{"id":"https://openalex.org/W3203616741","doi":"https://doi.org/10.1109/tai.2021.3116216","title":"Character-Level Street View Text Spotting Based on Deep Multisegmentation Network for Smarter Autonomous Driving","display_name":"Character-Level Street View Text Spotting Based on Deep Multisegmentation Network for Smarter Autonomous Driving","publication_year":2021,"publication_date":"2021-09-28","ids":{"openalex":"https://openalex.org/W3203616741","doi":"https://doi.org/10.1109/tai.2021.3116216","mag":"3203616741"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2021.3116216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2021.3116216","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Artificial Intelligence","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/A5091464412","display_name":"Chongsheng Zhang","orcid":"https://orcid.org/0000-0003-1632-7238"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chongsheng Zhang","raw_affiliation_strings":["Henan Provincial Key Laboratory of Big Data Analysis and Processing and Laboratory of the Yellow River Cultural Heritage, Henan University, Kaifeng, China"],"affiliations":[{"raw_affiliation_string":"Henan Provincial Key Laboratory of Big Data Analysis and Processing and Laboratory of the Yellow River Cultural Heritage, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014513350","display_name":"Yuefeng Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuefeng Tao","raw_affiliation_strings":["Henan Provincial Key Laboratory of Big Data Analysis and Processing and Laboratory of the Yellow River Cultural Heritage, Henan University, Kaifeng, China"],"affiliations":[{"raw_affiliation_string":"Henan Provincial Key Laboratory of Big Data Analysis and Processing and Laboratory of the Yellow River Cultural Heritage, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103451458","display_name":"Kai Du","orcid":null},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Du","raw_affiliation_strings":["Henan Provincial Key Laboratory of Big Data Analysis and Processing and Laboratory of the Yellow River Cultural Heritage, Henan University, Kaifeng, China"],"affiliations":[{"raw_affiliation_string":"Henan Provincial Key Laboratory of Big Data Analysis and Processing and Laboratory of the Yellow River Cultural Heritage, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069969191","display_name":"Weiping Ding","orcid":"https://orcid.org/0000-0002-3180-7347"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Ding","raw_affiliation_strings":["School of Information Science and Technology, Nantong University, Nantong, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108156794","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-3790-2708"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["School of Electrical Engineering, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396339","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0003-4710-5697"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Big Data Lab, Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Big Data Lab, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100777576","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-5974-1589"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091464412"],"corresponding_institution_ids":["https://openalex.org/I173899330"],"apc_list":null,"apc_paid":null,"fwci":2.9139,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.92603311,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"3","issue":"2","first_page":"297","last_page":"308"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.646612286567688},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5841134190559387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5612291097640991},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5402540564537048},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.519080638885498},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4881192147731781},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4687994122505188},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4540598392486572},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3664628863334656},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3546314835548401},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3402032256126404},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13456851243972778},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08269217610359192},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07751122117042542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.646612286567688},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5841134190559387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612291097640991},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5402540564537048},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.519080638885498},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4881192147731781},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4687994122505188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4540598392486572},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3664628863334656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3546314835548401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3402032256126404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13456851243972778},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08269217610359192},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07751122117042542},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2021.3116216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2021.3116216","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322878","display_name":"Henan