{"id":"https://openalex.org/W4381708538","doi":"https://doi.org/10.1145/3580305.3599929","title":"VRDU: A Benchmark for Visually-rich Document Understanding","display_name":"VRDU: A Benchmark for Visually-rich Document Understanding","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4381708538","doi":"https://doi.org/10.1145/3580305.3599929"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599929","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599929","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/10.1145/3580305.3599929","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100384100","display_name":"Zilong Wang","orcid":"https://orcid.org/0000-0002-1614-0943"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zilong Wang","raw_affiliation_strings":["University of California, San Diego, La Jolla, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101780760","display_name":"Yichao Zhou","orcid":"https://orcid.org/0009-0003-8632-446X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichao Zhou","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323852","display_name":"Wei Wei","orcid":"https://orcid.org/0009-0005-4217-0918"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Google, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005652285","display_name":"Chen-Yu Lee","orcid":"https://orcid.org/0009-0008-3275-6028"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen-Yu Lee","raw_affiliation_strings":["Google, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102945075","display_name":"Sandeep Tata","orcid":"https://orcid.org/0009-0007-7785-5516"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Tata","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100384100"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":1.0832,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79255152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5184","last_page":"5193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9958999752998352,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9958999752998352,"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/T10028","display_name":"Topic Modeling","score":0.9901000261306763,"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/T11309","display_name":"Music and Audio Processing","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8481500148773193},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6791290044784546},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6179639101028442},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.5170374512672424},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4682173728942871},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42554694414138794},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4136173129081726},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35085394978523254},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.26106464862823486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481500148773193},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6791290044784546},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6179639101028442},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5170374512672424},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4682173728942871},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42554694414138794},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4136173129081726},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35085394978523254},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26106464862823486},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599929","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599929","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599929","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599929","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599929","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381708538.pdf","grobid_xml":"https://content.openalex.org/works/W4381708538.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2004763266","https://openalex.org/W2194775991","https://openalex.org/W2962772269","https://openalex.org/W2979826702","https://openalex.org/W2997154779","https://openalex.org/W3000758063","https://openalex.org/W3003484198","https://openalex.org/W3093218477","https://openalex.org/W3104953317","https://openalex.org/W3120043490","https://openalex.org/W3132781388","https://openalex.org/W3176664887","https://openalex.org/W3201693581","https://openalex.org/W3202839357","https://openalex.org/W3204562006","https://openalex.org/W4312263373"],"related_works":["https://openalex.org/W2121300814","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W4231091074","https://openalex.org/W1886613375","https://openalex.org/W4236081792","https://openalex.org/W2130974462","https://openalex.org/W4250583430","https://openalex.org/W4234406076"],"abstract_inverted_index":{"Understanding":[0,66],"visually-rich":[1],"business":[2,10],"documents":[3,42],"to":[4,119,136,167],"extract":[5],"structured":[6,190],"data":[7,80,191],"and":[8,19,58,91,94,108,130,152,172],"automate":[9],"workflows":[11],"has":[12,147],"been":[13],"receiving":[14],"attention":[15],"both":[16],"in":[17,44,162,188],"academia":[18],"industry.":[20,45],"Although":[21],"recent":[22],"multi-modal":[23],"language":[24],"models":[25,154],"have":[26],"achieved":[27],"impressive":[28],"results,":[29],"we":[30,49,61],"find":[31],"that":[32,72],"existing":[33],"benchmarks":[34],"do":[35],"not":[36],"reflect":[37],"the":[38,51,125,170,173,180],"complexity":[39],"of":[40,96,127,150],"real":[41],"seen":[43],"In":[46],"this":[47,178],"work,":[48],"identify":[50],"desiderata":[52],"for":[53],"a":[54,101,114,148],"more":[55],"comprehensive":[56],"benchmark":[57,171],"propose":[59],"one":[60],"call":[62],"Visually":[63],"Rich":[64],"Document":[65],"(VRDU).":[67],"VRDU":[68],"contains":[69],"two":[70],"datasets":[71],"represent":[73],"several":[74],"challenges:":[75],"rich":[76,194],"schema":[77],"including":[78,89],"diverse":[79],"types":[81],"as":[82,84,160],"well":[83],"hierarchical":[85,157],"entities,":[86],"complex":[87],"templates":[88,139],"tables":[90],"multi-column":[92],"layouts,":[93],"diversity":[95],"different":[97],"layouts":[98],"(templates)":[99],"within":[100],"single":[102],"document":[103,138],"type.":[104],"We":[105,123,165,176],"design":[106],"few-shot":[107,145],"conventional":[109],"experiment":[110],"settings":[111],"along":[112],"with":[113,156],"carefully":[115],"designed":[116],"matching":[117],"algorithm":[118],"evaluate":[120],"extraction":[121],"results.":[122],"report":[124],"performance":[126,146],"strong":[128],"baselines":[129],"offer":[131],"three":[132],"observations:":[133],"(1)":[134],"generalizing":[135],"new":[137],"is":[140],"still":[141],"very":[142],"challenging,":[143],"(2)":[144],"lot":[149],"headroom,":[151],"(3)":[153],"struggle":[155],"fields":[158],"such":[159],"line-items":[161],"an":[163],"invoice.":[164],"plan":[166],"open":[168],"source":[169],"evaluation":[174],"toolkit.":[175],"hope":[177],"helps":[179],"community":[181],"make":[182],"progress":[183],"on":[184],"these":[185],"challenging":[186],"tasks":[187],"extracting":[189],"from":[192],"visually":[193],"documents.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}