheng Lin","orcid":"https://orcid.org/0009-0007-8996-8438"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hezheng Lin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101583704","display_name":"Cheng Xing","orcid":"https://orcid.org/0000-0002-8738-833X"},"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":"Xing Cheng","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/A5021998562","display_name":"Xiangyu Wu","orcid":"https://orcid.org/0000-0003-2055-5890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":["KuaiShou Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KuaiShou Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026403327","display_name":"Dong Shen","orcid":"https://orcid.org/0000-0001-5592-8453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Shen","raw_affiliation_strings":["KuaiShou Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KuaiShou Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071301036"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":12.0469,"has_fulltext":false,"cited_by_count":226,"citation_normalized_percentile":{"value":0.9887138,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7486499547958374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479956150054932},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6533947587013245},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.612537145614624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5390175580978394},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.42256397008895874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.327077180147171},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1484278440475464},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09994876384735107}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7486499547958374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479956150054932},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6533947587013245},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.612537145614624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5390175580978394},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.42256397008895874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.327077180147171},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1484278440475464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09994876384735107},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859720","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":110,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1538131130","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1923697677","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2124386111","https://openalex.org/W2144506857","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2331143823","https://openalex.org/W2412782625","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2560023338","https://openalex.org/W2565639579","https://openalex.org/W2612445135","https://openalex.org/W2626778328","https://openalex.org/W2630837129","https://openalex.org/W2737258237","https://openalex.org/W2768282280","https://openalex.org/W2796347433","https://openalex.org/W2883780447","https://openalex.org/W2884822772","https://openalex.org/W2896457183","https://openalex.org/W2910628332","https://openalex.org/W2913318911","https://openalex.org/W2916798096","https://openalex.org/W2936599103","https://openalex.org/W2938830017","https://openalex.org/W2950141105","https://openalex.org/W2950813464","https://openalex.org/W2952337489","https://openalex.org/W2953106684","https://openalex.org/W2955058313","https://openalex.org/W2955425717","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963341956","https://openalex.org/W2963351448","https://openalex.org/W2963840672","https://openalex.org/W2963857746","https://openalex.org/W2964080601","https://openalex.org/W2964241181","https://openalex.org/W2964309882","https://openalex.org/W2964350391","https://openalex.org/W2964444661","https://openalex.org/W2965373594","https://openalex.org/W2975059944","https://openalex.org/W2982083293","https://openalex.org/W2982770724","https://openalex.org/W2998385486","https://openalex.org/W3007759824","https://openalex.org/W3011411500","https://openalex.org/W3012524094","https://openalex.org/W3016719260","https://openalex.org/W3018757597","https://openalex.org/W3034429256","https://openalex.org/W3034445277","https://openalex.org/W3034971973","https://openalex.org/W3035396860","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3104401316","https://openalex.org/W3106250896","https://openalex.org/W3109301572","https://openalex.org/W3110402800","https://openalex.org/W3113747735","https://openalex.org/W3121523901","https://openalex.org/W3128633047","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3136416617","https://openalex.org/W3137963805","https://openalex.org/W3138516171","https://openalex.org/W3139773203","https://openalex.org/W3146097248","https://openalex.org/W3151130473","https://openalex.org/W3168649818","https://openalex.org/W3170841864","https://openalex.org/W3170874841","https://openalex.org/W4214493665","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W6632100814","https://openalex.org/W6639102338","https://openalex.org/W6674330103","https://openalex.org/W6696085341","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6748481559","https://openalex.org/W6753421600","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6768371451","https://openalex.org/W6773829392","https://openalex.org/W6779879114","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790690058"],"related_works":["https://openalex.org/W4405003489","https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W3149094754","https://openalex.org/W2148703997","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Since":[0],"Transformer":[1,11,35,61],"has":[2,14,18,145],"found":[3],"widespread":[4],"use":[5],"in":[6,12,60,106],"NLP,":[7],"the":[8,24,37,40,69,74,132,146],"potential":[9,147],"of":[10,39,73,134],"CV":[13],"been":[15],"realized":[16],"and":[17,49,81,130,139,155],"inspired":[19],"many":[20],"new":[21,57],"approaches.":[22],"However,":[23],"computation":[25,102],"required":[26],"for":[27,34,120],"replacing":[28],"word":[29],"tokens":[30],"with":[31],"image":[32,41,70,76,85],"patches":[33,86],"after":[36],"tokenization":[38],"is":[42],"vast(e.g.,":[43],"ViT),":[44],"which":[45,65,87],"bottlenecks":[46],"model":[47,125],"training":[48],"inference.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,111],"propose":[55],"a":[56,113],"attention":[58,67,83],"mechanism":[59],"termed":[62],"Cross":[63,117],"Attention,":[64],"alternates":[66],"inner":[68],"patch":[71],"instead":[72],"whole":[75],"to":[77,94,148],"capture":[78,95],"local":[79],"information":[80],"apply":[82],"between":[84],"are":[88,157],"divided":[89],"from":[90],"single-channel":[91],"feature":[92],"maps":[93],"global":[96],"information.":[97],"Both":[98],"operations":[99],"have":[100],"less":[101],"than":[103],"standard":[104],"self-attention":[105],"Transformer.":[107],"Based":[108],"on":[109,128,137],"that,":[110],"build":[112],"hierarchical":[114],"network":[115,144],"called":[116],"Attention":[118],"Transformer(CAT)":[119],"other":[121,135],"vision":[122],"tasks.":[123],"Our":[124],"achieves":[126],"82.8%":[127],"ImageNet-1K,":[129],"improves":[131],"performance":[133],"methods":[136],"COCO":[138],"ADE20K,":[140],"illustrating":[141],"that":[142],"our":[143],"serve":[149],"as":[150],"general":[151],"backbones.":[152],"The":[153],"code":[154],"models":[156],"avalible":[158],"at":[159],"https://github.com/linhezheng19/CAT.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":94},{"year":2024,"cited_by_count":63},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}