{"id":"https://openalex.org/W7214984137","doi":"https://doi.org/10.48550/arxiv.2609.36366","title":"Cross-attention encoding models reveal dynamic spatiotemporal routing across human higher visual cortex","display_name":"Cross-attention encoding models reveal dynamic spatiotemporal routing across human higher visual cortex","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214984137","doi":"https://doi.org/10.48550/arxiv.2609.36366"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36366","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36366","pdf_url":"https://arxiv.org/pdf/2609.36366","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.36366","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119547668","display_name":"Iishaan Inabathini","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Inabathini, Iishaan","raw_affiliation_strings":["Carnegie Mellon University Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070257872","display_name":"Margaret M. Henderson","orcid":"https://orcid.org/0000-0001-9375-6680","observed_orcids":["https://orcid.org/0000-0001-9375-6680"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henderson, Margaret M.","raw_affiliation_strings":["Carnegie Mellon University Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10427","display_name":"Visual perception and processing mechanisms","score":0.9570000171661377,"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/T10427","display_name":"Visual perception and processing mechanisms","score":0.9570000171661377,"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":0.023499999195337296,"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":0.004900000058114529,"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/spatiotemporal-attention","display_name":"spatio-temporal attention","score":0.8389999866485596},{"id":"https://openalex.org/keywords/naturalistic-video","display_name":"naturalistic video","score":0.6940000057220459},{"id":"https://openalex.org/keywords/fmri-decoding","display_name":"fMRI decoding","score":0.7540000081062317},{"id":"https://openalex.org/keywords/motion-perception","display_name":"motion perception","score":0.6899999976158142},{"id":"https://openalex.org/keywords/attention-maps","display_name":"attention maps","score":0.6179999709129333},{"id":"https://openalex.org/keywords/face-selective-cortex","display_name":"face-selective cortex","score":0.621999979019165},{"id":"https://openalex.org/keywords/scene-selective-cortex","display_name":"scene-selective cortex","score":0.9769999980926514},{"id":"https://openalex.org/keywords/dynamic-visual-perception","display_name":"dynamic visual perception","score":0.42800000309944153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7139999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6128000020980835},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.46549999713897705},{"id":"https://openalex.org/C2779345533","wikidata":"https://www.wikidata.org/wiki/Q75785","display_name":"Visual cortex","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3781999945640564},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C24856439","wikidata":"https://www.wikidata.org/wiki/Q352483","display_name":"Adaptive routing","level":5,"score":0.3549000024795532},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C2779226451","wikidata":"https://www.wikidata.org/wiki/Q903809","display_name":"Functional magnetic resonance imaging","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C58693492","wikidata":"https://www.wikidata.org/wiki/Q551875","display_name":"Neuroimaging","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.26420000195503235}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36366","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36366","pdf_url":"https://arxiv.org/pdf/2609.36366","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.36366","doi":"https://doi.org/10.48550/arxiv.2609.36366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36366","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.36366","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36366","pdf_url":"https://arxiv.org/pdf/2609.36366","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214984137.pdf","grobid_xml":"https://content.openalex.org/works/W7214984137.