University","ror":"https://ror.org/003xyzq10"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1972065312","https://openalex.org/W2127141656","https://openalex.org/W2194187530","https://openalex.org/W2275041823","https://openalex.org/W2340897893","https://openalex.org/W2515655118","https://openalex.org/W2519818067","https://openalex.org/W2604735854","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2620629206","https://openalex.org/W2784050770","https://openalex.org/W2787091153","https://openalex.org/W2799213142","https://openalex.org/W2810983211","https://openalex.org/W2945136398","https://openalex.org/W2948535054","https://openalex.org/W2950666050","https://openalex.org/W2963150697","https://openalex.org/W2963240573","https://openalex.org/W2963840241","https://openalex.org/W2964065044","https://openalex.org/W2967372292","https://openalex.org/W2967615747","https://openalex.org/W2983626510","https://openalex.org/W2988098900","https://openalex.org/W2997749585","https://openalex.org/W2998621280","https://openalex.org/W3003711889","https://openalex.org/W3011075597","https://openalex.org/W3011933327","https://openalex.org/W3034514377","https://openalex.org/W3034792612","https://openalex.org/W3034942609","https://openalex.org/W3035222584","https://openalex.org/W3035679705","https://openalex.org/W3048083653","https://openalex.org/W3083321694","https://openalex.org/W3102695566","https://openalex.org/W3110398855","https://openalex.org/W3111172959","https://openalex.org/W3152831436","https://openalex.org/W3173990630","https://openalex.org/W3174658120","https://openalex.org/W3175849542","https://openalex.org/W3175855397","https://openalex.org/W3186906052","https://openalex.org/W6726347659","https://openalex.org/W6760424586"],"related_works":["https://openalex.org/W2060724872","https://openalex.org/W2082094785","https://openalex.org/W2202198356","https://openalex.org/W3087203342","https://openalex.org/W2377184161","https://openalex.org/W228984114","https://openalex.org/W2090026684","https://openalex.org/W4226360758","https://openalex.org/W2151093953","https://openalex.org/W2907567977"],"abstract_inverted_index":{"Urban":[0],"scenes":[1,30],"are":[2],"full":[3],"of":[4,28,106,145,194],"street":[5,14],"entities":[6],"with":[7,169],"sign":[8],"boards.":[9],"Therefore,":[10],"in":[11,24,36,149],"autonomous":[12],"driving,":[13,32],"view":[15],"text":[16,120,167,187,201,206,216,223],"spotting":[17,168],"techniques":[18],"will":[19],"play":[20],"a":[21,68,93,125],"significant":[22],"role":[23],"the":[25,37,103,107,139,143,146,151,155,160,191,195,209,213,220],"precise":[26],"understanding":[27],"surrounding":[29],"during":[31],"because":[33],"texts":[34],"contained":[35],"images":[38,60],"usually":[39],"provide":[40],"important":[41],"clues":[42],"for":[43,52,78],"accurate":[44],"image":[45],"understanding,":[46],"while":[47],"it":[48,123],"is":[49],"often":[50],"ambiguous":[51],"existing":[53],"computer":[54],"vision":[55],"algorithms":[56],"to":[57,101,113,129,137,189],"understand":[58],"scene":[59,80,166,186,205,215,222],"without":[61],"texts.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"propose":[67],"<bold":[69,73,81,85],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[70,74,82,86],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</b>":[71],"ulti-":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</b>":[75],"egmentation":[76],"network":[77,140],"character-level":[79,198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</b>":[83],"ext":[84],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</b>":[87],"etection":[88],"(MSTD).":[89],"The":[90],"MSTD":[91,196,210],"introduces":[92],"densely":[94],"connected":[95],"atrous":[96],"spatial":[97],"pyramid":[98],"pooling":[99],"module":[100],"enlarge":[102],"receptive":[104],"field":[105],"feature":[108],"extraction":[109],"layer,":[110],"so":[111],"as":[112,116,118,175],"localize":[114],"long":[115],"well":[117],"large-sized":[119],"instances.":[121],"Moreover,":[122],"devises":[124],"double":[126],"segmentation":[127],"subnetwork":[128],"utilize":[130],"two":[131],"independent":[132],"but":[133],"inherently":[134],"complementary":[135],"losses":[136],"co-optimize":[138],"and":[141,177,199,204,219],"increase":[142],"reliability":[144],"confidence":[147],"scores":[148],"predicting":[150],"text/nontext":[152],"areas.":[153],"With":[154],"character":[156],"instances":[157],"detected":[158],"by":[159],"MSTD,":[161],"one":[162],"can":[163],"easily":[164],"perform":[165],"classic":[170],"object":[171],"recognition":[172],"networks":[173],"such":[174],"ResNet":[176],"DenseNet.":[178],"We":[179],"carried":[180],"out":[181],"extensive":[182],"experiments":[183],"on":[184,197],"nine":[185],"datasets":[188],"demonstrate":[190],"outstanding":[192],"performance":[193],"line-level":[200],"instance":[202],"localization":[203],"recognition,":[207],"where":[208],"significantly":[211],"outperforms":[212],"state-of-the-art":[214],"detection":[217],"methods":[218],"sequence-to-sequence-learning-based":[221],"recognizers.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}