{"id":"https://openalex.org/W4390451931","doi":"https://doi.org/10.1145/3611380.3628554","title":"Enhancing Visually-Rich Document Understanding via Layout Structure Modeling","display_name":"Enhancing Visually-Rich Document Understanding via Layout Structure Modeling","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390451931","doi":"https://doi.org/10.1145/3611380.3628554"},"language":"en","primary_location":{"id":"doi:10.1145/3611380.3628554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628554","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628554","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628554","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061142418","display_name":"Q. Li","orcid":"https://orcid.org/0009-0007-2531-6537"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwei Li","raw_affiliation_strings":["School of Computer Science, Wuhan University, China"],"raw_orcid":"https://orcid.org/0009-0007-2531-6537","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002584135","display_name":"Zuchao Li","orcid":"https://orcid.org/0000-0003-0436-8446"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuchao Li","raw_affiliation_strings":["School of Computer Science, Wuhan University, China"],"raw_orcid":"https://orcid.org/0000-0003-0436-8446","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003753939","display_name":"Xiantao Cai","orcid":"https://orcid.org/0000-0002-0764-5085"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiantao Cai","raw_affiliation_strings":["School of Computer Science, Wuhan University, China"],"raw_orcid":"https://orcid.org/0000-0002-0764-5085","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007642002","display_name":"Bo Du","orcid":"https://orcid.org/0000-0001-8104-3448"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["School of Computer Science, Wuhan University, China"],"raw_orcid":"https://orcid.org/0000-0001-8104-3448","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036050911","display_name":"Hai Zhao","orcid":"https://orcid.org/0000-0001-7290-0487"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0001-7290-0487","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.998199999332428,"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":0.998199999332428,"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":0.9972000122070312,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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":0.8318605422973633},{"id":"https://openalex.org/keywords/graph-layout","display_name":"Graph Layout","score":0.6214383840560913},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.5997873544692993},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5442145466804504},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40803903341293335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37828773260116577},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2875722348690033},{"id":"https://openalex.org/keywords/graph-drawing","display_name":"Graph drawing","score":0.2291121482849121},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08229202032089233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318605422973633},{"id":"https://openalex.org/C2911174283","wikidata":"https://www.wikidata.org/wiki/Q739462","display_name":"Graph Layout","level":4,"score":0.6214383840560913},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.5997873544692993},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5442145466804504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40803903341293335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37828773260116577},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2875722348690033},{"id":"https://openalex.org/C112953755","wikidata":"https://www.wikidata.org/wiki/Q739462","display_name":"Graph drawing","level":3,"score":0.2291121482849121},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08229202032089233}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3611380.3628554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628554","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628554","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3611380.3628554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628554","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628554","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G208121132","display_name":null,"funder_award_id":"No.62225113","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G4741396845","display_name":null,"funder_award_id":"No.2042023kf1033","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390451931.pdf","grobid_xml":"https://content.openalex.org/works/W4390451931.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2470673105","https://openalex.org/W2914911817","https://openalex.org/W2962772269","https://openalex.org/W2997154779","https://openalex.org/W3092968218","https://openalex.org/W3104953317","https://openalex.org/W4285105124"],"related_works":["https://openalex.org/W2130283001","https://openalex.org/W2886783053","https://openalex.org/W1997952588","https://openalex.org/W4390451931","https://openalex.org/W1555430809","https://openalex.org/W4388187290","https://openalex.org/W1593721195","https://openalex.org/W4385890273","https://openalex.org/W4387183640","https://openalex.org/W3080402"],"abstract_inverted_index":{"In":[0,41],"recent":[1],"years,":[2],"the":[3,33,54,66,76,81,102,105,151,169,182,187,198],"use":[4],"of":[5,35,56,104,108,153,171,174],"multi-modal":[6],"pre-trained":[7],"Transformers":[8],"has":[9],"led":[10],"to":[11,60,74,93,167],"significant":[12,144],"advancements":[13],"in":[14,196],"visually-rich":[15],"document":[16,49,62,95,112,158],"understanding.":[17],"However,":[18],"existing":[19,147],"models":[20],"have":[21],"mainly":[22],"focused":[23],"on":[24,80,118],"features":[25],"such":[26],"as":[27],"text":[28,39,77,109],"and":[29,124,126,149,186],"vision":[30],"while":[31],"neglecting":[32],"importance":[34,152],"layout":[36,57,63,96,155],"relationship":[37],"between":[38],"nodes.":[40],"this":[42],"paper,":[43],"we":[44],"propose":[45],"GraphLayoutLM,":[46],"a":[47,70,88,143,193],"novel":[48],"understanding":[50,103,159],"model":[51,86,100,117],"that":[52,138,180],"leverages":[53],"modeling":[55],"structure":[58],"graph":[59,71,82,183],"inject":[61],"knowledge":[64],"into":[65,157],"model.":[67,176],"GraphLayoutLM":[68],"utilizes":[69],"reordering":[72,184],"algorithm":[73,185],"adjust":[75],"sequence":[78],"based":[79],"structure.":[83],"Additionally,":[84],"our":[85,116,139,175],"uses":[87],"layout-aware":[89,188],"multi-head":[90,189],"self-attention":[91,190],"layer":[92,191],"learn":[94],"knowledge.":[97],"The":[98,177],"proposed":[99,140],"enables":[101],"spatial":[106],"arrangement":[107],"elements,":[110],"improving":[111],"comprehension.":[113],"We":[114,161],"evaluate":[115],"various":[119],"benchmarks,":[120],"including":[121],"FUNSD,":[122],"XFUND":[123],"CORD":[125],"it":[127],"achieves":[128],"state-of-the-art":[129],"results":[130,136,178],"among":[131],"these":[132],"datasets.":[133],"Our":[134],"experiment":[135],"demonstrate":[137],"method":[141],"provides":[142],"improvement":[145],"over":[146],"approaches":[148],"showcases":[150],"incorporating":[154],"information":[156],"models.":[160],"also":[162],"conduct":[163],"an":[164],"ablation":[165],"study":[166],"investigate":[168],"contribution":[170],"each":[172],"component":[173],"show":[179],"both":[181],"play":[192],"crucial":[194],"role":[195],"achieving":[197],"best":[199],"performance.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}