{"id":"https://openalex.org/W7125938654","doi":"https://doi.org/10.1109/tvcg.2025.3642641","title":"DKMap: Interactive Exploration of Vision-Language Alignment in Multimodal Embeddings via Dynamic Kernel Enhanced Projection","display_name":"DKMap: Interactive Exploration of Vision-Language Alignment in Multimodal Embeddings via Dynamic Kernel Enhanced Projection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125938654","doi":"https://doi.org/10.1109/tvcg.2025.3642641","pmid":"https://pubmed.ncbi.nlm.nih.gov/41605182"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2025.3642641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3642641","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5124122801","display_name":"Yilin Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilin Ye","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119174605","display_name":"Chenxi Ruan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenxi Ruan","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124052737","display_name":"Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["University of Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018428510","display_name":"Zikun Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zikun Deng","raw_affiliation_strings":["South China University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124093368","display_name":"Wei Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zeng","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.09403042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"1","first_page":"440","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.27320000529289246,"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":0.27320000529289246,"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/T11448","display_name":"Face recognition and analysis","score":0.163100004196167,"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/T10799","display_name":"Data Visualization and Analytics","score":0.0940999984741211,"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/kernel","display_name":"Kernel (algebra)","score":0.6539000272750854},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6284000277519226},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6227999925613403},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.5551999807357788},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4876999855041504},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.450300008058548},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.43050000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6651999950408936},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6539000272750854},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.5551999807357788},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.43050000071525574},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.39250001311302185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3643999993801117},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.3546000123023987},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C64073096","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Interactive visualization","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2025.3642641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3642641","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41605182","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41605182","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4023314675","display_name":null,"funder_award_id":"62172398","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8630915279","display_name":null,"funder_award_id":"62402184","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":55,"referenced_works":["https://openalex.org/W1625417290","https://openalex.org/W1861492603","https://openalex.org/W1893905004","https://openalex.org/W1908991523","https://openalex.org/W1974767305","https://openalex.org/W2020984122","https://openalex.org/W2030155517","https://openalex.org/W2030246490","https://openalex.org/W2031448663","https://openalex.org/W2105893525","https://openalex.org/W2128728535","https://openalex.org/W2129905273","https://openalex.org/W2610962473","https://openalex.org/W2611159092","https://openalex.org/W2807795618","https://openalex.org/W2899726877","https://openalex.org/W2958874938","https://openalex.org/W2969396217","https://openalex.org/W2986308225","https://openalex.org/W2995755016","https://openalex.org/W3084621683","https://openalex.org/W3121267967","https://openalex.org/W3153469116","https://openalex.org/W3204047821","https://openalex.org/W3212838649","https://openalex.org/W4226021591","https://openalex.org/W4312695444","https://openalex.org/W4312715377","https://openalex.org/W4312933868","https://openalex.org/W4385261545","https://openalex.org/W4385536252","https://openalex.org/W4385570204","https://openalex.org/W4385571801","https://openalex.org/W4385623782","https://openalex.org/W4386071707","https://openalex.org/W4387934915","https://openalex.org/W4387934929","https://openalex.org/W4388739142","https://openalex.org/W4390872671","https://openalex.org/W4390874002","https://openalex.org/W4396218624","https://openalex.org/W4396568157","https://openalex.org/W4396832813","https://openalex.org/W4396851234","https://openalex.org/W4402351708","https://openalex.org/W4402716201","https://openalex.org/W4402727496","https://openalex.org/W4402899001","https://openalex.org/W4403012121","https://openalex.org/W4403094611","https://openalex.org/W4404965790","https://openalex.org/W4409047052","https://openalex.org/W4410086685","https://openalex.org/W4413145264","https://openalex.org/W4415124086"],"related_works":[],"abstract_inverted_index":{"Examining":[0],"vision-language":[1],"alignment":[2,33,46,124,196],"in":[3,49,192],"multimodal":[4,35,87],"embeddings":[5,88],"is":[6,161],"crucial":[7],"for":[8,44,67,83,172,179],"various":[9],"tasks,":[10],"such":[11],"as":[12,163],"evaluating":[13,216],"generative":[14,217],"models":[15],"and":[16,64,100,135,175,202,219],"filtering":[17],"pretraining":[18,223],"data.":[19],"The":[20],"intricate":[21],"nature":[22],"of":[23,34,52,86,145,204],"high-dimensional":[24],"features":[25],"necessitates":[26],"dimensionality":[27,98],"reduction":[28,99],"(DR)":[29],"methods":[30,40],"to":[31,42,128],"explore":[32],"embeddings.":[36],"However,":[37],"existing":[38],"DR":[39,80,187],"fail":[41],"account":[43],"cross-modal":[45,123,195],"metrics,":[47],"resulting":[48],"severe":[50],"occlusion":[51],"points":[53],"with":[54,132,149,185,206],"divergent":[55],"metrics":[56],"clustered":[57],"together,":[58],"inaccurate":[59],"contour":[60,101,115],"maps":[61],"from":[62],"over-aggregation,":[63],"insufficient":[65],"support":[66],"multi-scale":[68,130],"exploration.":[69],"To":[70],"address":[71],"these":[72],"problems,":[73],"this":[74],"paper":[75],"introduces":[76],"DKMap,":[77],"a":[78,106,143,146,164,169,176,221],"novel":[79],"visualization":[81,166],"technique":[82],"interactive":[84,173],"exploration":[85,131,174],"through":[89],"Dynamic":[90],"Kernel":[91],"enhanced":[92,137],"projection.":[93],"First,":[94],"rather":[95],"than":[96],"performing":[97],"estimation":[102],"sequentially,":[103],"we":[104,140],"introduce":[105],"kernel":[107,155],"regression":[108],"supervised":[109],"t-SNE":[110],"that":[111],"directly":[112],"integrates":[113],"post-projection":[114],"mapping":[116,125,194],"into":[117],"the":[118],"projection":[119],"learning":[120],"process,":[121],"ensuring":[122,153],"accuracy.":[126],"Second,":[127],"enable":[129],"dynamic":[133],"zooming":[134],"progressively":[136],"local":[138],"detail,":[139],"integrate":[141],"validation-constrained":[142],"refinement":[144],"generalized":[147],"t-kernel":[148],"quad-tree-based":[150],"multi-resolution":[151],"technique,":[152],"reliable":[154],"parameter":[156],"tuning":[157],"without":[158],"overfitting.":[159],"DKMap":[160,205],"implemented":[162],"multi-platform":[165],"tool,":[167],"featuring":[168],"web-based":[170],"system":[171],"Python":[177],"package":[178],"computational":[180],"notebook":[181],"analysis.":[182],"Quantitative":[183],"comparisons":[184],"baseline":[186],"techniques":[188],"demonstrate":[189,200],"DKMap's":[190],"superiority":[191],"accurately":[193],"metrics.":[197],"We":[198],"further":[199],"generalizability":[201],"scalability":[203],"three":[207],"usage":[208],"scenarios,":[209],"including":[210],"visualizing":[211],"million-scale":[212],"text-to-image":[213],"corpus,":[214],"comparatively":[215],"models,":[218],"exploring":[220],"billion-scale":[222],"dataset.":[224]},"counts_by_year":[],"updated_date":"2026-02-09T05:59:30.833894","created_date":"2026-01-29T00:00:00"}