{"id":"https://openalex.org/W4387030630","doi":"https://doi.org/10.48550/arxiv.2309.12382","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","display_name":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","publication_year":2023,"publication_date":"2023-09-21","ids":{"openalex":"https://openalex.org/W4387030630","doi":"https://doi.org/10.48550/arxiv.2309.12382"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.12382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.12382","pdf_url":"https://arxiv.org/pdf/2309.12382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.12382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100383807","display_name":"Daehee Kim","orcid":"https://orcid.org/0000-0001-9676-9604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Daehee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083360792","display_name":"Yoonsik Kim","orcid":"https://orcid.org/0000-0001-8023-8278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Yoonsik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454683","display_name":"Donghyun Kim","orcid":"https://orcid.org/0000-0002-7132-4454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, DongHyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104173820","display_name":"Yumin Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, Yumin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082063964","display_name":"Geewook Kim","orcid":"https://orcid.org/0009-0001-6713-3858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Geewook","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010886776","display_name":"Taeho Kil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kil, Taeho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9979000091552734,"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":0.9979000091552734,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9735999703407288,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9610999822616577,"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/computer-science","display_name":"Computer science","score":0.800896942615509},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.775968074798584},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6758475303649902},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6366357803344727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5429477691650391},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5233960747718811},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4534454941749573},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4456678330898285},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41999685764312744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800896942615509},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.775968074798584},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6758475303649902},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6366357803344727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429477691650391},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5233960747718811},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4534454941749573},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4456678330898285},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41999685764312744},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.12382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.12382","pdf_url":"https://arxiv.org/pdf/2309.12382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.12382","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.12382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.12382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.12382","pdf_url":"https://arxiv.org/pdf/2309.12382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W202723009","https://openalex.org/W2145955964","https://openalex.org/W2188612292","https://openalex.org/W2165396616","https://openalex.org/W2058882606"],"abstract_inverted_index":{"Inspired":[0],"by":[1,122],"the":[2,72,92,124],"great":[3],"success":[4],"of":[5,74],"language":[6],"model":[7],"(LM)-based":[8],"pre-training,":[9],"recent":[10],"studies":[11],"in":[12,78,91],"visual":[13,57],"document":[14,25,117],"understanding":[15],"have":[16],"explored":[17],"LM-based":[18],"pre-training":[19,29,89,100,145,167],"methods":[20,146],"for":[21,68,165],"modeling":[22],"text":[23,33,61,75,112,120],"within":[24],"images.":[26,62],"Among":[27],"them,":[28],"that":[30,104,140,157],"reads":[31],"all":[32],"from":[34],"an":[35],"image":[36,76],"has":[37],"shown":[38],"promise,":[39],"but":[40],"often":[41],"exhibits":[42],"instability":[43],"and":[44,59,95,118,147,163],"even":[45],"fails":[46],"when":[47],"applied":[48],"to":[49,114,151],"broader":[50,93],"domains,":[51],"such":[52],"as":[53],"those":[54],"involving":[55],"both":[56],"documents":[58],"scene":[60,119],"This":[63],"is":[64,81],"a":[65,98],"substantial":[66],"limitation":[67],"real-world":[69],"scenarios,":[70],"where":[71],"processing":[73],"inputs":[77],"diverse":[79],"domains":[80,94,121],"essential.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"investigate":[87],"effective":[88],"tasks":[90],"also":[96],"propose":[97],"novel":[99],"method":[101],"called":[102],"SCOB":[103,128,141,158],"leverages":[105],"character-wise":[106],"supervised":[107,131],"contrastive":[108],"learning":[109],"with":[110],"online":[111],"rendering":[113],"effectively":[115,164],"pre-train":[116],"bridging":[123],"domain":[125],"gap.":[126],"Moreover,":[127],"enables":[129],"weakly":[130],"learning,":[132],"significantly":[133],"reducing":[134],"annotation":[135],"costs.":[136],"Extensive":[137],"benchmarks":[138],"demonstrate":[139],"generally":[142,162],"improves":[143],"vanilla":[144],"achieves":[148],"comparable":[149],"performance":[150],"state-of-the-art":[152],"methods.":[153,168],"Our":[154],"findings":[155],"suggest":[156],"can":[159],"be":[160,172],"served":[161],"read-type":[166],"The":[169],"code":[170],"will":[171],"available":[173],"at":[174],"https://github.com/naver-ai/scob.":[175]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2023-09-26T00:00:00"}