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1619178479","https://openalex.org/W1837967720","https://openalex.org/W1974750895","https://openalex.org/W1988013646","https://openalex.org/W1990037101","https://openalex.org/W1992570774","https://openalex.org/W2003386556","https://openalex.org/W2007997142","https://openalex.org/W2062906394","https://openalex.org/W2063951486","https://openalex.org/W2077081743","https://openalex.org/W2082627290","https://openalex.org/W2108358917","https://openalex.org/W2110065044","https://openalex.org/W2123341385","https://openalex.org/W2126309556","https://openalex.org/W2134927309","https://openalex.org/W2149166988","https://openalex.org/W2274405424","https://openalex.org/W2499800833","https://openalex.org/W2796001514","https://openalex.org/W2950747681","https://openalex.org/W2951583631","https://openalex.org/W2951617899","https://openalex.org/W2952182547","https://openalex.org/W3086360455","https://openalex.org/W3094502228","https://openalex.org/W3201124393","https://openalex.org/W4200613736","https://openalex.org/W4292767352","https://openalex.org/W4293044477","https://openalex.org/W4310113667","https://openalex.org/W4367596502","https://openalex.org/W4378782804","https://openalex.org/W4385802664","https://openalex.org/W4388141896","https://openalex.org/W4388625659","https://openalex.org/W4396787160","https://openalex.org/W4400958216","https://openalex.org/W4412660436","https://openalex.org/W4415981554","https://openalex.org/W4417091809","https://openalex.org/W4417095222","https://openalex.org/W4417261359","https://openalex.org/W6910554155","https://openalex.org/W6929123089","https://openalex.org/W7154093649","https://openalex.org/W7167209598"],"related_works":["https://openalex.org/W4415623085","https://openalex.org/W2990630012","https://openalex.org/W3100769144","https://openalex.org/W2110729445","https://openalex.org/W2507706845","https://openalex.org/W4414312528","https://openalex.org/W2054968556","https://openalex.org/W2313180542","https://openalex.org/W4392019740","https://openalex.org/W2108357538"],"abstract_inverted_index":{"Understanding":[0],"how":[1,222],"the":[2,42,58],"brain":[3,142],"parses":[4],"actions":[5],"and":[6,65,111,130,134,155,180],"events":[7],"from":[8,54,102,194],"time-varying":[9],"natural":[10,39],"inputs":[11],"is":[12,225],"a":[13,103,216],"central":[14],"challenge":[15],"in":[16,153,196,206],"neuroscience.":[17],"Recent":[18,68],"work":[19,214],"has":[20],"used":[21],"deep":[22],"neural":[23,66,186],"network":[24],"(DNN)":[25],"models":[26,32,47,71],"to":[27,37,92,98,116,119,144,184],"build":[28],"stimulus-computable":[29],"fMRI":[30,117],"encoding":[31,46,70],"that":[33,136,172,191],"predict":[34,48],"single-voxel":[35],"responses":[36,49,118,143],"complex":[38],"videos.":[40],"However,":[41],"majority":[43],"of":[44,82,141],"video-computable":[45],"using":[50,95],"simple":[51],"linear":[52],"mappings":[53],"model":[55,106,115],"tokens,":[56],"overlooking":[57],"spatiotemporal":[59,126],"structure":[60],"shared":[61],"by":[62,228],"video":[63,105,121],"representations":[64],"responses.":[67],"cross-attention":[69,97],"address":[72],"this":[73,90,114,213],"limitation":[74],"for":[75,220],"static":[76],"images,":[77],"enabling":[78],"flexible":[79],"stimulus-dependent":[80],"weighting":[81],"image":[83],"content":[84,205],"across":[85,108,147],"space.":[86],"Here,":[87],"we":[88],"extend":[89],"framework":[91,219],"naturalistic":[93],"video,":[94],"per-parcel":[96],"dynamically":[99,173],"route":[100],"features":[101],"self-supervised":[104],"(V-JEPA-2)":[107],"both":[109],"space":[110],"time,":[112],"fitting":[113],"short":[120],"clips.":[122],"We":[123,188],"compare":[124],"joint":[125,137],"attention":[127,170,192],"with":[128,160,208],"factorized":[129],"selectively":[131],"constrained":[132],"alternatives,":[133],"find":[135],"routing":[138],"improves":[139],"predictions":[140],"held-out":[145],"videos":[146],"higher":[148],"visual":[149,157,223,233],"regions,":[150],"most":[151],"consistently":[152],"lateral":[154],"dorsal":[156],"areas":[158],"associated":[159],"dynamic":[161,232],"motion":[162],"perception.":[163,234],"Moreover,":[164],"our":[165],"method":[166],"provides":[167,215],"interpretable,":[168],"stimulus-specific":[169],"maps":[171,193],"follow":[174],"moving":[175],"objects,":[176],"revealing":[177],"which":[178],"locations":[179],"temporal":[181],"moments":[182],"contribute":[183],"each":[185],"response.":[187],"further":[189],"show":[190],"parcels":[195],"different":[197],"category-selective":[198],"networks":[199],"(face-,":[200],"body-,":[201],"scene-selective)":[202],"differentially":[203],"weight":[204],"accordance":[207],"expected":[209],"semantic":[210],"selectivity.":[211],"Together,":[212],"new":[217],"computational":[218],"understanding":[221],"information":[224],"adaptively":[226],"weighted":[227],"cortical":[229],"populations":[230],"during":[231]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}