{"id":"https://openalex.org/W4416798579","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249117","title":"Zero-shot Artistic Text Recognition with Multimodal Language Models","display_name":"Zero-shot Artistic Text Recognition with Multimodal Language Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798579","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249117"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5103126474","display_name":"Tien Do","orcid":"https://orcid.org/0000-0002-5381-3414"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tien Do","raw_affiliation_strings":["University of Information Technology, VNU-HCM,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016544332","display_name":"Thuyen Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thuyen Tran","raw_affiliation_strings":["University of Information Technology, VNU-HCM,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043063578","display_name":"Duy-Dinh Le","orcid":"https://orcid.org/0000-0003-0356-5501"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duy-Dinh Le","raw_affiliation_strings":["University of Information Technology, VNU-HCM,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081841048","display_name":"Thanh Duc Ngo","orcid":"https://orcid.org/0000-0001-6882-0070"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thanh Duc Ngo","raw_affiliation_strings":["University of Information Technology, VNU-HCM,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123565023"],"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":"2430","last_page":"2435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8285999894142151,"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":0.8285999894142151,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.025699999183416367,"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":0.023000000044703484,"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/stylized-fact","display_name":"Stylized fact","score":0.7657999992370605},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5855000019073486},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.5130000114440918},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47049999237060547},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3659000098705292},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.7657999992370605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424999833106995},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.565500020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192000269889832},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2593572697","https://openalex.org/W2875814315","https://openalex.org/W2953606406","https://openalex.org/W2963233387","https://openalex.org/W2963526661","https://openalex.org/W2965066169","https://openalex.org/W2983626510","https://openalex.org/W2998382406","https://openalex.org/W3004846386","https://openalex.org/W3013224334","https://openalex.org/W3034414401","https://openalex.org/W3082397598","https://openalex.org/W3181186176","https://openalex.org/W3204479434","https://openalex.org/W4285606530","https://openalex.org/W4310335763","https://openalex.org/W4312843595","https://openalex.org/W4312879041","https://openalex.org/W4313045695","https://openalex.org/W4320489219","https://openalex.org/W4382202677","https://openalex.org/W4385767967","https://openalex.org/W4387968089","https://openalex.org/W4390871731","https://openalex.org/W4392172801","https://openalex.org/W4402713111","https://openalex.org/W4402716477","https://openalex.org/W4405784827","https://openalex.org/W4414192342"],"related_works":[],"abstract_inverted_index":{"Artistic":[0],"Text":[1],"(AT),":[2],"characterized":[3],"by":[4],"stylized":[5],"fonts,":[6],"geometric":[7],"distortions,":[8],"and":[9,22,35,57,83],"complex":[10],"visual":[11,92],"effects,":[12],"frequently":[13],"appears":[14],"in":[15],"real-world":[16],"contexts":[17],"such":[18,25],"as":[19],"advertising,":[20],"signage,":[21],"branding.":[23],"Recognizing":[24],"text":[26],"is":[27],"crucial":[28],"for":[29,87],"downstream":[30],"tasks":[31],"like":[32],"image":[33],"understanding":[34],"multimodal":[36],"reasoning.":[37],"While":[38],"recent":[39],"Multimodal":[40],"Language":[41],"Models":[42],"(MLLMs)":[43],"demonstrate":[44],"strong":[45],"general":[46],"vision-language":[47],"capabilities,":[48],"it":[49],"remains":[50],"unclear":[51],"whether":[52],"they":[53],"can":[54],"effectively":[55],"perceive":[56],"interpret":[58],"artistic":[59,78],"text.":[60],"In":[61],"this":[62],"work,":[63],"we":[64],"conduct":[65],"a":[66,74],"comprehensive":[67],"zero-shot":[68],"evaluation":[69],"of":[70,77],"representative":[71],"MLLMs":[72],"on":[73],"diverse":[75],"benchmark":[76],"text,":[79],"revealing":[80],"key":[81],"limitations":[82],"motivating":[84],"the":[85],"need":[86],"hybrid":[88],"approaches":[89],"that":[90],"combine":[91],"grounding":[93],"with":[94],"robust":[95],"language":[96],"modeling.":[97]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}