{"id":"https://openalex.org/W7131215075","doi":"https://doi.org/10.1109/tmi.2026.3667706","title":"Cogformer: A Unified Multi-Scale Brain Representation for Visual Decoding and Reconstruction From fMRI","display_name":"Cogformer: A Unified Multi-Scale Brain Representation for Visual Decoding and Reconstruction From fMRI","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131215075","doi":"https://doi.org/10.1109/tmi.2026.3667706","pmid":"https://pubmed.ncbi.nlm.nih.gov/41734131"},"language":"en","primary_location":{"id":"doi:10.1109/tmi.2026.3667706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2026.3667706","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Medical Imaging","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/A5126734583","display_name":"Xu Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092262","display_name":"Ministry of Education","ror":"https://ror.org/00dh5gw98","country_code":"RO","type":"funder","lineage":["https://openalex.org/I2799732796","https://openalex.org/I4210092262"]},{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN","RO"],"is_corresponding":false,"raw_author_name":"Xu Yin","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I4210092262","https://openalex.org/I4210100356","https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082525691","display_name":"John Q. Gan","orcid":"https://orcid.org/0000-0003-1230-7643"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Q. Gan","raw_affiliation_strings":["School of Computer Science and Electronic Engineering, University of Essex, Colchester, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1230-7643","affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex, Colchester, U.K","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126728158","display_name":"Haixian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092262","display_name":"Ministry of Education","ror":"https://ror.org/00dh5gw98","country_code":"RO","type":"funder","lineage":["https://openalex.org/I2799732796","https://openalex.org/I4210092262"]},{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN","RO"],"is_corresponding":false,"raw_author_name":"Haixian Wang","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0001-8220-9737","affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I4210092262","https://openalex.org/I4210100356","https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17377026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"6","first_page":"3021","last_page":"3038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.6934999823570251,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.6934999823570251,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.10429999977350235,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.03840000182390213,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7652999758720398},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6065000295639038},{"id":"https://openalex.org/keywords/functional-magnetic-resonance-imaging","display_name":"Functional magnetic resonance imaging","score":0.4666000008583069},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4505999982357025},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4406000077724457},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4009999930858612},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3944999873638153},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37770000100135803},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3711000084877014},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119999766349792},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7652999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6797999739646912},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6065000295639038},{"id":"https://openalex.org/C2779226451","wikidata":"https://www.wikidata.org/wiki/Q903809","display_name":"Functional magnetic resonance imaging","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4406000077724457},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C556910895","wikidata":"https://www.wikidata.org/wiki/Q384188","display_name":"Magnetoencephalography","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2612999975681305},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C152478114","wikidata":"https://www.wikidata.org/wiki/Q660910","display_name":"Neurophysiology","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25119999051094055}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098409","descriptor_name":"Representation Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098409","descriptor_name":"Representation Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D001931","descriptor_name":"Brain Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D001931","descriptor_name":"Brain Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D008279","descriptor_name":"Magnetic Resonance Imaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008279","descriptor_name":"Magnetic Resonance Imaging","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tmi.2026.3667706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2026.3667706","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Medical Imaging","raw_type":"journal-article"},{"id":"pmid:41734131","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41734131","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 medical imaging","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3298841845","display_name":null,"funder_award_id":"62176054.","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,9,27,39,44,65,101,128,135,166,184,192],"rapid":[2],"development":[3],"of":[4,11,30,48,98,111,130,152,170],"deep":[5],"generative":[6],"models":[7],"(DGMs),":[8],"performance":[10,147,211],"decoding":[12,81,113,220],"language":[13],"and":[14,43,77,82,88,124,160,173,198,222],"reconstructing":[15],"images":[16],"from":[17,71],"Functional":[18],"Magnetic":[19],"Resonance":[20],"Imaging":[21],"(fMRI)":[22],"has":[23],"been":[24],"improved.":[25],"Nevertheless,":[26],"accurate":[28],"representation":[29,61,70],"brain":[31,60,69],"activity":[32],"remains":[33],"highly":[34],"challenging,":[35],"primarily":[36],"due":[37],"to":[38,67,149,182],"limited":[40],"paired":[41],"samples":[42],"low":[45],"signal-to-noise":[46],"ratios":[47],"fMRI.":[49],"To":[50,127],"tackle":[51],"these":[52],"challenges,":[53],"we":[54],"introduce":[55],"Cogformer,":[56],"a":[57,79,95,108,150,178],"unified":[58],"multi-scale":[59,72],"method.":[62],"It":[63],"is":[64],"first":[66],"learn":[68],"fMRI":[73],"activities":[74],"via":[75],"self-attention,":[76],"integrate":[78],"synchronized":[80],"dynamic":[83],"decoupling":[84],"strategy":[85],"for":[86,195],"structural":[87],"semantic":[89,193],"features":[90],"through":[91],"cross-attention.":[92],"We":[93],"conduct":[94],"systematic":[96],"evaluation":[97,206],"Cogformer":[99,144,176,208],"on":[100],"large-scale":[102],"Natural":[103],"Scenes":[104],"Dataset":[105],"(NSD)":[106],"across":[107],"broad":[109],"range":[110,151],"visual":[112,199],"tasks,":[114],"including":[115],"category":[116,156],"classification,":[117,119,157,159],"multi-label":[118,158],"image":[120,122,125,161,171,174,187,202],"retrieval,":[121],"captioning,":[123],"reconstruction.":[126,203],"best":[129],"our":[131],"knowledge,":[132],"this":[133],"represents":[134],"most":[136],"extensive":[137],"task":[138],"coverage":[139],"reported":[140],"in":[141,155,165,201],"related":[142],"research.":[143],"achieves":[145],"superior":[146],"compared":[148],"transformer-based":[153],"baselines":[154],"retrieval":[162],"tasks.":[163],"Moreover,":[164],"more":[167],"challenging":[168],"tasks":[169],"captioning":[172],"reconstruction,":[175],"leverages":[177],"prior":[179],"diffusion":[180],"module":[181],"enhance":[183],"alignment":[185],"with":[186],"semantics.":[188],"This":[189],"further":[190],"improves":[191],"consistency":[194],"caption":[196],"generation":[197],"fidelity":[200],"Across":[204],"multiple":[205],"metrics,":[207],"demonstrates":[209],"competitive":[210],"against":[212],"existing":[213],"state-of-the-art":[214],"(SOTA)":[215],"methods,":[216],"highlighting":[217],"its":[218],"strong":[219],"capabilities":[221],"generalization":[223],"potential.":[224]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-02-25T00:00:00"}