{"id":"https://openalex.org/W3206276570","doi":"https://doi.org/10.1145/3474085.3475423","title":"TDI TextSpotter: Taking Data Imbalance into Account in Scene Text Spotting","display_name":"TDI TextSpotter: Taking Data Imbalance into Account in Scene Text Spotting","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206276570","doi":"https://doi.org/10.1145/3474085.3475423","mag":"3206276570"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475423","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_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5101986556","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8376-3107"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"funder","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"funder","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008604905","display_name":"Shancheng Fang","orcid":"https://orcid.org/0000-0002-3100-3664"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"funder","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shancheng Fang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378720","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0003-4567-3869"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"funder","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Huawei Cloud & AI, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud & AI, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"funder","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengjun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"funder","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.239,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.645273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":75,"max":78},"biblio":{"volume":null,"issue":null,"first_page":"2510","last_page":"2518"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9999,"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":0.9999,"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":0.9987,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9899,"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/spotting","display_name":"Spotting","score":0.78780067},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness","score":0.7517402},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text Detection","score":0.7380102},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.5872255},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.4620902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79668224},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.78780067},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7517402},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.7380102},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.667869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63748336},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.5872255},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5002103},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48865297},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.4620902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4586816},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43455502},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.41885477},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.41335064},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2863641},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.13985202},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08683881},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475423","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_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.79}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":37,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1922126009","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2127141656","https://openalex.org/W2144554289","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2344822769","https://openalex.org/W2565639579","https://openalex.org/W2613718673","https://openalex.org/W2784050770","https://openalex.org/W2875814315","https://openalex.org/W2896034938","https://openalex.org/W2906333459","https://openalex.org/W2949229884","https://openalex.org/W2952302849","https://openalex.org/W2962773189","https://openalex.org/W2962986948","https://openalex.org/W2963150697","https://openalex.org/W2963299604","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2965463054","https://openalex.org/W2969477892","https://openalex.org/W2970910956","https://openalex.org/W2981969038","https://openalex.org/W2987563462","https://openalex.org/W2988098900","https://openalex.org/W2997351497","https://openalex.org/W2997371611","https://openalex.org/W3007389333","https://openalex.org/W3027134841","https://openalex.org/W3034792612","https://openalex.org/W3092834961","https://openalex.org/W3102695566","https://openalex.org/W3110398855"],"related_works":["https://openalex.org/W4286899409","https://openalex.org/W3206276570","https://openalex.org/W3134513473","https://openalex.org/W3003921261","https://openalex.org/W2988098900","https://openalex.org/W2982121298","https://openalex.org/W2982049215","https://openalex.org/W2972866811","https://openalex.org/W2949229884","https://openalex.org/W2875814315"],"abstract_inverted_index":{"Recent":[0],"scene":[1,61],"text":[2,6,28,32,39,52,62,93,129,139,153,169,183,187],"spotters":[3],"that":[4,160],"integrate":[5],"detection":[7,29,130,184],"module":[8,11,30,34,95,144],"and":[9,31,100,124,185,194],"recognition":[10,33,94],"have":[12],"made":[13],"significant":[14],"progress.":[15],"However,":[16],"existing":[17],"methods":[18,176],"encounter":[19],"two":[20],"problems.":[21,68],"1).":[22],"The":[23,42],"data":[24,75],"imbalance":[25,76],"issue":[26],"between":[27],"limits":[35],"the":[36,74,92,120,125,128,149,166,192],"performance":[37,167],"of":[38,87,127,152,168,196],"spotters.":[40],"2).":[41],"default":[43],"left-to-right":[44],"reading":[45,150],"direction":[46,142,151],"leads":[47],"to":[48,65,72,84,112,135,147],"errors":[49],"in":[50,70,133,181],"unconventional":[51],"spotting.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,78,104,141],"novel":[60],"spotter":[63],"TDI":[64],"solve":[66,73],"these":[67,161],"Firstly,":[69],"order":[71,134],"problem,":[77],"sample":[79,121],"generation":[80,108,122],"algorithm":[81,109,123],"is":[82,110,145],"proposed":[83,146],"generate":[85,113],"plenty":[86],"samples":[88],"online":[89],"for":[90,119],"training":[91,126],"by":[96],"using":[97],"character":[98,101,107],"features":[99],"labels.":[102],"Secondly,":[103],"weakly":[105],"supervised":[106],"designed":[111],"character-level":[114],"labels":[115,118],"from":[116],"word-level":[117],"module.":[131],"Finally,":[132],"spot":[136],"arbitrarily":[137],"arranged":[138],"correctly,":[140],"perception":[143],"perceive":[148],"instance.":[154],"Experiments":[155],"on":[156,177],"several":[157],"benchmarks":[158],"show":[159],"designs":[162],"can":[163],"significantly":[164],"improve":[165],"spotter.":[170],"Specifically,":[171],"our":[172,197],"method":[173],"outperforms":[174],"state-of-the-art":[175],"three":[178],"public":[179],"datasets":[180],"both":[182],"end-to-end":[186],"recognition,":[188],"which":[189],"fully":[190],"proves":[191],"effectiveness":[193],"robustness":[195],"method.":[198]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3206276570","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-04-16T15:25:24.589133","created_date":"2021-10-25"}