{"id":"https://openalex.org/W4283706417","doi":"https://doi.org/10.48550/arxiv.2206.13155","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","display_name":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4283706417","doi":"https://doi.org/10.48550/arxiv.2206.13155"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.13155","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.13155","pdf_url":"https://arxiv.org/pdf/2206.13155","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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/2206.13155","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062254598","display_name":"Chuwei Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luo, Chuwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109578044","display_name":"Guozhi Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Guozhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750527","display_name":"Qi Zheng","orcid":"https://orcid.org/0009-0001-3822-2616"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100313026","display_name":"Cong Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Cong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Lianwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734065","display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0001-9077-3928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xue, Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101718341","display_name":"Luo Si","orcid":"https://orcid.org/0000-0002-3263-234X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Luo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5062254598"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9805999994277954,"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":0.9805999994277954,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.978600025177002,"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":0.9517999887466431,"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/computer-science","display_name":"Computer science","score":0.8081152439117432},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6191742420196533},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.543910562992096},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5343961119651794},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5180842876434326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034136176109314},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4855670630931854},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.48370224237442017},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46909984946250916},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.45380523800849915},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4317346215248108},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.428357869386673},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4194784164428711},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34375596046447754},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33936434984207153},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09731361269950867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081152439117432},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6191742420196533},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.543910562992096},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5343961119651794},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5180842876434326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034136176109314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4855670630931854},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.48370224237442017},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46909984946250916},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.45380523800849915},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4317346215248108},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.428357869386673},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4194784164428711},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34375596046447754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33936434984207153},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09731361269950867},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.13155","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.13155","pdf_url":"https://arxiv.org/pdf/2206.13155","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2206.13155","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.13155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.13155","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.13155","pdf_url":"https://arxiv.org/pdf/2206.13155","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283706417.pdf","grobid_xml":"https://content.openalex.org/works/W4283706417.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4301143707","https://openalex.org/W2952745240","https://openalex.org/W2941608206","https://openalex.org/W4387929264","https://openalex.org/W3105220303","https://openalex.org/W4287903637","https://openalex.org/W2999168658","https://openalex.org/W69308499","https://openalex.org/W4288365749","https://openalex.org/W2936497627"],"abstract_inverted_index":{"Multi-modal":[0],"document":[1,15,21,115,126,137],"pre-trained":[2,22],"models":[3,23],"have":[4,24],"proven":[5],"to":[6,100,111,145,152,159,171],"be":[7],"very":[8],"effective":[9],"in":[10,86],"a":[11,79,88,94],"variety":[12],"of":[13,64,75],"visually-rich":[14],"understanding":[16,138],"(VrDU)":[17],"tasks.":[18],"Though":[19],"existing":[20],"achieved":[25],"excellent":[26],"performance":[27,133,169],"on":[28,45,134],"standard":[29],"benchmarks":[30],"for":[31,69],"VrDU,":[32],"the":[33,39,62,73,105,122,131,167],"way":[34],"they":[35],"model":[36,174],"and":[37,43,54,93,103,154],"exploit":[38],"interactions":[40,106],"between":[41,107],"vision":[42],"language":[44],"documents":[46],"has":[47],"hindered":[48],"them":[49],"from":[50,72,121],"better":[51],"generalization":[52],"ability":[53],"higher":[55],"accuracy.":[56],"In":[57],"this":[58],"work,":[59],"we":[60],"investigate":[61],"problem":[63],"vision-language":[65,90,95],"joint":[66],"representation":[67],"learning":[68],"VrDU":[70],"mainly":[71],"perspective":[74],"supervisory":[76],"signals.":[77],"Specifically,":[78],"pre-training":[80],"paradigm":[81],"called":[82],"Bi-VLDoc":[83,128,165],"is":[84],"proposed,":[85],"which":[87],"bidirectional":[89],"supervision":[91],"strategy":[92],"hybrid-attention":[96],"mechanism":[97],"are":[98],"devised":[99],"fully":[101],"explore":[102],"utilize":[104],"these":[108],"two":[109],"modalities,":[110],"learn":[112],"stronger":[113],"cross-modal":[114,125],"representations":[116],"with":[117],"richer":[118],"semantics.":[119],"Benefiting":[120],"learned":[123],"informative":[124],"representations,":[127],"significantly":[129],"advances":[130],"state-of-the-art":[132,168],"three":[135],"widely-used":[136],"benchmarks,":[139],"including":[140],"Form":[141],"Understanding":[142],"(from":[143,150,157],"85.14%":[144],"93.44%),":[146],"Receipt":[147],"Information":[148],"Extraction":[149],"96.01%":[151],"97.84%),":[153],"Document":[155,162],"Classification":[156],"96.08%":[158],"97.12%).":[160],"On":[161],"Visual":[163],"QA,":[164],"achieves":[166],"compared":[170],"previous":[172],"single":[173],"methods.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}