{"id":"https://openalex.org/W7160308018","doi":"https://doi.org/10.1109/wacv61042.2026.00122","title":"mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval","display_name":"mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160308018","doi":"https://doi.org/10.1109/wacv61042.2026.00122"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00122","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/A5065924645","display_name":"Kyeong Seon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Kyeong Seon Kim","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043953973","display_name":"Seong-Eun Baek","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Baek Seong-Eun","raw_affiliation_strings":["POSTECH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135308921","display_name":"Lee Jung-Mok","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lee Jung-Mok","raw_affiliation_strings":["POSTECH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.6816,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9898549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1191","last_page":"1200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4036000072956085,"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":0.4036000072956085,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.19990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.1703999936580658,"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/image-retrieval","display_name":"Image retrieval","score":0.4650999903678894},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38589999079704285},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.33180001378059387},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31139999628067017},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.3098999857902527},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3057999908924103},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2939999997615814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642300009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5974000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5508999824523926},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4650999903678894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.3098999857902527},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C59662460","wikidata":"https://www.wikidata.org/wiki/Q170130","display_name":"Vector graphics","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.2750000059604645},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00122","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":26,"referenced_works":["https://openalex.org/W2966583823","https://openalex.org/W2970641574","https://openalex.org/W2988217457","https://openalex.org/W3156636935","https://openalex.org/W3194782062","https://openalex.org/W4224313754","https://openalex.org/W4385573170","https://openalex.org/W4386072256","https://openalex.org/W4386076124","https://openalex.org/W4386576685","https://openalex.org/W4390873312","https://openalex.org/W4401248343","https://openalex.org/W4402671846","https://openalex.org/W4402754147","https://openalex.org/W4404782013","https://openalex.org/W4407466877","https://openalex.org/W4409263378","https://openalex.org/W4411113421","https://openalex.org/W4413144680","https://openalex.org/W4413147425","https://openalex.org/W4415539870","https://openalex.org/W4415708671","https://openalex.org/W4416034873","https://openalex.org/W7160154847","https://openalex.org/W7160271719","https://openalex.org/W7160334508"],"related_works":[],"abstract_inverted_index":{"Scalable":[0],"Vector":[1],"Graphics":[2],"(SVGs)":[3],"function":[4],"both":[5],"as":[6,10,133,197],"visual":[7,48,154],"images":[8],"and":[9,17,25,73,90,148,162,180,188],"structured":[11,50],"code":[12,75],"that":[13,60,144,182],"encode":[14],"rich":[15],"geometric":[16,161],"layout":[18],"information,":[19],"yet":[20],"most":[21],"methods":[22,37],"rasterize":[23],"them":[24],"discard":[26],"this":[27],"symbolic":[28],"organization.":[29],"At":[30],"the":[31,83,95,118,157,175],"same":[32],"time,":[33],"recent":[34],"sentence":[35],"embedding":[36,58,79],"produce":[38],"strong":[39],"text":[40],"representations":[41],"but":[42],"do":[43],"not":[44],"naturally":[45],"extend":[46],"to":[47,68,120,201],"or":[49,101],"modalities.":[51],"We":[52,81],"propose":[53],"a":[54,62,126,134,170],"training-free,":[55],"instruction-guided":[56],"multimodal":[57,123,190,206],"framework":[59],"uses":[61],"Multimodal":[63,111],"Large":[64],"Language":[65],"Model":[66],"(MLLM)":[67],"map":[69],"text,":[70],"raster":[71],"images,":[72],"SVG":[74,92,141,151],"into":[76,125],"an":[77,198],"aligned":[78],"space.":[80],"control":[82,196],"direction":[84],"of":[85],"embeddings":[86,185],"through":[87,153],"modality-specific":[88],"instructions":[89],"structural":[91],"cues,":[93],"eliminating":[94],"need":[96],"for":[97,204],"learned":[98],"projection":[99],"heads":[100],"contrastive":[102],"training.":[103],"Our":[104],"method":[105],"has":[106],"two":[107],"key":[108],"components:":[109],"(1)":[110],"Explicit":[112],"One-word":[113],"Limitation":[114],"(mEOL),":[115],"which":[116],"instructs":[117],"MLLM":[119],"summarize":[121],"any":[122],"input":[124],"single":[127],"token":[128],"whose":[129],"hidden":[130,165],"state":[131],"serves":[132],"compact":[135],"semantic":[136,140],"embedding.":[137],"(2)":[138],"A":[139],"rewriting":[142],"module":[143],"assigns":[145],"meaningful":[146],"identifiers":[147],"simplifies":[149],"nested":[150],"elements":[152],"reasoning":[155],"over":[156],"rendered":[158],"image,":[159],"exposing":[160],"relational":[163],"cues":[164],"in":[166],"raw":[167],"code.":[168],"Using":[169],"repurposed":[171],"VGBench,":[172],"we":[173],"build":[174],"first":[176],"text-to-SVG":[177],"retrieval":[178],"benchmark":[179],"show":[181],"our":[183],"training-free":[184],"outperform":[186],"encoder-based":[187],"training-based":[189],"baselines.":[191],"These":[192],"results":[193],"highlight":[194],"prompt-level":[195],"effective":[199],"alternative":[200],"parameter-level":[202],"training":[203],"structure-aware":[205],"retrieval.":[207],"Project":[208],"page:":[209],"https://scene-the-ella.github.io/meol/":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}