{"id":"https://openalex.org/W3205961173","doi":"https://doi.org/10.1145/3474085.3478328","title":"MMOCR","display_name":"MMOCR","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205961173","doi":"https://doi.org/10.1145/3474085.3478328","mag":"3205961173"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3478328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5054299179","display_name":"Zhanghui Kuang","orcid":"https://orcid.org/0000-0002-9102-5152"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanghui Kuang","raw_affiliation_strings":["SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706021","display_name":"Hongbin Sun","orcid":"https://orcid.org/0000-0001-9183-4462"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Sun","raw_affiliation_strings":["SenseTime Research, Shen Zhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shen Zhen, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742450","display_name":"Zhizhong Li","orcid":"https://orcid.org/0000-0003-0574-2487"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhizhong Li","raw_affiliation_strings":["SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068378871","display_name":"Xiaoyu Yue","orcid":"https://orcid.org/0000-0001-7023-0264"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyu Yue","raw_affiliation_strings":["Center for Perceptual and Interactive Intelligence, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Perceptual and Interactive Intelligence, Hong Kong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005848691","display_name":"Tsui Hin Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tsui Hin Lin","raw_affiliation_strings":["SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044377595","display_name":"Jianyong Chen","orcid":"https://orcid.org/0000-0002-6203-1254"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyong Chen","raw_affiliation_strings":["South China University of Technology, Guang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guang Zhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015033337","display_name":"Huaqiang Wei","orcid":"https://orcid.org/0000-0002-1590-7612"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaqiang Wei","raw_affiliation_strings":["SenseTime Research, Shen Zhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shen Zhen, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013642582","display_name":"Yiqin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqin Zhu","raw_affiliation_strings":["South China University of Technology, Guang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guang Zhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935395","display_name":"Tong Gao","orcid":"https://orcid.org/0009-0006-6706-6284"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Gao","raw_affiliation_strings":["SenseTime Research, Shen Zhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shen Zhen, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709483","display_name":"Wenwei Zhang","orcid":"https://orcid.org/0000-0003-0704-9029"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Wenwei Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437924","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6384-0355"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["SenseTime Research & Shanghai AI Laboratory, Guang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research & Shanghai AI Laboratory, Guang Zhou, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057842914","display_name":"Wayne Zhang","orcid":"https://orcid.org/0000-0002-8415-1062"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Wayne Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3791","last_page":"3794"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.845690131187439},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.7384893298149109},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.669751763343811},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6164089441299438},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5468605756759644},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.4776107966899872},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4585454761981964},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42594587802886963},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4143630266189575},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39618679881095886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3477823734283447},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33987855911254883},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.25009381771087646},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15826529264450073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845690131187439},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.7384893298149109},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.669751763343811},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6164089441299438},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5468605756759644},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4776107966899872},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4585454761981964},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42594587802886963},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4143630266189575},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39618679881095886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3477823734283447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33987855911254883},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25009381771087646},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15826529264450073},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3478328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1903029394","https://openalex.org/W2001642682","https://openalex.org/W2097117768","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2570343428","https://openalex.org/W2593572697","https://openalex.org/W2748159032","https://openalex.org/W2808142148","https://openalex.org/W2809273748","https://openalex.org/W2810028092","https://openalex.org/W2962688956","https://openalex.org/W2962835968","https://openalex.org/W2963517393","https://openalex.org/W2963625095","https://openalex.org/W2963647456","https://openalex.org/W2967155990","https://openalex.org/W2967615747","https://openalex.org/W2979371747","https://openalex.org/W2989889352","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W3005436539","https://openalex.org/W3014074635","https://openalex.org/W3034514377","https://openalex.org/W3101769104","https://openalex.org/W3110267192","https://openalex.org/W3152831436","https://openalex.org/W3163650427","https://openalex.org/W3175248253","https://openalex.org/W3181016597"],"related_works":["https://openalex.org/W4304080438","https://openalex.org/W2963339673","https://openalex.org/W4285594464","https://openalex.org/W2795728081","https://openalex.org/W3163712264","https://openalex.org/W4306707571","https://openalex.org/W3179897446","https://openalex.org/W2970150031","https://openalex.org/W4309224528","https://openalex.org/W1562999394"],"abstract_inverted_index":{"We":[0],"present":[1],"MMOCR---an":[2],"open-source":[3,43],"toolbox":[4],"which":[5,35],"provides":[6],"a":[7,66],"comprehensive":[8],"pipeline":[9],"for":[10],"text":[11,60,82],"detection":[12],"and":[13,26,56,72,85],"recognition,":[14],"as":[15,17,22],"well":[16],"their":[18],"downstream":[19],"tasks":[20],"such":[21],"named":[23],"entity":[24],"recognition":[25,84],"key":[27],"information":[28],"extraction.":[29],"MMOCR":[30,87],"implements":[31],"14":[32],"state-of-the-art":[33],"algorithms,":[34],"is":[36,88],"significantly":[37],"more":[38],"than":[39],"all":[40],"the":[41,79],"existing":[42],"OCR":[44],"projects":[45],"we":[46,63],"are":[47],"aware":[48],"of":[49,59,69,81],"to":[50,75],"date.":[51],"To":[52],"facilitate":[53],"future":[54],"research":[55],"industrial":[57],"applications":[58],"recognition-related":[61],"problems,":[62],"also":[64],"provide":[65],"large":[67],"number":[68],"trained":[70],"models":[71],"detailed":[73],"benchmarks":[74],"give":[76],"insights":[77],"into":[78],"performance":[80],"detection,":[83],"understanding.":[86],"publicly":[89],"released":[90],"at":[91],"https://github.com/open-mmlab/mmocr.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-10-25T00:00:00"}