{"id":"https://openalex.org/W4395702368","doi":"https://doi.org/10.1145/3603287.3651184","title":"Optimum Deep Learning Method for Document Layout Analysis in Low Resource Languages","display_name":"Optimum Deep Learning Method for Document Layout Analysis in Low Resource Languages","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4395702368","doi":"https://doi.org/10.1145/3603287.3651184"},"language":"en","primary_location":{"id":"doi:10.1145/3603287.3651184","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603287.3651184","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603287.3651184?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Southeast Conference on ZZZ","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3603287.3651184?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095920297","display_name":"Md. Mutasim Billah Abu Noman Akanda","orcid":"https://orcid.org/0009-0006-4981-7822"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Md. Mutasim Billah Abu Noman Akanda","raw_affiliation_strings":["Apurba Technologies, Dhaka, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0006-4981-7822","affiliations":[{"raw_affiliation_string":"Apurba Technologies, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055506237","display_name":"Maruf Ahmed","orcid":"https://orcid.org/0009-0004-1923-1738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maruf Ahmed","raw_affiliation_strings":["Apurba Technologies, Dhaka, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0004-1923-1738","affiliations":[{"raw_affiliation_string":"Apurba Technologies, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061996966","display_name":"AKM Shahariar Azad Rabby","orcid":"https://orcid.org/0000-0003-3994-3105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"AKM Shahariar Azad Rabby","raw_affiliation_strings":["Apurba Technologies, Dhaka, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0003-3994-3105","affiliations":[{"raw_affiliation_string":"Apurba Technologies, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029426102","display_name":"Fuad Rahman","orcid":"https://orcid.org/0000-0002-8670-7124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuad Rahman","raw_affiliation_strings":["Apurba Technologies, Sunnyvale, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-8670-7124","affiliations":[{"raw_affiliation_string":"Apurba Technologies, Sunnyvale, California, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5095920297"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9523,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7479126,"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":"199","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9896000027656555,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7839529514312744},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5552161931991577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5171474814414978},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.51129150390625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3435286283493042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839529514312744},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5552161931991577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5171474814414978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.51129150390625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3435286283493042},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603287.3651184","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603287.3651184","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603287.3651184?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Southeast Conference on ZZZ","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3603287.3651184","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603287.3651184","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603287.3651184?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Southeast Conference on ZZZ","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395702368.pdf","grobid_xml":"https://content.openalex.org/works/W4395702368.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2007680663","https://openalex.org/W2031489346","https://openalex.org/W2163113711","https://openalex.org/W2194775991","https://openalex.org/W2889055479","https://openalex.org/W2963037989","https://openalex.org/W2969860478","https://openalex.org/W2980913015","https://openalex.org/W2999905431","https://openalex.org/W4234552385","https://openalex.org/W4288083516","https://openalex.org/W4304013646","https://openalex.org/W4304014014"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Document":[0],"Layout":[1],"Analysis":[2],"(DLA)":[3],"has":[4,13,112],"become":[5,14],"a":[6,20,73,114],"crucial":[7],"process":[8],"in":[9,103,185],"digitizing":[10],"documents.":[11],"Today,":[12],"increasingly":[15],"important":[16,76],"to":[17,23,47,77,147],"properly":[18],"understand":[19],"digital":[21],"document":[22,57,63,74],"get":[24],"insights":[25,68],"on":[26,120],"the":[27,32,70,79,121,149,166],"structure":[28],"and":[29,43,84,144,154,175,188],"contents":[30],"of":[31,38,72,81,117,123],"document.":[33],"DLA":[34,95,127,139,183],"combines":[35],"different":[36],"techniques":[37],"image":[39],"processing,":[40],"computer":[41],"vision,":[42],"natural":[44],"language":[45],"processing":[46],"help":[48],"us":[49],"perform":[50],"various":[51],"tasks":[52],"such":[53],"as":[54],"character":[55],"recognition,":[56],"classification,":[58],"information":[59,119],"retrieval,":[60],"content":[61],"summarization,":[62],"restructuring,":[64],"etc.":[65],"Gathering":[66],"proper":[67],"into":[69],"layout":[71],"is":[75],"detect":[78],"identity":[80],"each":[82],"element":[83],"its":[85],"relationship.":[86],"There":[87],"have":[88],"been":[89,113],"many":[90],"major":[91],"Deep":[92,124],"Learning":[93,125],"based":[94,126],"algorithms":[96],"invented":[97],"recently":[98],"which":[99],"obtained":[100],"impressive":[101],"results":[102],"publicly":[104],"available":[105,118],"high-resource":[106],"languages":[107,156],"like":[108,157],"English.":[109],"However,":[110],"there":[111],"significant":[115],"shortage":[116],"effectiveness":[122],"approaches":[128,140],"for":[129,152,182],"low-resource":[130,153],"languages.":[131],"This":[132],"paper":[133],"investigates":[134],"these":[135],"state-of-the-art":[136],"deep":[137],"learning-based":[138],"-":[141],"DiT,":[142],"LayoutLMv3,":[143],"YOLOv8":[145,163],"[9]":[146,164],"find":[148],"optimal":[150],"approach":[151],"grapheme-based":[155,189],"Bengali.":[158],"We":[159],"found":[160],"out":[161],"that":[162],"performs":[165],"best":[167],"with":[168],"8.95%":[169],"better":[170,177],"IoU":[171,178],"score":[172,179],"than":[173,180],"DiT":[174],"38.48%":[176],"LayoutLMv3":[181],"task":[184],"low":[186],"resource":[187],"language.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-10-10T00:00:00"}