{"id":"https://openalex.org/W4394963135","doi":"https://doi.org/10.1007/s11633-024-1393-8","title":"Vision Transformers with Hierarchical Attention","display_name":"Vision Transformers with Hierarchical Attention","publication_year":2024,"publication_date":"2024-04-19","ids":{"openalex":"https://openalex.org/W4394963135","doi":"https://doi.org/10.1007/s11633-024-1393-8"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-024-1393-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-024-1393-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1393-8.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1393-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056961910","display_name":"Yun Liu","orcid":"https://orcid.org/0000-0001-6143-0264"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yun Liu","raw_affiliation_strings":["Institute for Infocomm Research (I2R), A*STAR, Singapore, 138632, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001598042","display_name":"Yu-Huan Wu","orcid":"https://orcid.org/0000-0001-8666-3435"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yu-Huan Wu","raw_affiliation_strings":["Institute of High Performance Computing (IHPC), A*STAR, Singapore, 138632, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing (IHPC), A*STAR, Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010215983","display_name":"Guolei Sun","orcid":"https://orcid.org/0000-0001-8667-9656"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Guolei Sun","raw_affiliation_strings":["Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350631","display_name":"Le Zhang","orcid":"https://orcid.org/0000-0002-6930-8674"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Le Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611731, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611731, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009256545","display_name":"Ajad Chhatkuli","orcid":"https://orcid.org/0000-0003-2051-2209"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ajad Chhatkuli","raw_affiliation_strings":["Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001254143","display_name":"Luc Van Gool","orcid":"https://orcid.org/0000-0002-3445-5711"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luc Van Gool","raw_affiliation_strings":["Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010215983","https://openalex.org/A5100350631"],"corresponding_institution_ids":["https://openalex.org/I150229711","https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":9.5864,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.9862952,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"21","issue":"4","first_page":"670","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.998199999332428,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.998199999332428,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9966999888420105,"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":0.4964905381202698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44976502656936646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38123035430908203},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21491339802742004},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10299438238143921}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4964905381202698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44976502656936646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38123035430908203},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21491339802742004},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10299438238143921},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11633-024-1393-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-024-1393-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1393-8.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11633-024-1393-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-024-1393-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-024-1393-8.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394963135.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2518108298","https://openalex.org/W2549139847","https://openalex.org/W2550553598","https://openalex.org/W2560622558","https://openalex.org/W2737258237","https://openalex.org/W2883780447","https://openalex.org/W2884585870","https://openalex.org/W2910628332","https://openalex.org/W2922509574","https://openalex.org/W2946948417","https://openalex.org/W2962834855","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963341956","https://openalex.org/W2963351448","https://openalex.org/W2963420686","https://openalex.org/W2963446712","https://openalex.org/W2963495494","https://openalex.org/W2963918968","https://openalex.org/W2964110616","https://openalex.org/W3016719260","https://openalex.org/W3034429256","https://openalex.org/W3034922525","https://openalex.org/W3085685449","https://openalex.org/W3112885960","https://openalex.org/W3116489684","https://openalex.org/W3121523901","https://openalex.org/W3127842933","https://openalex.org/W3131500599","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3157528469","https://openalex.org/W3172509117","https://openalex.org/W3175515048","https://openalex.org/W3216325077","https://openalex.org/W4214493665","https://openalex.org/W4214614183","https://openalex.org/W4214634256","https://openalex.org/W4214636423","https://openalex.org/W4226297238","https://openalex.org/W4226363321","https://openalex.org/W4231059779","https://openalex.org/W4285787147","https://openalex.org/W6753038380","https://openalex.org/W6757817989","https://openalex.org/W6790690058","https://openalex.org/W6795140394","https://openalex.org/W6796417832","https://openalex.org/W6846577953"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"tackles":[3],"the":[4,39,56,71,82,86,90,95,124,144,160],"high":[5],"computational/space":[6],"complexity":[7],"associated":[8],"with":[9,106],"multi-head":[10],"self-attention":[11],"(MHSA)":[12],"in":[13,31,164],"vanilla":[14],"vision":[15,173,192],"transformers.":[16,193],"To":[17,158],"this":[18],"end,":[19],"we":[20,36,111,148,167],"propose":[21],"hierarchical":[22,33],"MHSA":[23],"(H-MHSA),":[24],"a":[25,32,53,116,150,188],"novel":[26],"approach":[27],"that":[28],"computes":[29],"sell-attention":[30],"fashion.":[34],"Specifically,":[35],"first":[37],"divide":[38],"input":[40],"image":[41,176],"into":[42,76],"patches":[43,73],"as":[44,52,66],"commonly":[45],"done,":[46],"and":[47,79,97,182,195],"each":[48,122],"patch":[49],"is":[50,127],"viewed":[51],"token.":[54],"Then,":[55,70],"proposed":[57],"H-MHSA":[58,80,131,145],"learns":[59],"token":[60],"relationships":[61,136],"within":[62],"local":[63,67,96],"patches,":[64],"serving":[65],"relationship":[68],"modeling.":[69],"small":[72,87],"are":[74,101,198],"merged":[75,91],"larger":[77],"ones,":[78],"models":[81,197],"global":[83,98,135],"dependencies":[84],"for":[85,115,191],"number":[88,118],"of":[89,119,152,162],"tokens.":[92],"At":[93],"last,":[94],"attentive":[99],"features":[100,105],"aggregated":[102],"to":[103],"obtain":[104],"powerful":[107],"representation":[108],"capacity.":[109],"Since":[110],"only":[112],"calculate":[113],"attention":[114],"limited":[117],"tokens":[120,138],"at":[121,200],"step,":[123],"computational":[125],"load":[126],"reduced":[128],"dramatically.":[129],"Hence,":[130],"can":[132],"efficiently":[133],"model":[134],"among":[137],"without":[139],"sacrificing":[140],"fine-grained":[141],"information.":[142],"With":[143],"module":[146],"incorporated,":[147],"build":[149],"family":[151],"hierarchical-attention-based":[153],"transformer":[154],"networks,":[155],"namely":[156],"HAT-Net.":[157],"demonstrate":[159],"superiority":[161],"HAT-Net":[163,186],"scene":[165],"understanding,":[166],"conduct":[168],"extensive":[169],"experiments":[170],"on":[171],"fundamental":[172],"tasks,":[174],"including":[175],"classification,":[177],"semantic":[178],"segmentation,":[179],"object":[180],"detection":[181],"instance":[183],"segmentation.":[184],"Therefore,":[185],"provides":[187],"new":[189],"perspective":[190],"Code":[194],"pretrained":[196],"available":[199],"https://github.com/yun-liu/HAT-Net":[201],".":[202]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":8}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}