{"id":"https://openalex.org/W4308236023","doi":"https://doi.org/10.1109/icip46576.2022.9897491","title":"Transformer-Based Approach for Document Layout Understanding","display_name":"Transformer-Based Approach for Document Layout Understanding","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236023","doi":"https://doi.org/10.1109/icip46576.2022.9897491"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897491","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","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/A5109217666","display_name":"Huichen Yang","orcid":"https://orcid.org/0009-0003-8344-9566"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huichen Yang","raw_affiliation_strings":["Kansas State University,Department of Computer Science,Manhattan,Kansas,USA","Department of Computer Science, Kansas State University, Manhattan, Kansas, USA"],"affiliations":[{"raw_affiliation_string":"Kansas State University,Department of Computer Science,Manhattan,Kansas,USA","institution_ids":["https://openalex.org/I189590672"]},{"raw_affiliation_string":"Department of Computer Science, Kansas State University, Manhattan, Kansas, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016291944","display_name":"William Hsu","orcid":"https://orcid.org/0000-0002-5168-070X"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Hsu","raw_affiliation_strings":["Kansas State University,Department of Computer Science,Manhattan,Kansas,USA","Department of Computer Science, Kansas State University, Manhattan, Kansas, USA"],"affiliations":[{"raw_affiliation_string":"Kansas State University,Department of Computer Science,Manhattan,Kansas,USA","institution_ids":["https://openalex.org/I189590672"]},{"raw_affiliation_string":"Department of Computer Science, Kansas State University, Manhattan, Kansas, USA","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109217666"],"corresponding_institution_ids":["https://openalex.org/I189590672"],"apc_list":null,"apc_paid":null,"fwci":1.0195,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84272066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9929999709129333,"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/transformer","display_name":"Transformer","score":0.7740035057067871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569016218185425},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6043927669525146},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4935988187789917},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.461734414100647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4547133445739746},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4253145456314087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32610270380973816},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.20139846205711365},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15593260526657104},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09372955560684204}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7740035057067871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569016218185425},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6043927669525146},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4935988187789917},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.461734414100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4547133445739746},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4253145456314087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32610270380973816},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.20139846205711365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15593260526657104},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09372955560684204},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897491","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2022351003","https://openalex.org/W2133713322","https://openalex.org/W2601564443","https://openalex.org/W2798826627","https://openalex.org/W2964346820","https://openalex.org/W2970042171","https://openalex.org/W2997747012","https://openalex.org/W3003711898","https://openalex.org/W3096609285","https://openalex.org/W3122239467","https://openalex.org/W3138516171","https://openalex.org/W3146455718","https://openalex.org/W3163476226","https://openalex.org/W3176664887","https://openalex.org/W3201871940","https://openalex.org/W3212748493","https://openalex.org/W3217139832","https://openalex.org/W4206216093","https://openalex.org/W4225984125","https://openalex.org/W6784094891","https://openalex.org/W6793267612","https://openalex.org/W6803817551","https://openalex.org/W6804794748","https://openalex.org/W6810479921"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W4321487865","https://openalex.org/W3155418658","https://openalex.org/W2969228573"],"abstract_inverted_index":{"We":[0,127],"present":[1],"an":[2,45],"end-to-end":[3],"transformer-based":[4,49,81,122],"framework":[5,123],"named":[6],"TRDLU":[7,78,90,129,140],"for":[8],"the":[9,18,62,108,115,142],"task":[10,20],"of":[11,41,110,118,148],"Document":[12],"Layout":[13],"Understanding":[14],"(DLU).":[15],"DLU":[16,71,125,133],"is":[17,43,91,100,114],"fundamental":[19],"to":[21],"automatically":[22],"understand":[23],"document":[24],"structures.":[25],"To":[26,107],"accurately":[27],"detect":[28],"content":[29],"boxes":[30],"and":[31,76,84],"classify":[32],"them":[33],"into":[34],"semantically":[35],"meaningful":[36],"classes":[37],"from":[38],"various":[39],"formats":[40],"documents":[42],"still":[44],"open":[46],"challenge.":[47],"Recently,":[48],"detection":[50,64,74,88],"neural":[51],"networks":[52],"have":[53],"shown":[54],"their":[55],"capability":[56],"over":[57],"traditional":[58],"convolutional-based":[59],"methods":[60,145],"in":[61,124],"object":[63],"area.":[65],"In":[66],"this":[67,113],"paper,":[68],"we":[69],"consider":[70],"as":[72,87],"a":[73,93,120],"task,":[75],"introduce":[77],"which":[79],"integrates":[80],"vision":[82],"backbone":[83],"transformer":[85],"encoder-decoder":[86],"pipeline.":[89],"only":[92],"visual":[94],"feature-based":[95,105],"framework,":[96],"but":[97],"its":[98],"performance":[99],"even":[101],"better":[102],"than":[103],"multi-modal":[104],"models.":[106],"best":[109],"our":[111],"knowledge,":[112],"first":[116],"study":[117],"employing":[119],"fully":[121],"tasks.":[126],"evaluated":[128],"on":[130,146],"three":[131],"different":[132],"benchmark":[134],"datasets,":[135],"each":[136],"with":[137],"strong":[138],"baselines.":[139],"outperforms":[141],"current":[143],"state-of-the-art":[144],"all":[147],"them.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}