{"id":"https://openalex.org/W4406611756","doi":"https://doi.org/10.1109/smc54092.2024.10831373","title":"RobustLayoutLM: Leveraging Optimized Layout with Additional Modalities for Improved Document Understanding","display_name":"RobustLayoutLM: Leveraging Optimized Layout with Additional Modalities for Improved Document Understanding","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611756","doi":"https://doi.org/10.1109/smc54092.2024.10831373"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"https://openalex.org/A5100412537","display_name":"Bowen Wang","orcid":"https://orcid.org/0000-0001-8466-4266"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Wang","raw_affiliation_strings":["Shanghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101703681","display_name":"Xiao Wei","orcid":"https://orcid.org/0000-0002-6258-6129"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wei","raw_affiliation_strings":["Shanghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31982228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3167","last_page":"3174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9876000285148621,"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":0.9876000285148621,"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/T11309","display_name":"Music and Audio Processing","score":0.9355999827384949,"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"}},{"id":"https://openalex.org/T11657","display_name":"Digital and Traditional Archives Management","score":0.9164000153541565,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7801107168197632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7608085870742798},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4352710545063019}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7801107168197632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608085870742798},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4352710545063019},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10831373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1964101267","https://openalex.org/W2095818033","https://openalex.org/W2099926976","https://openalex.org/W2112692009","https://openalex.org/W2135164809","https://openalex.org/W2163113711","https://openalex.org/W2163534337","https://openalex.org/W2194775991","https://openalex.org/W2769316437","https://openalex.org/W2891117443","https://openalex.org/W2896457183","https://openalex.org/W2962772269","https://openalex.org/W2963150697","https://openalex.org/W2964346820","https://openalex.org/W2970042171","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3173306993","https://openalex.org/W3173325518","https://openalex.org/W3176664887","https://openalex.org/W3176851559","https://openalex.org/W3182680257","https://openalex.org/W3200439183","https://openalex.org/W4221167941","https://openalex.org/W4226020328","https://openalex.org/W4304013646","https://openalex.org/W4386065837","https://openalex.org/W4386066295","https://openalex.org/W4386075596"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4306353150","https://openalex.org/W2026860389"],"abstract_inverted_index":{"Pre-training":[0],"methods":[1,118],"have":[2],"become":[3],"the":[4,51,64,88,93,120],"mainstream":[5],"in":[6,119],"document":[7,15,29,36],"understanding,":[8],"involving":[9],"self-supervised":[10],"learning":[11],"on":[12,25,110],"large-scale":[13],"unlabeled":[14],"to":[16,81],"learn":[17],"rich":[18],"feature":[19,90],"representations,":[20],"followed":[21],"by":[22,69],"supervised":[23],"fine-tuning":[24],"a":[26],"smaller":[27],"labeled":[28],"dataset.":[30],"Recently":[31],"emerged":[32],"pre-training":[33],"models":[34],"for":[35],"understanding":[37],"all":[38],"use":[39],"layout":[40,52,66,97,124],"information":[41,53,67,86],"as":[42],"important":[43],"features,":[44],"however,":[45],"their":[46],"performance":[47],"significantly":[48],"suffers":[49],"when":[50],"is":[54,79],"incorrect.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"introduce":[60],"RobustLayoutLM,":[61],"which":[62],"utilizes":[63],"optimized":[65],"generated":[68],"our":[70,103],"proposed":[71],"Uniform":[72],"XY":[73],"Cut":[74],"algorithm.":[75],"And":[76],"Visual-Graph":[77],"Tagger":[78],"introduced":[80],"integrate":[82],"image":[83],"and":[84,115],"graph":[85],"after":[87],"transformer":[89],"fusion,":[91],"minimizing":[92],"impact":[94],"of":[95,122],"erroneous":[96],"information.":[98,125],"Experimental":[99],"results":[100,109],"show":[101],"that":[102],"RobustLayoutLM":[104],"achieves":[105],"competitive":[106],"or":[107],"better":[108],"multiple":[111],"standard":[112],"VrDU":[113],"benchmarks":[114],"outperforms":[116],"previous":[117],"face":[121],"incorrect":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}