{"id":"https://openalex.org/W4417283085","doi":"https://doi.org/10.1109/iccv51701.2025.01707","title":"Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction","display_name":"Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417283085","doi":"https://doi.org/10.1109/iccv51701.2025.01707"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.11167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043280371","display_name":"Haonan Wang","orcid":"https://orcid.org/0000-0002-8892-6232"},"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":true,"raw_author_name":"Haonan Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763743","display_name":"Qixiang Zhang","orcid":"https://orcid.org/0000-0003-0315-3400"},"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":"Qixiang Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046621613","display_name":"Lehan Wang","orcid":"https://orcid.org/0009-0000-4707-6828"},"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":"Lehan Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuanqi Huang","orcid":null},"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":"Xuanqi Huang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427643","display_name":"Xiaomeng Li","orcid":"https://orcid.org/0000-0003-1105-8083"},"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":"Xiaomeng Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043280371"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37742218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18367","last_page":"18376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.5827999711036682,"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":0.5827999711036682,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.07329999655485153,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.061799999326467514,"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/interpretability","display_name":"Interpretability","score":0.7127000093460083},{"id":"https://openalex.org/keywords/visual-cortex","display_name":"Visual cortex","score":0.6065999865531921},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4934999942779541},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.42160001397132874},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3953000009059906},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.38499999046325684},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.37959998846054077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37369999289512634},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.36480000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.738099992275238},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7127000093460083},{"id":"https://openalex.org/C2779345533","wikidata":"https://www.wikidata.org/wiki/Q75785","display_name":"Visual cortex","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.492000013589859},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.42160001397132874},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.37959998846054077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36480000615119934},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2779226451","wikidata":"https://www.wikidata.org/wiki/Q903809","display_name":"Functional magnetic resonance imaging","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C152478114","wikidata":"https://www.wikidata.org/wiki/Q660910","display_name":"Neurophysiology","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C2776196576","wikidata":"https://www.wikidata.org/wiki/Q196113","display_name":"Camouflage","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.11167","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11167","pdf_url":"https://arxiv.org/pdf/2503.11167","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},{"id":"doi:10.48550/arxiv.2503.11167","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.11167","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.11167","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11167","pdf_url":"https://arxiv.org/pdf/2503.11167","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7997540062","display_name":null,"funder_award_id":"N_HKUST654/24","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":{"Decoding":[0],"visual":[1,55,64,94,153],"stimuli":[2],"from":[3],"neural":[4],"activity":[5],"is":[6],"essential":[7],"for":[8,29,115,158],"understanding":[9],"the":[10,27,59,63,93,99,107,123,152],"human":[11],"brain.":[12],"While":[13],"fMRI":[14,51],"methods":[15],"have":[16,40],"successfully":[17],"reconstructed":[18],"static":[19],"images,":[20],"fMRI-to-video":[21],"reconstruction":[22],"faces":[23],"challenges":[24],"due":[25],"to":[26,48,101,121],"need":[28],"capturing":[30],"spatiotemporal":[31],"dynamics":[32],"like":[33],"motion":[34],"and":[35,43,86,140,161,165],"scene":[36,84],"transitions.":[37],"Recent":[38],"approaches":[39],"improved":[41],"semantic":[42],"perceptual":[44],"alignment":[45],"but":[46],"struggle":[47],"integrate":[49],"coarse":[50],"data":[52],"with":[53,151],"detailed":[54],"features.":[56],"Inspired":[57],"by":[58],"hierarchical":[60],"organization":[61],"of":[62],"system,":[65],"we":[66],"propose":[67],"NEURONS,":[68],"a":[69,116,147],"novel":[70],"framework":[71],"that":[72,128],"decouples":[73],"learning":[74],"into":[75],"four":[76],"correlated":[77],"sub-tasks:":[78],"key":[79],"object":[80],"segmentation,":[81],"concept":[82],"recognition,":[83],"description,":[85],"blurry":[87],"video":[88,104,137],"reconstruction.":[89],"This":[90],"approach":[91],"simulates":[92],"cortex's":[95],"functional":[96,149],"specialization,":[97],"allowing":[98],"model":[100,120,166],"capture":[102],"diverse":[103],"content.":[105],"In":[106],"inference":[108],"stage,":[109],"NEURONS":[110,129,145],"generates":[111],"robust":[112],"conditioning":[113],"signals":[114],"pre-trained":[117],"text-to-video":[118],"diffusion":[119],"reconstruct":[122],"videos.":[124],"Extensive":[125],"experiments":[126],"demonstrate":[127],"outperforms":[130],"state-of-the-art":[131],"baselines,":[132],"achieving":[133],"solid":[134],"improvements":[135],"in":[136],"consistency":[138],"(26.6%)":[139],"semantic-level":[141],"accuracy":[142],"(19.1%).":[143],"Notably,":[144],"shows":[146],"strong":[148],"correlation":[150],"cortex,":[154],"highlighting":[155],"its":[156],"potential":[157],"brain-computer":[159],"interfaces":[160],"clinical":[162],"applications.":[163],"Code":[164],"weights":[167],"are":[168],"available":[169],"at:":[170],"https://github.com/xmed-lab/NEURONS.":[171]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}