{"id":"https://openalex.org/W4389977645","doi":"https://doi.org/10.1109/tpami.2023.3341806","title":"CrossFormer++: A Versatile Vision Transformer Hinging on Cross-Scale Attention","display_name":"CrossFormer++: A Versatile Vision Transformer Hinging on Cross-Scale Attention","publication_year":2023,"publication_date":"2023-12-19","ids":{"openalex":"https://openalex.org/W4389977645","doi":"https://doi.org/10.1109/tpami.2023.3341806","pmid":"https://pubmed.ncbi.nlm.nih.gov/38113150"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3341806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3341806","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/A5029109301","display_name":"Wenxiao Wang","orcid":"https://orcid.org/0000-0002-6399-292X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenxiao Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740616","display_name":"Wei Chen","orcid":"https://orcid.org/0009-0009-3265-3966"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055301514","display_name":"Qibo Qiu","orcid":"https://orcid.org/0000-0002-2848-6079"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibo Qiu","raw_affiliation_strings":["Zhejiang Lab, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833492","display_name":"Boxi Wu","orcid":"https://orcid.org/0000-0003-4494-193X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boxi Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103236286","display_name":"Binbin Lin","orcid":"https://orcid.org/0000-0002-0330-6406"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Lin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013345","display_name":"Xiaofei He","orcid":"https://orcid.org/0009-0001-9107-2354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei He","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Data Platform, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Data Platform, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5029109301"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":31.0201,"has_fulltext":false,"cited_by_count":265,"citation_normalized_percentile":{"value":0.99830354,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"46","issue":"5","first_page":"3123","last_page":"3136"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9995999932289124,"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":0.9980000257492065,"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/transformer","display_name":"Transformer","score":0.7101593613624573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6819800138473511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6459702849388123},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6348459720611572},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.632591187953949},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.541153073310852},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46863269805908203},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4454532265663147},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3872842788696289},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16894474625587463},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07022956013679504}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7101593613624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819800138473511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6459702849388123},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6348459720611572},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.632591187953949},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.541153073310852},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46863269805908203},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4454532265663147},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3872842788696289},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16894474625587463},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07022956013679504},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2023.3341806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3341806","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:38113150","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38113150","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},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-135089","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-135089","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2101641620","display_name":null,"funder_award_id":"62273303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5002927567","display_name":null,"funder_award_id":"62303406","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2331143823","https://openalex.org/W2884561390","https://openalex.org/W2884822772","https://openalex.org/W2910628332","https://openalex.org/W2963150697","https://openalex.org/W2963925437","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3034572008","https://openalex.org/W3035682985","https://openalex.org/W3096609285","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3139633126","https://openalex.org/W3151130473","https://openalex.org/W3159481202","https://openalex.org/W3164208409","https://openalex.org/W3164540605","https://openalex.org/W3165150763","https://openalex.org/W3166942762","https://openalex.org/W3168101492","https://openalex.org/W3168825659","https://openalex.org/W3172345956","https://openalex.org/W3172509117","https://openalex.org/W3172801447","https://openalex.org/W3202742610","https://openalex.org/W3204801262","https://openalex.org/W4214493665","https://openalex.org/W4214633470","https://openalex.org/W4288325606","https://openalex.org/W4295308583","https://openalex.org/W4312628331","https://openalex.org/W4312769131","https://openalex.org/W4312847199","https://openalex.org/W4312881242","https://openalex.org/W4312977443","https://openalex.org/W4313007769","https://openalex.org/W4313156423","https://openalex.org/W4315705623","https://openalex.org/W4366208220","https://openalex.org/W4386221015","https://openalex.org/W4389977645","https://openalex.org/W6631190155","https://openalex.org/W6741437728","https://openalex.org/W6745136726","https://openalex.org/W6764322716","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6792695861","https://openalex.org/W6795463671","https://openalex.org/W6795467770","https://openalex.org/W6795592662","https://openalex.org/W6796237581","https://openalex.org/W6796526935","https://openalex.org/W6796750486","https://openalex.org/W6796931752","https://openalex.org/W6800217721","https://openalex.org/W6803469875","https://openalex.org/W6810007534","https://openalex.org/W6851800889"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4304700937","https://openalex.org/W1522196789"],"abstract_inverted_index":{"While":[0],"features":[1,99],"of":[2,19,57],"different":[3,58],"scales":[4],"are":[5],"perceptually":[6],"important":[7],"to":[8,142],"visual":[9],"inputs,":[10],"existing":[11],"vision":[12,30,115,166],"transformers":[13,167],"do":[14],"not":[15,86],"yet":[16],"take":[17],"advantage":[18],"them":[20],"explicitly.":[21],"To":[22],"this":[23],"end,":[24],"we":[25,108,127],"first":[26],"propose":[27,129],"a":[28,35,41,78,82,130],"cross-scale":[29,36,66],"transformer,":[31],"CrossFormer.":[32],"It":[33],"introduces":[34],"embedding":[37],"layer":[38,140],"(CEL)":[39],"and":[40,81,97,123,136,153,175],"long-short":[42],"distance":[43],"attention":[44],"(LSDA).":[45],"On":[46,68],"the":[47,61,69,74,89,101,119,144,164],"one":[48,80],"hand,":[49,71],"CEL":[50],"blends":[51],"each":[52],"token":[53],"with":[54,65,151],"multiple":[55],"patches":[56],"scales,":[59],"providing":[60],"self-attention":[62,75,121],"module":[63,76],"itself":[64],"features.":[67],"other":[70,165],"LSDA":[72],"splits":[73],"into":[77],"short-distance":[79],"long-distance":[83],"counterpart,":[84],"which":[85],"only":[87],"reduces":[88],"computational":[90],"burden":[91],"but":[92],"also":[93],"keeps":[94],"both":[95],"small-scale":[96],"large-scale":[98],"in":[100],"tokens.":[102],"Moreover,":[103],"through":[104],"experiments":[105,159],"on":[106,168],"CrossFormer,":[107],"observe":[109],"another":[110],"two":[111,145],"issues":[112],"that":[113,161],"affect":[114],"transformers'":[116],"performance,":[117],"i.e.,":[118],"enlarging":[120],"maps":[122],"amplitude":[124,138],"explosion.":[125],"Thus,":[126],"further":[128],"progressive":[131],"group":[132],"size":[133],"(PGS)":[134],"paradigm":[135],"an":[137],"cooling":[139],"(ACL)":[141],"alleviate":[143],"issues,":[146],"respectively.":[147],"The":[148],"CrossFormer":[149],"incorporating":[150],"PGS":[152],"ACL":[154],"is":[155],"called":[156],"CrossFormer++.":[157],"Extensive":[158],"show":[160],"CrossFormer++":[162],"outperforms":[163],"image":[169],"classification,":[170],"object":[171],"detection,":[172],"instance":[173],"segmentation,":[174],"semantic":[176],"segmentation":[177],"tasks.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":129},{"year":2024,"cited_by_count":66},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}