{"id":"https://openalex.org/W4390660439","doi":"https://doi.org/10.1109/tpami.2023.3347693","title":"Vision Transformer With Quadrangle Attention","display_name":"Vision Transformer With Quadrangle Attention","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4390660439","doi":"https://doi.org/10.1109/tpami.2023.3347693","pmid":"https://pubmed.ncbi.nlm.nih.gov/38190690"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3347693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3347693","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/A5100639013","display_name":"Qiming Zhang","orcid":"https://orcid.org/0000-0003-0060-0543"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiming Zhang","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0060-0543","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345321","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6595-7661","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042154277","display_name":"Yufei Xu","orcid":"https://orcid.org/0000-0002-9931-5138"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yufei Xu","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9931-5138","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":11.3155,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.99291439,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"46","issue":"5","first_page":"3608","last_page":"3624"},"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":0.9983000159263611,"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":0.9968000054359436,"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/quadrangle","display_name":"Quadrangle","score":0.856308102607727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774540901184082},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6603546142578125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919201970100403},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45246338844299316},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4483826458454132},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.414113312959671},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10083869099617004}],"concepts":[{"id":"https://openalex.org/C27258493","wikidata":"https://www.wikidata.org/wiki/Q7268308","display_name":"Quadrangle","level":2,"score":0.856308102607727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774540901184082},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6603546142578125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919201970100403},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45246338844299316},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4483826458454132},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.414113312959671},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10083869099617004},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"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":2,"locations":[{"id":"doi:10.1109/tpami.2023.3347693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3347693","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:38190690","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38190690","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":[],"awards":[{"id":"https://openalex.org/G7519899501","display_name":null,"funder_award_id":"FL-170100117","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1921523184","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2549139847","https://openalex.org/W2601564443","https://openalex.org/W2737258237","https://openalex.org/W2765407302","https://openalex.org/W2884822772","https://openalex.org/W2963150697","https://openalex.org/W2963402313","https://openalex.org/W2964241181","https://openalex.org/W2966926453","https://openalex.org/W2989676862","https://openalex.org/W2992308087","https://openalex.org/W2998341422","https://openalex.org/W3009184501","https://openalex.org/W3034742259","https://openalex.org/W3121523901","https://openalex.org/W3122239467","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3159663321","https://openalex.org/W3168101492","https://openalex.org/W3175515048","https://openalex.org/W3187216907","https://openalex.org/W4214636423","https://openalex.org/W4226424839","https://openalex.org/W4288325606","https://openalex.org/W4312257978","https://openalex.org/W4312349930","https://openalex.org/W4312446817","https://openalex.org/W4312599212","https://openalex.org/W4312638656","https://openalex.org/W4312652102","https://openalex.org/W4312769131","https://openalex.org/W4312881242","https://openalex.org/W4312950730","https://openalex.org/W4312960790","https://openalex.org/W4313007769","https://openalex.org/W4313156423","https://openalex.org/W4313166619","https://openalex.org/W4315705623","https://openalex.org/W4389977645","https://openalex.org/W6640185926","https://openalex.org/W6696085341","https://openalex.org/W6745136726","https://openalex.org/W6757817989","https://openalex.org/W6764322716","https://openalex.org/W6779602356","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6792695861","https://openalex.org/W6794345597","https://openalex.org/W6795308139","https://openalex.org/W6795463671","https://openalex.org/W6796237581","https://openalex.org/W6796526935","https://openalex.org/W6796761347","https://openalex.org/W6796931752","https://openalex.org/W6797235774","https://openalex.org/W6797790494","https://openalex.org/W6803650990","https://openalex.org/W6803680838","https://openalex.org/W6803916128","https://openalex.org/W6809664228"],"related_works":["https://openalex.org/W1585542233","https://openalex.org/W4237181552","https://openalex.org/W1563088842","https://openalex.org/W1903581","https://openalex.org/W1578917397","https://openalex.org/W137481974","https://openalex.org/W4252312427","https://openalex.org/W62814732","https://openalex.org/W1602359905","https://openalex.org/W4233996937"],"abstract_inverted_index":{"Window-based":[0],"attention":[1,55,62,93],"has":[2],"become":[3],"a":[4,52,64,79,123],"popular":[5],"choice":[6],"in":[7],"vision":[8,119,149,153],"transformers":[9,35,120,150],"due":[10],"to":[11,36,38,63,82,98,121],"its":[12],"superior":[13],"performance,":[14],"lower":[15],"computational":[16,136],"complexity,":[17],"and":[18,44,92,105,107,117,133,161],"less":[19],"memory":[20],"footprint.":[21],"However,":[22],"the":[23,32,60,96],"design":[24],"of":[25,34,40],"hand-crafted":[26],"windows,":[27],"which":[28,128],"is":[29],"data-agnostic,":[30],"constrains":[31],"flexibility":[33],"adapt":[37],"objects":[39],"varying":[41],"sizes,":[42],"shapes,":[43],"orientations.":[45],"To":[46],"address":[47],"this":[48],"issue,":[49],"we":[50],"propose":[51],"novel":[53],"quadrangle":[54,66,74],"(QA)":[56],"method":[57,69],"that":[58,77,144],"extends":[59],"window-based":[61],"general":[65],"formulation.":[67],"Our":[68],"employs":[70],"an":[71],"end-to-end":[72],"learnable":[73],"regression":[75],"module":[76],"predicts":[78],"transformation":[80],"matrix":[81],"transform":[83],"default":[84],"windows":[85],"into":[86,115],"target":[87],"quadrangles":[88],"for":[89],"token":[90],"sampling":[91],"calculation,":[94],"enabling":[95],"network":[97],"model":[99],"various":[100,152],"targets":[101],"with":[102],"different":[103],"shapes":[104],"orientations":[106],"capture":[108],"rich":[109],"context":[110],"information.":[111],"We":[112],"integrate":[113],"QA":[114],"plain":[116],"hierarchical":[118],"create":[122],"new":[124],"architecture":[125],"named":[126],"QFormer,":[127],"offers":[129],"minor":[130],"code":[131,165],"modifications":[132],"negligible":[134],"extra":[135],"cost.":[137],"Extensive":[138],"experiments":[139],"on":[140,151],"public":[141],"benchmarks":[142],"demonstrate":[143],"QFormer":[145],"outperforms":[146],"existing":[147],"representative":[148],"tasks,":[154],"including":[155],"classification,":[156],"object":[157],"detection,":[158],"semantic":[159],"segmentation,":[160],"pose":[162],"estimation.":[163],"The":[164],"will":[166],"be":[167],"made":[168],"publicly":[169],"available":[170],"at":[171],"QFormer.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}