{"id":"https://openalex.org/W4399418505","doi":"https://doi.org/10.1145/3652583.3657624","title":"Extending CLIP for Text-to-font Retrieval","display_name":"Extending CLIP for Text-to-font Retrieval","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418505","doi":"https://doi.org/10.1145/3652583.3657624"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3657624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657624","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657624","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 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://dl.acm.org/doi/pdf/10.1145/3652583.3657624","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057809569","display_name":"Qinghua Sun","orcid":"https://orcid.org/0000-0002-8913-4608"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinghua Sun","raw_affiliation_strings":["School of Design, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Design, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101625242","display_name":"Jia Cui","orcid":"https://orcid.org/0000-0002-1631-0535"},"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":"Jia Cui","raw_affiliation_strings":["School of Design, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Design, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005095014","display_name":"Zhenyu Gu","orcid":"https://orcid.org/0000-0003-3921-5837"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Gu","raw_affiliation_strings":["School of Design, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Design, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057809569"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.7895,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71445654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1170","last_page":"1174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901000261306763,"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":0.9901000261306763,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.984499990940094,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/font","display_name":"Font","score":0.9663064479827881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8747743368148804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6545612215995789},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5741671919822693},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5270215272903442},{"id":"https://openalex.org/keywords/typeface","display_name":"Typeface","score":0.5029363036155701},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4908314645290375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47766241431236267},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47590336203575134},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43707695603370667},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4135088324546814},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41017335653305054}],"concepts":[{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.9663064479827881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8747743368148804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6545612215995789},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5741671919822693},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5270215272903442},{"id":"https://openalex.org/C80797182","wikidata":"https://www.wikidata.org/wiki/Q17451","display_name":"Typeface","level":2,"score":0.5029363036155701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4908314645290375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47766241431236267},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47590336203575134},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43707695603370667},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4135088324546814},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41017335653305054},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3657624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657624","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657624","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3657624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657624","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657624","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418505.pdf","grobid_xml":"https://content.openalex.org/works/W4399418505.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W41077023","https://openalex.org/W1981219830","https://openalex.org/W2612690371","https://openalex.org/W2791190294","https://openalex.org/W2896457183","https://openalex.org/W2898390142","https://openalex.org/W2898848610","https://openalex.org/W2952615055","https://openalex.org/W2964121744","https://openalex.org/W3034838543","https://openalex.org/W3092982061","https://openalex.org/W3094502228","https://openalex.org/W3181158454","https://openalex.org/W3209401134","https://openalex.org/W4225665828","https://openalex.org/W4378765444"],"related_works":["https://openalex.org/W2326324334","https://openalex.org/W2486962493","https://openalex.org/W2071402150","https://openalex.org/W2385728895","https://openalex.org/W4293093933","https://openalex.org/W3163268046","https://openalex.org/W2053735135","https://openalex.org/W2990826939","https://openalex.org/W2767847244","https://openalex.org/W4280558518"],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,43,58,61,83,120,128,139,154,158,169,177],"challenge":[4],"of":[5],"font":[6,71,90,130,135,147,173],"retrieval":[7,41,148],"in":[8,157],"design":[9,55,111],"by":[10,180],"proposing":[11],"a":[12,20],"novel":[13],"approach":[14,93],"utilizing":[15],"contrastive":[16],"learning":[17],"to":[18,30,34],"establish":[19],"shared":[21],"embedding":[22],"space":[23],"for":[24,73,146],"texts":[25],"and":[26,54,67,70,89,125,168],"fonts.":[27],"In":[28],"contrast":[29],"previous":[31],"methods":[32],"limited":[33],"word-level":[35],"queries,":[36],"our":[37,74],"method":[38],"enables":[39],"text-font":[40,48,115],"at":[42],"sentence":[44],"level.":[45],"We":[46,141],"collected":[47],"pair":[49,116],"data":[50,117],"from":[51,165],"web":[52],"pages":[53],"templates":[56],"on":[57,64,119],"Internet,":[59],"finetuned":[60],"CLIP":[62],"model":[63],"these":[65],"pairs,":[66],"obtained":[68],"text":[69,88,103],"encoders":[72],"application.":[75],"The":[76,150],"top-k":[77],"fonts":[78,100,156,178],"were":[79],"then":[80],"retrieved":[81,155,172],"using":[82],"cosine":[84],"distance":[85],"between":[86],"input":[87],"embeddings.":[91],"Our":[92],"offers":[94],"three":[95],"key":[96],"advantages:":[97],"(1)":[98],"retrieving":[99],"with":[101,110,176],"sentence-level":[102],"as":[104],"input,":[105],"which":[106],"is":[107,174],"intuitively":[108],"consistent":[109],"behaviors;":[112],"(2)":[113],"leveraging":[114],"available":[118],"Internet":[121],"without":[122,137],"manual":[123],"annotation;":[124],"(3)":[126],"scalability,":[127],"trained":[129],"encoder":[131],"can":[132],"encode":[133],"new":[134],"candidates":[136],"retraining":[138],"model.":[140],"introduced":[142],"an":[143],"evaluation":[144],"metric":[145],"results.":[149],"results":[151],"indicate":[152],"that":[153],"top":[159,170],"3":[160],"score":[161],"better":[162],"than":[163],"those":[164],"baseline":[166],"methods,":[167],"1":[171],"competitive":[175],"selected":[179],"experienced":[181],"graphic":[182],"designers.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}