{"id":"https://openalex.org/W7164828802","doi":"https://doi.org/10.1145/3805622.3810885","title":"NeuroAlign: Dynamic Dual-Stream Alignment of Perception and Cognition for Zero-Shot Brain-Image Retrieval","display_name":"NeuroAlign: Dynamic Dual-Stream Alignment of Perception and Cognition for Zero-Shot Brain-Image Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164828802","doi":"https://doi.org/10.1145/3805622.3810885"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810885","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810885","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052303311","display_name":"\u514b\u4e00 \u661f","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Ke","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China; Shenzhen University of Advanced Technology, Shenzhen, China and Shenzhen Institute of Advanced Technology\uff0cChinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-8265-5152","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China; Shenzhen University of Advanced Technology, Shenzhen, China and Shenzhen Institute of Advanced Technology\uff0cChinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107191592","display_name":"Dong Liang","orcid":"https://orcid.org/0000-0003-1358-9777"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology\uff0cChinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1358-9777","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology\uff0cChinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101431758","display_name":"Kun Shang","orcid":"https://orcid.org/0000-0003-3826-1102"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Shang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology\uff0cChinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3826-1102","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology\uff0cChinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.9352631,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.5130000114440918,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.5130000114440918,"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":0.16249999403953552,"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/T11094","display_name":"Face Recognition and Perception","score":0.08410000056028366,"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/salient","display_name":"Salient","score":0.652400016784668},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5995000004768372},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5605000257492065},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.48249998688697815},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4523000121116638},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.43050000071525574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4269999861717224},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4058000147342682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888000011444092},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.652400016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322000026702881},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5995000004768372},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.43050000071525574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3734000027179718},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3555999994277954},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810885","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810885","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W1971017968","https://openalex.org/W1973292737","https://openalex.org/W2003370853","https://openalex.org/W2019370496","https://openalex.org/W2044758367","https://openalex.org/W2054802006","https://openalex.org/W2091845343","https://openalex.org/W2102022426","https://openalex.org/W2114977008","https://openalex.org/W2117731089","https://openalex.org/W2125311180","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2299862820","https://openalex.org/W2344975321","https://openalex.org/W2412480261","https://openalex.org/W2949512190","https://openalex.org/W2951574693","https://openalex.org/W2963855931","https://openalex.org/W3028543194","https://openalex.org/W3210923133","https://openalex.org/W4221099735","https://openalex.org/W4309409002","https://openalex.org/W4312629998","https://openalex.org/W4322494696","https://openalex.org/W4327663834","https://openalex.org/W4361855028","https://openalex.org/W4381487463","https://openalex.org/W4386076190","https://openalex.org/W4386295635","https://openalex.org/W4396731376","https://openalex.org/W4402727764","https://openalex.org/W4408766978","https://openalex.org/W4410738225","https://openalex.org/W4413146099","https://openalex.org/W4413146477","https://openalex.org/W4415708655","https://openalex.org/W4415795888","https://openalex.org/W7131160845","https://openalex.org/W7133217898","https://openalex.org/W7133219845","https://openalex.org/W7133226256"],"related_works":[],"abstract_inverted_index":{"Visual":[0,58,114],"retrieval":[1],"from":[2],"brain":[3,32],"signals":[4,19,33],"is":[5],"a":[6,21,99],"key":[7],"challenge":[8],"in":[9,72,176],"Brain-Computer":[10],"Interfaces":[11],"(BCIs).":[12],"Existing":[13],"methods":[14],"directly":[15],"map":[16],"noisy":[17,83],"neural":[18,30],"into":[20],"unified":[22],"feature":[23],"space,":[24],"ignoring":[25],"the":[26,37,76,137],"dual-stream":[27,101],"mechanism":[28],"of":[29,39],"decoding:":[31],"are":[34,134],"generated":[35],"through":[36],"interaction":[38],"bottom-up":[40],"perception":[41],"(processing":[42],"visual":[43],"saliency)":[44],"and":[45,90,106,122,157,170,178],"top-down":[46,129],"cognition":[47],"(interpreting":[48],"semantic":[49,65,77,91,130,151],"concepts":[50],"based":[51],"on":[52,155],"prior":[53],"knowledge).":[54],"In":[55],"Rapid":[56],"Serial":[57],"Presentation":[59],"paradigm,":[60],"standard":[61],"encoders":[62],"prioritize":[63],"high-level":[64],"abstractions":[66],"over":[67],"actual":[68],"salient":[69,120],"features":[70,121],"encoded":[71],"human":[73],"vision,":[74],"lacking":[75],"guidance":[78],"needed":[79],"to":[80,118,127,150],"stabilize":[81],"inherently":[82],"signals.":[84],"This":[85],"mismatch":[86],"causes":[87],"perceptual":[88],"misalignment":[89],"inconsistency.":[92],"To":[93],"resolve":[94],"this,":[95],"we":[96,112],"propose":[97],"NeuroAlign,":[98],"dynamic":[100],"framework":[102],"that":[103,161],"explicitly":[104],"separates":[105],"coordinates":[107],"these":[108],"two":[109],"processes.":[110],"Specifically,":[111],"utilize":[113],"Saliency":[115],"Extraction":[116],"(VSE)":[117],"capture":[119],"Semantic":[123],"Guidance":[124],"Alignment":[125],"(SGA)":[126],"provide":[128],"guidance.":[131],"These":[132],"processes":[133],"coordinated":[135],"by":[136],"Dynamic":[138],"Loss":[139],"Adjustment":[140],"(DLA)":[141],"mechanism,":[142],"which":[143],"adaptively":[144],"prioritizes":[145],"structural":[146],"alignment":[147],"before":[148],"shifting":[149],"refinement.":[152],"Extensive":[153],"experiments":[154],"THINGS-EEG2":[156],"THINGS-MEG":[158],"datasets":[159],"demonstrate":[160],"NeuroAlign":[162],"achieves":[163],"SOTA":[164],"performance,":[165],"reaching":[166],"48.1%":[167],"(\\(\\uparrow":[168,172],"2.4\\%\\))":[169],"14.5%":[171],"2.6\\%\\))":[173],"Top-1":[174],"accuracy":[175],"intra-":[177],"inter-subject":[179],"retrieval,":[180],"respectively.":[181]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}