{"id":"https://openalex.org/W7154602016","doi":"https://doi.org/10.48448/sjyz-k615","title":"Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging","display_name":"Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging","publication_year":2025,"publication_date":"2025-06-18","ids":{"openalex":"https://openalex.org/W7154602016","doi":"https://doi.org/10.48448/sjyz-k615"},"language":"en","primary_location":{"id":"doi:10.48448/sjyz-k615","doi":"https://doi.org/10.48448/sjyz-k615","is_oa":true,"landing_page_url":"https://doi.org/10.48448/sjyz-k615","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/sjyz-k615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133793129","display_name":"Cognitive Science Society 2025","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cognitive Science Society 2025","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125734182","display_name":"Shuo Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Shuo","raw_affiliation_strings":["College of  Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of  Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125755255","display_name":"Piji Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Piji","raw_affiliation_strings":["College of  Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of  Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133744275","display_name":"Renzhi Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Renzhi","raw_affiliation_strings":["College of  Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of  Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073301735","display_name":"Xuyun Wen","orcid":"https://orcid.org/0000-0003-2230-8658","observed_orcids":["https://orcid.org/0000-0003-2230-8658"]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Xuyun","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059419447","display_name":"Runze Xia","orcid":"https://orcid.org/0000-0001-7656-6594","observed_orcids":["https://orcid.org/0000-0001-7656-6594"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Runze","raw_affiliation_strings":["College of  Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of  Artificial Intelligence","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111096791","display_name":"Congchi Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin, Congchi","raw_affiliation_strings":["Nanjing University Of Aeronautics And Astronautics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University Of Aeronautics And Astronautics","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3109999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3109999895095825,"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":0.1729000061750412,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.11739999800920486,"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/fmri-decoding","display_name":"fMRI decoding","score":0.7699999809265137},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7760000228881836},{"id":"https://openalex.org/keywords/caption-generation","display_name":"caption generation","score":0.7540000081062317},{"id":"https://openalex.org/keywords/semantic-consistency","display_name":"semantic consistency","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728000283241272},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5521000027656555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5120000243186951},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/sjyz-k615","doi":"https://doi.org/10.48448/sjyz-k615","is_oa":true,"landing_page_url":"https://doi.org/10.48448/sjyz-k615","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/sjyz-k615","doi":"https://doi.org/10.48448/sjyz-k615","is_oa":true,"landing_page_url":"https://doi.org/10.48448/sjyz-k615","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.4043000042438507,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7163165301","https://openalex.org/W4407292980","https://openalex.org/W4387969592","https://openalex.org/W7133226256","https://openalex.org/W4403792182","https://openalex.org/W7030322422","https://openalex.org/W7126122751","https://openalex.org/W4386995747","https://openalex.org/W4396638748","https://openalex.org/W7213411273"],"abstract_inverted_index":{"Brain-to-Image":[0,42,132],"reconstruction":[1,43,127],"aims":[2],"to":[3,28,51,79,105,129],"recover":[4],"visual":[5,16,84],"stimuli":[6,17,85],"perceived":[7],"by":[8],"humans":[9],"from":[10,115],"brain":[11],"activity.":[12],"However,":[13],"the":[14,71,107],"reconstructed":[15],"often":[18],"missing":[19],"details":[20],"and":[21,66,86,101],"semantic":[22,30,99,103],"inconsistencies,":[23],"which":[24,45],"may":[25],"be":[26,123],"attributed":[27],"insufficient":[29],"information.":[31],"To":[32],"address":[33],"this":[34],"issue,":[35],"we":[36,74],"propose":[37,92],"an":[38],"approach":[39],"named":[40],"Fine-grained":[41],"(FgB2I),":[44],"employs":[46],"fine-grained":[47,63,81,112,119,131],"text":[48,64,113,120],"as":[49],"bridge":[50],"improve":[52],"image":[53],"reconstruction.":[54,69,133],"FgB2I":[55],"comprises":[56],"three":[57,93],"key":[58],"stages:":[59],"detail":[60],"enhancement,":[61],"decoding":[62,111],"descriptions,":[65],"text-bridged":[67],"brain-to-image":[68],"In":[70],"detail-enhancement":[72],"stage,":[73],"leverage":[75],"large":[76],"vision\u2013language":[77],"models":[78],"generate":[80],"captions":[82],"for":[83],"experimentally":[87],"validate":[88],"its":[89],"importance.":[90],"We":[91],"reward":[94],"metrics":[95],"(object":[96],"accuracy,":[97],"text-image":[98],"similarity,":[100],"image-image":[102],"similarity)":[104],"guide":[106],"language":[108],"model":[109],"in":[110],"descriptions":[114,121],"fMRI":[116],"signals.":[117],"The":[118],"can":[122],"integrated":[124],"into":[125],"existing":[126],"methods":[128],"achieve":[130]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-04-17T00:00:00"}