{"id":"https://openalex.org/W7156294769","doi":"https://doi.org/10.1016/j.patcog.2026.113818","title":"Vision transformer Hook for dense predictions","display_name":"Vision transformer Hook for dense predictions","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7156294769","doi":"https://doi.org/10.1016/j.patcog.2026.113818"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.113818","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113818","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2026.113818","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103267120","display_name":"Siyuan Mei","orcid":"https://orcid.org/0009-0002-1136-2501"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Siyuan Mei","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0009-0002-1136-2501","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029146495","display_name":"Mareike Thies","orcid":"https://orcid.org/0000-0002-1364-4337"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mareike Thies","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1364-4337","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746140","display_name":"Yan Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"id":"https://openalex.org/I4210088053","display_name":"Universit\u00e4tsklinikum Erlangen","ror":"https://ror.org/0030f2a11","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210088053"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yan Xia","raw_affiliation_strings":["Department of Orthodontics and Orofacial Orthopaedics, University of Erlangen\u2013Nuremberg, Gl\u00fcckstra\u00dfe 13, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Orthodontics and Orofacial Orthopaedics, University of Erlangen\u2013Nuremberg, Gl\u00fcckstra\u00dfe 13, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854","https://openalex.org/I4210088053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110375849","display_name":"Yipeng Sun","orcid":"https://orcid.org/0009-0009-8587-8894"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yipeng Sun","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0009-0009-8587-8894","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134669823","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-4196-0289"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4196-0289","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035094835","display_name":"Fuxin Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fuxin Fan","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9602-6237","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134684783","display_name":"Mingxuan Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mingxuan Gu","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134699415","display_name":"Chengze Ye","orcid":"https://orcid.org/0009-0001-0221-506X"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chengze Ye","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0009-0001-0221-506X","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073209088","display_name":"Yixing Huang","orcid":"https://orcid.org/0000-0003-2627-3077"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Huang","raw_affiliation_strings":["Institute of Medical Technology, Peking University, 38 Xueyuan Rd, 100191, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2627-3077","affiliations":[{"raw_affiliation_string":"Institute of Medical Technology, Peking University, 38 Xueyuan Rd, 100191, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087093169","display_name":"Vincent Christlein","orcid":"https://orcid.org/0000-0003-0455-3799"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vincent Christlein","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0455-3799","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128859507","display_name":"Andreas Maier","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Maier","raw_affiliation_strings":["Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, University of Erlangen\u2013Nuremberg, Martensstr. 3, Erlangen, 91054, Bavaria, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103267120"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":{"value":2710,"currency":"USD","value_usd":2710},"apc_paid":{"value":2710,"currency":"USD","value_usd":2710},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43956811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"179","issue":null,"first_page":"113818","last_page":"113818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.047200001776218414,"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":0.047200001776218414,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.045099999755620956,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.029400000348687172,"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":0.7182000279426575},{"id":"https://openalex.org/keywords/hook","display_name":"Hook","score":0.4230000078678131},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4194999933242798},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4083000123500824},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3889000117778778},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3749000132083893},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.35530000925064087},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.34279999136924744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953000068664551},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7182000