{"id":"https://openalex.org/W4413155844","doi":"https://doi.org/10.1109/cvpr52734.2025.01347","title":"Relation-Rich Visual Document Generator for Visual Information Extraction","display_name":"Relation-Rich Visual Document Generator for Visual Information Extraction","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413155844","doi":"https://doi.org/10.1109/cvpr52734.2025.01347"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":null,"display_name":"Zi-Han Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zi-Han Jiang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058394936","display_name":"Chien\u2010Wei Lin","orcid":"https://orcid.org/0000-0003-4023-7339"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Wei Lin","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101469985","display_name":"Wei-Hua Li","orcid":"https://orcid.org/0009-0005-8330-0491"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Hua Li","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030971950","display_name":"Hsuan-Tung Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087940","display_name":"Technology Holding (United States)","ror":"https://ror.org/005mr0595","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087940"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsuan-Tung Liu","raw_affiliation_strings":["E.SUN Financial Holding Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"E.SUN Financial Holding Co., Ltd","institution_ids":["https://openalex.org/I4210087940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024171815","display_name":"Yi-Ren Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I135551196","display_name":"National Kaohsiung Normal University","ror":"https://ror.org/04tsc8g87","country_code":"TW","type":"education","lineage":["https://openalex.org/I135551196"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Ren Yeh","raw_affiliation_strings":["National Kaohsiung Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Kaohsiung Normal University","institution_ids":["https://openalex.org/I135551196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107837581","display_name":"Chu-Song Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chu-Song Chen","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14449","last_page":"14459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9912999868392944,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9912999868392944,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9872999787330627,"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":0.7248010039329529},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.64754319190979},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5604112148284912},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5562773942947388},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4201239347457886},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.41982632875442505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40808165073394775},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3327341675758362},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2008606195449829},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07313966751098633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7248010039329529},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.64754319190979},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5604112148284912},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5562773942947388},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4201239347457886},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.41982632875442505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40808165073394775},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3327341675758362},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2008606195449829},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07313966751098633},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2962772269","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3000176874","https://openalex.org/W3003484198","https://openalex.org/W3035050475","https://openalex.org/W3120043490","https://openalex.org/W3132296545","https://openalex.org/W3158362813","https://openalex.org/W3167280680","https://openalex.org/W3176851559","https://openalex.org/W3200439183","https://openalex.org/W3201833923","https://openalex.org/W4283803959","https://openalex.org/W4285105124","https://openalex.org/W4304013646","https://openalex.org/W4312233877","https://openalex.org/W4320481960","https://openalex.org/W4365512576","https://openalex.org/W4385570166","https://openalex.org/W4385574075","https://openalex.org/W4385982154","https://openalex.org/W4385990846","https://openalex.org/W4385991013","https://openalex.org/W4385991027","https://openalex.org/W4386076094","https://openalex.org/W4386076211","https://openalex.org/W4386076468","https://openalex.org/W4387846478","https://openalex.org/W4389519972","https://openalex.org/W4402671775","https://openalex.org/W4402702988","https://openalex.org/W4402716330","https://openalex.org/W4404782234","https://openalex.org/W4405595839"],"related_works":["https://openalex.org/W2976808399","https://openalex.org/W2609844752","https://openalex.org/W4392969631","https://openalex.org/W4285246823","https://openalex.org/W4226278302","https://openalex.org/W4221160509","https://openalex.org/W2547211086","https://openalex.org/W2538200646","https://openalex.org/W1968988659","https://openalex.org/W2888033806"],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"and":[7,30,51,87,130,132],"Multimodal":[8],"LLMs":[9,113],"(MLLMs)":[10],"for":[11,78],"visual":[12,16,96],"document":[13,37,116,143,173],"understanding":[14,174],"(VDU),":[15],"information":[17],"extraction":[18],"(VIE)":[19],"from":[20,146],"relation-rich":[21],"documents":[22,80],"remains":[23],"challenging":[24],"due":[25],"to":[26,40,114,139],"the":[27,85,170],"layout":[28,59,63],"diversity":[29],"limited":[31],"training":[32],"data.":[33],"While":[34],"existing":[35],"synthetic":[36],"generators":[38],"attempt":[39],"address":[41],"data":[42],"scarcity,":[43],"they":[44],"either":[45],"rely":[46],"on":[47,68,176],"manually":[48],"designed":[49,121],"layouts":[50,144],"templates,":[52],"or":[53,158],"adopt":[54],"rule-based":[55],"approaches":[56],"that":[57,100,165],"limit":[58],"diversity.":[60],"Besides,":[61],"current":[62],"generation":[64],"methods":[65],"focus":[66],"solely":[67,145],"topological":[69],"patterns":[70],"without":[71],"considering":[72],"textual":[73],"content,":[74],"making":[75],"them":[76],"impractical":[77],"generating":[79],"with":[81],"complex":[82],"associations":[83],"between":[84],"contents":[86],"layouts.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"propose":[93],"a":[94,105,119],"Relation-rIch":[95],"Document":[97],"GEnerator":[98],"(RIDGE)":[99],"addresses":[101],"these":[102],"limitations":[103],"through":[104],"two-stage":[106],"approach:":[107],"(1)":[108],"Content":[109],"Generation,":[110,136],"which":[111,126,137],"leverages":[112],"generate":[115],"content":[117],"using":[118],"carefully":[120],"Hierarchical":[122],"Structure":[123],"Text":[124],"format":[125],"captures":[127],"entity":[128],"categories":[129],"relationships,":[131],"(2)":[133],"Content-driven":[134],"Layout":[135],"learns":[138],"create":[140],"diverse,":[141],"plausible":[142],"easily":[147],"available":[148],"Optical":[149],"Character":[150],"Recognition":[151],"(OCR)":[152],"results,":[153],"requiring":[154],"no":[155],"human":[156],"labeling":[157],"annotations":[159],"efforts.":[160],"Experimental":[161],"results":[162],"have":[163],"demonstrated":[164],"our":[166],"method":[167],"significantly":[168],"enhances":[169],"performance":[171],"of":[172],"models":[175],"various":[177],"VIE":[178],"benchmarks.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}