{"id":"https://openalex.org/W4214575780","doi":"https://doi.org/10.1145/3488933.3489039","title":"Multi-Scale Approach for Document Detection Based on the Cascade mask RCNN","display_name":"Multi-Scale Approach for Document Detection Based on the Cascade mask RCNN","publication_year":2021,"publication_date":"2021-09-24","ids":{"openalex":"https://openalex.org/W4214575780","doi":"https://doi.org/10.1145/3488933.3489039"},"language":"en","primary_location":{"id":"doi:10.1145/3488933.3489039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488933.3489039","pdf_url":null,"source":{"id":"https://openalex.org/S4363608564","display_name":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","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":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","raw_type":"proceedings-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/A5052308903","display_name":"Jiashan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiashan Tang","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028317852","display_name":"Tongwei Lu","orcid":"https://orcid.org/0000-0002-3900-6456"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Lu","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084293354","display_name":"Jixin Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixin Wei","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Robot,School of Computer ScienceampEngineering, Wuhan Institute of Technology, China","institution_ids":["https://openalex.org/I91125648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052308903"],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":null,"apc_paid":null,"fwci":0.1307,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52836982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T14319","display_name":"Currency Recognition and Detection","score":0.9922000169754028,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9919000267982483,"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":0.8295888304710388},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.8215151429176331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7556331157684326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7270388603210449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6552599668502808},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.48486456274986267},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4829408526420593},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05470472574234009},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.050310879945755005}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8295888304710388},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.8215151429176331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7556331157684326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7270388603210449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6552599668502808},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.48486456274986267},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4829408526420593},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05470472574234009},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.050310879945755005},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3488933.3489039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488933.3489039","pdf_url":null,"source":{"id":"https://openalex.org/S4363608564","display_name":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","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":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1983321062","https://openalex.org/W2109255472","https://openalex.org/W2165992492","https://openalex.org/W2949530802","https://openalex.org/W2963150697"],"related_works":["https://openalex.org/W1570447736","https://openalex.org/W2000329305","https://openalex.org/W2028369743","https://openalex.org/W2132155476","https://openalex.org/W4364376818","https://openalex.org/W2367062657","https://openalex.org/W4281635263","https://openalex.org/W2363475415","https://openalex.org/W2033709138","https://openalex.org/W2794420885"],"abstract_inverted_index":{"The":[0],"previous":[1],"traditional":[2],"methods":[3,16],"could":[4],"not":[5],"simultaneously":[6],"extract":[7],"every":[8],"region":[9],"and":[10,14,97,116,121],"represent":[11],"its":[12],"category,":[13],"these":[15],"needs":[17],"to":[18,36,39],"be":[19,82],"preprocessed":[20],"in":[21],"a":[22,32,41],"complex":[23],"way":[24],"for":[25],"the":[26,48,55,75,78,106,119],"document":[27,90],"image.":[28],"This":[29],"paper":[30],"presents":[31],"deep":[33],"learning-based":[34],"end":[35,37],"approach":[38],"solve":[40],"problem":[42],"that":[43,102],"is":[44,52],"sample":[45],"imbalance.":[46],"Specifically,":[47],"single-scale":[49],"training":[50],"strategy":[51],"replaced":[53],"by":[54,114],"proposed":[56],"multi-scale":[57],"on":[58,73,118],"Cascade":[59,110],"mask":[60,111],"-RCNN":[61,112],"which":[62],"consisted":[63],"of":[64,77,89,109],"three":[65],"detectors":[66],"trained":[67],"with":[68,104],"increasing":[69],"IoU":[70],"thresholds,":[71],"based":[72],"this,":[74],"robustness":[76],"detection":[79],"networks":[80],"can":[81,86],"improved":[83],".This":[84],"model":[85],"detects":[87],"areas":[88],"images,":[91],"including":[92],"paragraphs,":[93],"text,":[94],"formulas,":[95],"pictures,":[96],"tables.":[98],"Extensive":[99],"experiments":[100],"show":[101],"compared":[103],"Mask-RCNN,":[105],"AP":[107],"scores":[108],"increased":[113],"0.031":[115],"0.037":[117],"Publaynet":[120],"ICDAR":[122],"2017":[123],"datasets,":[124],"respectively.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}