{"id":"https://openalex.org/W4304080438","doi":"https://doi.org/10.1145/3503161.3548547","title":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","display_name":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080438","doi":"https://doi.org/10.1145/3503161.3548547"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548547","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Qiao","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383008","display_name":"Ying Chen","orcid":"https://orcid.org/0000-0001-7379-5025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Chen","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334065","display_name":"Can Li","orcid":"https://orcid.org/0000-0003-3795-2008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Can Li","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339791","display_name":"Pengfei Li","orcid":"https://orcid.org/0009-0009-4234-1579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Li","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034730393","display_name":"Zaisheng Li","orcid":"https://orcid.org/0000-0001-8052-0708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zaisheng Li","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055485426","display_name":"Baorui Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baorui Zou","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078677549","display_name":"Dashan Guo","orcid":"https://orcid.org/0000-0001-6833-8882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dashan Guo","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101931121","display_name":"Yingda Xu","orcid":"https://orcid.org/0000-0003-0637-177X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingda Xu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011474118","display_name":"Yunlu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlu Xu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011185036","display_name":"Zhanzhan Cheng","orcid":"https://orcid.org/0000-0002-5732-1513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanzhan Cheng","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101448949","display_name":"Yi Niu","orcid":"https://orcid.org/0000-0002-7359-276X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Niu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7355","last_page":"7358"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/toolbox","display_name":"Toolbox","score":0.9411731362342834},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8220254182815552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8174495697021484},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5877861976623535},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5676660537719727},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5179852247238159},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4255332052707672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41085392236709595},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3869541585445404},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.34145641326904297},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.34115904569625854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3387657403945923},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16187724471092224},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10071715712547302},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09469175338745117}],"concepts":[{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.9411731362342834},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8220254182815552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174495697021484},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5877861976623535},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5676660537719727},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5179852247238159},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4255332052707672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41085392236709595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3869541585445404},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.34145641326904297},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34115904569625854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3387657403945923},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16187724471092224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10071715712547302},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09469175338745117},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548547","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2194187530","https://openalex.org/W2964296749","https://openalex.org/W2964346820","https://openalex.org/W2967615747","https://openalex.org/W2982121298","https://openalex.org/W2998621280","https://openalex.org/W3003711898","https://openalex.org/W3108646486","https://openalex.org/W3120043490","https://openalex.org/W3152831436","https://openalex.org/W3160285664","https://openalex.org/W3161254153","https://openalex.org/W3173990630","https://openalex.org/W3194594797","https://openalex.org/W3201871940","https://openalex.org/W3201922353","https://openalex.org/W6601846425"],"related_works":["https://openalex.org/W2068663075","https://openalex.org/W4205140848","https://openalex.org/W2978678743","https://openalex.org/W2797837731","https://openalex.org/W2150344375","https://openalex.org/W829257147","https://openalex.org/W3081389670","https://openalex.org/W4390832911","https://openalex.org/W4385302116","https://openalex.org/W4304080438"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"DavarOCR,":[3],"an":[4],"open-source":[5,40],"toolbox":[6],"for":[7,33,49],"OCR":[8,41,68],"and":[9,29,65,72],"document":[10,57],"understanding":[11],"tasks.":[12],"DavarOCR":[13,24,43,90],"currently":[14],"implements":[15],"19":[16],"advanced":[17],"algorithms,":[18],"covering":[19],"9":[20],"different":[21,84],"task":[22],"forms.":[23],"provides":[25],"detailed":[26],"usage":[27],"instructions":[28],"the":[30,38,50,53,63,79],"trained":[31],"models":[32],"each":[34],"algorithm.":[35],"Compared":[36],"with":[37],"previous":[39],"toolbox,":[42],"has":[44],"relatively":[45],"more":[46,76],"complete":[47],"support":[48],"sub-tasks":[51],"of":[52,56,67,81,86],"cutting-edge":[54],"technology":[55,69,87],"understanding.":[58],"In":[59],"order":[60],"to":[61,78],"promote":[62],"development":[64],"application":[66],"in":[70],"academia":[71],"industry,":[73],"we":[74],"pay":[75],"attention":[77],"use":[80],"modules":[82],"that":[83],"sub-domains":[85],"can":[88],"share.":[89],"is":[91],"publicly":[92],"released":[93],"at":[94],"https://github.com/hikopensource/Davar-Lab-OCR.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}