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051999926567078},{"id":"https://openalex.org/C2777586403","wikidata":"https://www.wikidata.org/wiki/Q4243098","display_name":"Hook","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37630000710487366},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3749000132083893},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2858999967575073},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.263700008392334}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.patcog.2026.113818","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113818","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},{"id":"pmh:oai:open.fau.de:openfau/40292","is_oa":true,"landing_page_url":"https://open.fau.de/handle/openfau/40292","pdf_url":null,"source":{"id":"https://openalex.org/S7407055110","display_name":"OPUS FAU - Online publication system of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.patcog.2026.113818","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113818","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2531409750","https://openalex.org/W2561196672","https://openalex.org/W2565639579","https://openalex.org/W2884822772","https://openalex.org/W2963150697","https://openalex.org/W2963341956","https://openalex.org/W2964241181","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3175515048","https://openalex.org/W4312443924","https://openalex.org/W4312815172","https://openalex.org/W4313156423","https://openalex.org/W4386065524","https://openalex.org/W4386071687","https://openalex.org/W4386076222","https://openalex.org/W4386076522","https://openalex.org/W4388157208","https://openalex.org/W4390873750","https://openalex.org/W4393906060","https://openalex.org/W4402716137","https://openalex.org/W4402727452"],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"vision":[1,120,295],"transformers":[2],"(ViTs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capability":[7],"in":[8],"learning":[9],"semantically":[10],"rich":[11],"image":[12],"representations.":[13],"However,":[14],"their":[15],"underlying":[16],"plain":[17,49],"architectures":[18],"yield":[19],"low-resolution":[20],"feature":[21],"maps,":[22],"lacking":[23],"essential":[24],"fine-grained":[25],"spatial":[26,62,94,237],"details":[27],"required":[28],"for":[29,118],"dense":[30,168,231],"prediction":[31,169,232],"tasks.":[32,233],"To":[33],"better":[34],"transfer":[35],"the":[36,54,70,77,182,280,292],"learned":[37],"visual":[38],"features,":[39],"we":[40,131],"present":[41],"ViT-Hook,":[42,219],"a":[43,83,115,194,220,259,271],"novel":[44,260],"hybrid":[45,221],"backbone":[46,222],"compatible":[47],"with":[48,98,154,162],"ViTs":[50],"that":[51,88,133,223],"effectively":[52,224],"bridges":[53],"gap":[55],"between":[56],"global":[57],"semantic":[58,172],"understanding":[59],"and":[60,72,96,126,151,176,185,208,239,275],"local":[61],"encodings.":[63],"Specifically,":[64],"our":[65,189],"method":[66],"aims":[67],"to":[68,250],"broaden":[69],"scope":[71],"impact":[73],"of":[74,273,282,287],"ViT":[75,100,139],"from":[76,102],"following":[78],"perspectives:":[79],"(1)":[80],"We":[81,159,217,257,278],"propose":[82,218],"simple":[84],"transformer-decoder-inspired":[85],"hook":[86,240],"module":[87],"receives":[89],"hierarchical":[90],"CNN":[91],"features":[92,101],"as":[93,124],"queries":[95],"interacts":[97],"expressive":[99],"large-scale":[103],"pre-training,":[104],"therefore":[105],"instantiating":[106],"general-purpose":[107],"representations":[108],"into":[109],"task-suited":[110],"ones.":[111],"(2)":[112],"ViT-Hook":[113,161,190,283],"is":[114],"plug-and-play":[116],"solution":[117],"powerful":[119],"foundation":[121,296],"models,":[122],"such":[123],"DINOv2":[125],"RADIO.":[127],"In":[128],"this":[129],"case,":[130],"find":[132],"only":[134,270],"partially":[135],"fine-tuning":[136,145,262,267],"several":[137],"intermediate":[138],"layers":[140],"can":[141],"outperform":[142],"previous":[143],"full":[144,266],"methods,":[146,290],"while":[147,268],"substantially":[148],"reducing":[149],"compute":[150,274],"memory":[152],"burdens":[153],"most":[155,293],"parameters":[156],"frozen.":[157],"(3)":[158],"evaluate":[160],"various":[163,230],"pre-trained":[164],"sources":[165],"on":[166,181,201,213,229,252,284],"multiple":[167,285],"tasks,":[170],"including":[171,291],"segmentation,":[173,175],"instance":[174],"object":[177],"detection.":[178],"Notably,":[179],"tested":[180],"unified":[183],"UperNet":[184],"Mask":[186],"R-CNN":[187],"frameworks,":[188],"surpasses":[191],"state-of-the-art":[192],"by":[193],"large":[195],"margin,":[196],"achieving":[197,246],"59.7":[198],"(+4.7)":[199],"mIoU":[200],"ADE20K":[202],"val,":[203],"55.0":[204],"(+3.6)":[205],"box":[206],"AP":[207,212],"48.5":[209],"(+3.3)":[210],"mask":[211],"COCO":[214],"val2017.":[215],"\u2022":[216,234,256,277],"enhances":[225],"Vision":[226],"Transformer":[227],"performance":[228],"The":[235],"proposed":[236],"query":[238],"modules":[241],"are":[242],"lightweight":[243],"yet":[244],"powerful,":[245],"competitive":[247],"results":[248],"compared":[249],"SoTA":[251],"widely":[253],"used":[254],"benchmarks.":[255],"introduce":[258],"partial":[261],"strategy,":[263],"which":[264],"outperforms":[265],"using":[269],"fraction":[272],"memory.":[276],"validate":[279],"generalizability":[281],"types":[286],"upstream":[288],"pre-training":[289],"recent":[294],"models.":[297]},"counts_by_year":[],"updated_date":"2026-05-05T06:06:40.768181","created_date":"2026-04-28T00:00:00"}