{"id":"https://openalex.org/W4214922754","doi":"https://doi.org/10.1109/tpami.2022.3155612","title":"Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion","display_name":"Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion","publication_year":2022,"publication_date":"2022-03-03","ids":{"openalex":"https://openalex.org/W4214922754","doi":"https://doi.org/10.1109/tpami.2022.3155612","pmid":"https://pubmed.ncbi.nlm.nih.gov/35239474"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3155612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3155612","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5030174783","display_name":"Minghui Liao","orcid":"https://orcid.org/0000-0002-2583-4314"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minghui Liao","raw_affiliation_strings":["Huawei Cloud, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2583-4314","affiliations":[{"raw_affiliation_string":"Huawei Cloud, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071354796","display_name":"Zhisheng Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhisheng Zou","raw_affiliation_strings":["WeRide, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeRide, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042537847","display_name":"Zhaoyi Wan","orcid":"https://orcid.org/0000-0002-1994-260X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoyi Wan","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-1994-260X","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669593","display_name":"Cong Yao","orcid":"https://orcid.org/0000-0001-6564-4796"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Yao","raw_affiliation_strings":["Alibaba DAMO Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6564-4796","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3449-5940","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030174783"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":36.6443,"has_fulltext":false,"cited_by_count":392,"citation_normalized_percentile":{"value":0.99876001,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"45","issue":"1","first_page":"919","last_page":"931"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9990000128746033,"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":0.9965000152587891,"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/robustness","display_name":"Robustness (evolution)","score":0.8332515954971313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695045471191406},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7571338415145874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7431825399398804},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5515701770782471},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.530702531337738},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5143759846687317},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5100958943367004},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49085408449172974},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4728429913520813},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45635393261909485},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.45525890588760376},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4240276515483856}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8332515954971313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695045471191406},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7571338415145874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7431825399398804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5515701770782471},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.530702531337738},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5143759846687317},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5100958943367004},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49085408449172974},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4728429913520813},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.45635393261909485},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.45525890588760376},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4240276515483856},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3155612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3155612","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35239474","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35239474","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3418581704","display_name":null,"funder_award_id":"61733007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1972065312","https://openalex.org/W1988461287","https://openalex.org/W2061802763","https://openalex.org/W2074849287","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2217433794","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2560023338","https://openalex.org/W2563705555","https://openalex.org/W2565639579","https://openalex.org/W2593539516","https://openalex.org/W2601564443","https://openalex.org/W2604243686","https://openalex.org/W2604735854","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2630837129","https://openalex.org/W2752782242","https://openalex.org/W2766895242","https://openalex.org/W2784050770","https://openalex.org/W2799166040","https://openalex.org/W2810028092","https://openalex.org/W2831607544","https://openalex.org/W2875814315","https://openalex.org/W2884585870","https://openalex.org/W2902494497","https://openalex.org/W2914492226","https://openalex.org/W2953606406","https://openalex.org/W2953894958","https://openalex.org/W2955058313","https://openalex.org/W2962804639","https://openalex.org/W2962810613","https://openalex.org/W2963150697","https://openalex.org/W2963161243","https://openalex.org/W2963299604","https://openalex.org/W2963353821","https://openalex.org/W2963398399","https://openalex.org/W2963495494","https://openalex.org/W2963647456","https://openalex.org/W2963807362","https://openalex.org/W2963840241","https://openalex.org/W2963977642","https://openalex.org/W2964294787","https://openalex.org/W2964309882","https://openalex.org/W2964685115","https://openalex.org/W2966926453","https://openalex.org/W2967591398","https://openalex.org/W2967615747","https://openalex.org/W2968226676","https://openalex.org/W2970910956","https://openalex.org/W2981689412","https://openalex.org/W2981899103","https://openalex.org/W2982220924","https://openalex.org/W2990032492","https://openalex.org/W2990775046","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W3034958977","https://openalex.org/W3082397598","https://openalex.org/W3097932944","https://openalex.org/W3102695566","https://openalex.org/W3106228955","https://openalex.org/W3106250896","https://openalex.org/W6639824700","https://openalex.org/W6642972425","https://openalex.org/W6739696289","https://openalex.org/W6748481559","https://openalex.org/W6753412334","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3144569342","https://openalex.org/W2185902295","https://openalex.org/W2945274617","https://openalex.org/W2103507220","https://openalex.org/W2055202857","https://openalex.org/W1999008862","https://openalex.org/W2371519352","https://openalex.org/W4205800335","https://openalex.org/W2386644571","https://openalex.org/W2551987074"],"abstract_inverted_index":{"Recently,":[0],"segmentation-based":[1,44],"scene":[2,12,179],"text":[3,13,23,138,180],"detection":[4,14,139,190],"methods":[5],"have":[6],"drawn":[7],"extensive":[8],"attention":[9],"in":[10,20,110,186],"the":[11,22,34,38,42,54,62,70,77,101,106,111,121,125,135,156,168,174],"field,":[15],"because":[16],"of":[17,25,41,57,105,137,162,188],"their":[18,49,58],"superiority":[19],"detecting":[21],"instances":[24],"arbitrary":[26],"shapes":[27],"and":[28,53,76,171,192],"extreme":[29],"aspect":[30],"ratios,":[31],"profiting":[32],"from":[33],"pixel-level":[35],"descriptions.":[36],"However,":[37],"vast":[39],"majority":[40],"existing":[43],"approaches":[45],"are":[46,65],"limited":[47],"to":[48,69,154],"complex":[50],"post-processing":[51,63,112],"algorithms":[52,64],"scale":[55,78,157],"robustness":[56,79,158],"segmentation":[59,116,126,175],"models,":[60],"where":[61],"not":[66],"only":[67],"isolated":[68],"model":[71],"optimization":[72],"but":[73],"also":[74],"time-consuming":[75],"is":[80,152],"usually":[81],"strengthened":[82],"by":[83,159],"fusing":[84,160],"multi-scale":[85],"feature":[86],"maps":[87],"directly.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"propose":[93],"a":[94,115,141],"Differentiable":[95],"Binarization":[96],"(DB)":[97],"module":[98,151],"that":[99],"integrates":[100],"binarization":[102],"process,":[103],"one":[104],"most":[107],"important":[108],"steps":[109],"procedure,":[113],"into":[114],"network.":[117],"Optimized":[118],"along":[119],"with":[120,140,173],"proposed":[122,153,169,178],"DB":[123,170],"module,":[124],"network":[127],"can":[128],"produce":[129],"more":[130],"accurate":[131],"results,":[132,185],"which":[133],"enhances":[134],"accuracy":[136,191],"simple":[142],"pipeline.":[143],"Furthermore,":[144],"an":[145],"efficient":[146],"Adaptive":[147],"Scale":[148],"Fusion":[149],"(ASF)":[150],"improve":[155],"features":[161],"different":[163],"scales":[164],"adaptively.":[165],"By":[166],"incorporating":[167],"ASF":[172],"network,":[176],"our":[177],"detector":[181],"consistently":[182],"achieves":[183],"state-of-the-art":[184],"terms":[187],"both":[189],"speed,":[193],"on":[194],"five":[195],"standard":[196],"benchmarks.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":114},{"year":2024,"cited_by_count":138},{"year":2023,"cited_by_count":96},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}