{"id":"https://openalex.org/W4414393686","doi":"https://doi.org/10.1007/s10032-025-00556-4","title":"Devanagari character encoded mix-merge vision transformer for robust document layout analysis","display_name":"Devanagari character encoded mix-merge vision transformer for robust document layout analysis","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414393686","doi":"https://doi.org/10.1007/s10032-025-00556-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-025-00556-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-025-00556-4","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-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/A5100642841","display_name":"Shweta Singh","orcid":"https://orcid.org/0000-0002-1561-2494"},"institutions":[{"id":"https://openalex.org/I74885063","display_name":"Sharda University","ror":"https://ror.org/03b6ffh07","country_code":"IN","type":"education","lineage":["https://openalex.org/I74885063"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shweta Singh","raw_affiliation_strings":["Department of Computer Science and Engineering, Sharda University, Greater Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sharda University, Greater Noida, India","institution_ids":["https://openalex.org/I74885063"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004016283","display_name":"Sudeep Varshney","orcid":"https://orcid.org/0000-0002-9136-8614"},"institutions":[{"id":"https://openalex.org/I74885063","display_name":"Sharda University","ror":"https://ror.org/03b6ffh07","country_code":"IN","type":"education","lineage":["https://openalex.org/I74885063"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sudeep Varshney","raw_affiliation_strings":["Department of Computer Science and Engineering, Sharda University, Greater Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sharda University, Greater Noida, India","institution_ids":["https://openalex.org/I74885063"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014849255","display_name":"Ankur Choudhary","orcid":"https://orcid.org/0000-0003-0037-518X"},"institutions":[{"id":"https://openalex.org/I1310439424","display_name":"Accenture (Switzerland)","ror":"https://ror.org/041r3e346","country_code":"CH","type":"company","lineage":["https://openalex.org/I1310439424","https://openalex.org/I4210093804"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ankur Choudhary","raw_affiliation_strings":["Accenture Pvt Ltd., Greater Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Accenture Pvt Ltd., Greater Noida, India","institution_ids":["https://openalex.org/I1310439424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004016283"],"corresponding_institution_ids":["https://openalex.org/I74885063"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20920968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"2","first_page":"365","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9943000078201294,"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/devanagari","display_name":"Devanagari","score":0.9672999978065491},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.637499988079071},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6259999871253967},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.6061999797821045},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5432999730110168},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.506600022315979},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.48969998955726624},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.43950000405311584},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.4074000120162964}],"concepts":[{"id":"https://openalex.org/C2780144916","wikidata":"https://www.wikidata.org/wiki/Q38592","display_name":"Devanagari","level":4,"score":0.9672999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954999804496765},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.637499988079071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6295999884605408},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6259999871253967},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5432999730110168},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2513999938964844},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10032-025-00556-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-025-00556-4","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1755397260","https://openalex.org/W2067287574","https://openalex.org/W2125440314","https://openalex.org/W2945259612","https://openalex.org/W2980913015","https://openalex.org/W2997154779","https://openalex.org/W3028389105","https://openalex.org/W3040920819","https://openalex.org/W3088036953","https://openalex.org/W3104953317","https://openalex.org/W3110641752","https://openalex.org/W3113753692","https://openalex.org/W3126478797","https://openalex.org/W3169305685","https://openalex.org/W3194193629","https://openalex.org/W3194824089","https://openalex.org/W4226051738","https://openalex.org/W4286681621","https://openalex.org/W4304013646","https://openalex.org/W4304014014","https://openalex.org/W4311644716","https://openalex.org/W4316658054","https://openalex.org/W4375947589","https://openalex.org/W4377009036","https://openalex.org/W4390872501","https://openalex.org/W4392457660","https://openalex.org/W4402422296"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-21T06:12:48.119943","created_date":"2025-10-10T00:00:00"}
