{"id":"https://openalex.org/W7160258866","doi":"https://doi.org/10.1109/wacv61042.2026.00227","title":"CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning","display_name":"CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160258866","doi":"https://doi.org/10.1109/wacv61042.2026.00227"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5101631518","display_name":"Zeyuan Chen","orcid":"https://orcid.org/0000-0002-2237-1633"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyuan Chen","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368903","display_name":"Xiang Zhang","orcid":"https://orcid.org/0000-0002-9726-0858"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Zhang","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135246723","display_name":"Haiyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125595009","display_name":"Jianwen Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086225","display_name":"Lambda Instruments (United States)","ror":"https://ror.org/00thhxf09","country_code":"US","type":"company","lineage":["https://openalex.org/I4210086225"]},{"id":"https://openalex.org/I4210160406","display_name":"Lambda Science (United States)","ror":"https://ror.org/04wae4s50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160406"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianwen Xie","raw_affiliation_strings":["Lambda, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lambda, Inc","institution_ids":["https://openalex.org/I4210086225","https://openalex.org/I4210160406"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001760915","display_name":"Zhuowen Tu","orcid":"https://orcid.org/0000-0002-1900-2124"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuowen Tu","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"2295","last_page":"2305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.7649999856948853,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.7649999856948853,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.061500001698732376,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.053599998354911804,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.31769999861717224},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27079999446868896},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.2581000030040741},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.25360000133514404},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24199999868869781}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.599399983882904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587000250816345},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2434999942779541},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24199999868869781},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.23149999976158142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.227400004863739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1987648924","https://openalex.org/W2097696373","https://openalex.org/W2101105183","https://openalex.org/W2336416123","https://openalex.org/W2594519801","https://openalex.org/W2889469641","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2964070326","https://openalex.org/W2966683369","https://openalex.org/W2968296999","https://openalex.org/W3095319910","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3129238537","https://openalex.org/W3168640669","https://openalex.org/W3182910454","https://openalex.org/W3198001539","https://openalex.org/W3203949114","https://openalex.org/W4221167937","https://openalex.org/W4226376247","https://openalex.org/W4311166797","https://openalex.org/W4312270234","https://openalex.org/W4312385518","https://openalex.org/W4312650216","https://openalex.org/W4312818263","https://openalex.org/W4312852845","https://openalex.org/W4313162371","https://openalex.org/W4385804899","https://openalex.org/W4386066792","https://openalex.org/W4386075583","https://openalex.org/W4386076628","https://openalex.org/W4389519030","https://openalex.org/W4390872495","https://openalex.org/W4390872898","https://openalex.org/W4390873312","https://openalex.org/W4390874439","https://openalex.org/W4402716059","https://openalex.org/W4402716423","https://openalex.org/W4402727108","https://openalex.org/W4402727142","https://openalex.org/W4402961670","https://openalex.org/W4403778769","https://openalex.org/W4413145659","https://openalex.org/W4413146466","https://openalex.org/W4413147101","https://openalex.org/W4413787297","https://openalex.org/W4414051111","https://openalex.org/W7133193597","https://openalex.org/W7133250029","https://openalex.org/W7160046300","https://openalex.org/W7160054212","https://openalex.org/W7160158679"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,7,84,140],"central-peripheral":[3],"vision-inspired":[4],"framework":[5],"(CVP),":[6],"simple":[8],"yet":[9],"effective":[10],"multimodal":[11],"model":[12],"for":[13],"spatial":[14,62,116],"reasoning":[15,63],"that":[16,95,110,134],"draws":[17],"inspiration":[18],"from":[19],"the":[20,67,97],"two":[21,80],"types":[22],"of":[23,69,128,142],"human":[24],"visual":[25],"fields":[26],"\u2013":[27],"central":[28,93],"vision":[29],"and":[30,48,103,115],"peripheral":[31,108],"vision.":[32],"Existing":[33],"approaches":[34],"primarily":[35],"rely":[36],"on":[37],"unstructured":[38],"representations,":[39],"such":[40],"as":[41],"point":[42],"clouds,":[43],"voxels,":[44],"or":[45],"patch":[46],"features,":[47],"inject":[49],"scene":[50,113,144],"context":[51,114],"implicitly":[52],"via":[53],"coordinate":[54],"embeddings.":[55],"However,":[56],"this":[57,76],"often":[58],"results":[59],"in":[60,121],"limited":[61],"capabilities":[64],"due":[65],"to":[66,92,107,123],"lack":[68],"explicit,":[70],"high-level":[71],"structural":[72],"understanding.":[73],"To":[74],"address":[75],"limitation,":[77],"we":[78],"introduce":[79],"complementary":[81],"components":[82,119],"into":[83],"Large":[85],"Multimodal":[86],"Model-based":[87],"architecture:":[88],"target-affinity":[89],"token,":[90],"analogous":[91],"vision,":[94,109],"guides":[96],"model\u2019s":[98],"attention":[99],"toward":[100],"query-relevant":[101],"objects;":[102],"allocentric":[104],"grid,":[105],"akin":[106],"captures":[111],"global":[112],"arrangements.":[117],"These":[118],"work":[120],"tandem":[122],"enable":[124],"structured,":[125],"context-aware":[126],"understanding":[127,145],"complex":[129],"3D":[130,143],"environments.":[131],"Experiments":[132],"show":[133],"CVP":[135],"achieves":[136],"state-of-the-art":[137],"performance":[138],"across":[139],"range":[141],"benchmarks.":[146]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-06T00:00:00"}