{"id":"https://openalex.org/W4223967348","doi":"https://doi.org/10.1145/3523150.3523154","title":"A Deep Learning-Based System for Document Layout Analysis","display_name":"A Deep Learning-Based System for Document Layout Analysis","publication_year":2022,"publication_date":"2022-01-15","ids":{"openalex":"https://openalex.org/W4223967348","doi":"https://doi.org/10.1145/3523150.3523154"},"language":"en","primary_location":{"id":"doi:10.1145/3523150.3523154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523150.3523154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 6th International Conference on Machine Learning and Soft Computing","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/A5038151678","display_name":"Hong Tai Tran","orcid":"https://orcid.org/0000-0001-7261-9855"},"institutions":[{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Hong Tai Tran","raw_affiliation_strings":["Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045421508","display_name":"Nam Nguyen","orcid":"https://orcid.org/0009-0002-1135-4069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nam Quan Nguyen","raw_affiliation_strings":["Research Department, Cinnamon AI, Vietnam"],"affiliations":[{"raw_affiliation_string":"Research Department, Cinnamon AI, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101610867","display_name":"Tuan Anh Tran","orcid":"https://orcid.org/0000-0002-0920-4726"},"institutions":[{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tuan Anh Tran","raw_affiliation_strings":["Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031625254","display_name":"Xuan Toan","orcid":"https://orcid.org/0000-0002-9522-3797"},"institutions":[{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Xuan Toan Mai","raw_affiliation_strings":["Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101153572","display_name":"Quoc Thang Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quoc Thang Nguyen","raw_affiliation_strings":["Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science & Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam","institution_ids":["https://openalex.org/I47265099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038151678"],"corresponding_institution_ids":["https://openalex.org/I47265099"],"apc_list":null,"apc_paid":null,"fwci":1.1073,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.77934736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"25"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8246312141418457},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.821574330329895},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.714409589767456},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.629873514175415},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.628911018371582},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5267547965049744},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.522084653377533},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5093358755111694},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46764039993286133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46087318658828735},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45199233293533325},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.430184543132782},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4184998571872711},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.41712841391563416},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32423165440559387},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16944536566734314},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11779233813285828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246312141418457},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.821574330329895},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.714409589767456},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.629873514175415},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.628911018371582},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5267547965049744},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.522084653377533},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5093358755111694},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46764039993286133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46087318658828735},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45199233293533325},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.430184543132782},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4184998571872711},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.41712841391563416},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32423165440559387},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16944536566734314},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11779233813285828},{"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:10.1145/3523150.3523154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523150.3523154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 6th International Conference on Machine Learning and Soft Computing","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":21,"referenced_works":["https://openalex.org/W1987058485","https://openalex.org/W2055408294","https://openalex.org/W2095034769","https://openalex.org/W2108959246","https://openalex.org/W2112692009","https://openalex.org/W2133059825","https://openalex.org/W2135085165","https://openalex.org/W2158295445","https://openalex.org/W2160664703","https://openalex.org/W2200736738","https://openalex.org/W2270798212","https://openalex.org/W2296099862","https://openalex.org/W2533973874","https://openalex.org/W2612452126","https://openalex.org/W2787480186","https://openalex.org/W2808606449","https://openalex.org/W2915774443","https://openalex.org/W3105988348","https://openalex.org/W4242177601","https://openalex.org/W4319705925","https://openalex.org/W6687483927"],"related_works":["https://openalex.org/W2786527349","https://openalex.org/W182542749","https://openalex.org/W2037668370","https://openalex.org/W2268591602","https://openalex.org/W2610978234","https://openalex.org/W2178966353","https://openalex.org/W4377821420","https://openalex.org/W4367292478","https://openalex.org/W3150102101","https://openalex.org/W1502347913"],"abstract_inverted_index":{"Document":[0],"image":[1,42],"understanding":[2],"is":[3,33,74,104],"an":[4],"essential":[5],"process":[6],"in":[7],"the":[8,38,65,79,86,118],"digital":[9,21],"transformation":[10],"era.":[11],"Those":[12],"systems":[13],"automatically":[14],"convert":[15],"a":[16,20,34,47,113],"paper":[17,45],"document":[18,22,30,41],"to":[19,63,110],"for":[23,37],"storing":[24],"and":[25,67,82,107,121],"information":[26],"extracting.":[27],"In":[28],"practice,":[29],"layout":[31,116],"analysis":[32],"critical":[35],"step":[36],"success":[39],"of":[40],"modeling.":[43],"This":[44],"introduces":[46],"page":[48],"segmentation":[49,73],"system":[50,57],"based":[51,77],"on":[52,78],"deep":[53],"neural":[54],"networks.":[55],"Our":[56,92],"uses":[58],"two":[59],"auto":[60],"encoder-decoder":[61],"networks":[62],"segment":[64],"text-line":[66],"non-text":[68,87],"components":[69],"simultaneously.":[70],"The":[71],"paragraph":[72],"then":[75],"realized":[76],"text":[80],"line":[81],"separator":[83],"mask.":[84],"Besides,":[85],"elements":[88],"are":[89],"also":[90],"identified.":[91],"algorithm":[93],"has":[94],"been":[95],"tested":[96],"RDCL2019.":[97],"Experimental":[98],"results":[99],"show":[100],"that":[101],"our":[102],"method":[103],"more":[105,108],"stable":[106],"comfortable":[109],"adapt":[111],"with":[112],"new":[114],"format":[115],"than":[117],"previous":[119],"commercial":[120],"publishing":[122],"systems.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}