{"id":"https://openalex.org/W4410192162","doi":"https://doi.org/10.1145/3734872","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","display_name":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410192162","doi":"https://doi.org/10.1145/3734872"},"language":"en","primary_location":{"id":"doi:10.1145/3734872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3734872","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5077828258","display_name":"Jiahao Lyu","orcid":"https://orcid.org/0000-0003-2051-8045"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahao Lyu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674793","display_name":"Wei Jin","orcid":"https://orcid.org/0000-0003-2016-0901"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wei","raw_affiliation_strings":["Lenovo Group Ltd, Lenovo Research, Beijing, China","Lenovo Research, China"],"affiliations":[{"raw_affiliation_string":"Lenovo Group Ltd, Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"Lenovo Research, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046229717","display_name":"Gangyan Zeng","orcid":"https://orcid.org/0000-0003-2696-8549"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangyan Zeng","raw_affiliation_strings":["School of Cyber Science and Engineering, Nanjing University of Science and Technology, Jiangyin, China","School of Cyber Science and Engineering, Nanjing University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Nanjing University of Science and Technology, Jiangyin, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570690","display_name":"Li Zeng","orcid":"https://orcid.org/0009-0008-7075-1869"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070013530","display_name":"Enze Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enze Xie","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103128509","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-6847-469X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Wei Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China","Shanghai Artificial Intelligence Laboratory, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101021225","display_name":"Can Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Ma","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["VCIP &amp; TMCC &amp; DISSec, College of Computer Science, Nankai University, Tianjin, China","VCIP &amp; TMCC &amp; DISSec, College of Computer Science, Nankai University, China"],"affiliations":[{"raw_affiliation_string":"VCIP &amp; TMCC &amp; DISSec, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"VCIP &amp; TMCC &amp; DISSec, College of Computer Science, Nankai University, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5077828258"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.5568,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89158077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"21","issue":"6","first_page":"1","last_page":"21"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9267404675483704},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8758574724197388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5908485651016235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5697766542434692},{"id":"https://openalex.org/keywords/hands-free","display_name":"Hands free","score":0.5066736340522766},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5039874911308289},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38237273693084717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37063395977020264},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3506599962711334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9267404675483704},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8758574724197388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5908485651016235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5697766542434692},{"id":"https://openalex.org/C3018339088","wikidata":"https://www.wikidata.org/wiki/Q28460","display_name":"Hands free","level":2,"score":0.5066736340522766},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5039874911308289},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38237273693084717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37063395977020264},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3506599962711334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3734872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3734872","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3171905462","display_name":null,"funder_award_id":"62376266 and 62406318","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W2194187530","https://openalex.org/W2945260553","https://openalex.org/W2963150697","https://openalex.org/W2965066169","https://openalex.org/W2970910956","https://openalex.org/W2983626510","https://openalex.org/W2996609910","https://openalex.org/W2997351497","https://openalex.org/W2998382406","https://openalex.org/W3014074635","https://openalex.org/W3034792612","https://openalex.org/W3035449864","https://openalex.org/W3111172959","https://openalex.org/W3154631726","https://openalex.org/W3157738407","https://openalex.org/W3181186176","https://openalex.org/W3185705915","https://openalex.org/W3196976036","https://openalex.org/W3199928321","https://openalex.org/W4224232320","https://openalex.org/W4226020328","https://openalex.org/W4287186597","https://openalex.org/W4302617179","https://openalex.org/W4309795858","https://openalex.org/W4310335763","https://openalex.org/W4312879041","https://openalex.org/W4312988011","https://openalex.org/W4317677707","https://openalex.org/W4382202677","https://openalex.org/W4385767964","https://openalex.org/W4386302310","https://openalex.org/W4388848051","https://openalex.org/W4390874051","https://openalex.org/W4393979362","https://openalex.org/W4403580612","https://openalex.org/W4405433631","https://openalex.org/W4405562095","https://openalex.org/W4405627750","https://openalex.org/W4409366302","https://openalex.org/W4409367174","https://openalex.org/W4409367990","https://openalex.org/W6748634344"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W2058491579","https://openalex.org/W1483316057","https://openalex.org/W2095257897","https://openalex.org/W4285801728","https://openalex.org/W50227226","https://openalex.org/W2611015909","https://openalex.org/W2133855304"],"abstract_inverted_index":{"Existing":[0],"scene":[1,27,74,87,163,181,198],"text":[2,69,75,88,108,170,182],"spotters":[3],"are":[4],"designed":[5],"to":[6,20,93,110,125,191,200],"locate":[7],"and":[8,24,39,64,152,166],"transcribe":[9],"texts":[10,28,56,193],"from":[11,130,195],"images.":[12],"However,":[13],"it":[14],"is":[15],"challenging":[16],"for":[17,73,106],"a":[18,103,118,121],"spotter":[19,89,183],"achieve":[21,126],"precise":[22,58],"detection":[23,59,109],"recognition":[25,142,164],"of":[26,36,42,157,169,179,204],"simultaneously.":[29],"Inspired":[30],"by":[31],"the":[32,131,137,140,158,167,176,202],"glimpse-focus":[33],"spotting":[34,76],"pipeline":[35],"human":[37,62],"beings":[38],"impressive":[40],"performances":[41],"Pre-trained":[43],"Language":[44,208],"Models":[45,209],"(PLMs)":[46],"on":[47,162],"visual":[48],"tasks,":[49],"we":[50,100,116,189],"ask:":[51],"(1)":[52],"\u201cCan":[53],"machines":[54],"spot":[55,192],"without":[57,96],"just":[60],"like":[61],"beings?\u201d,":[63],"if":[65],"yes,":[66],"(2)":[67],"\u201cIs":[68],"block":[70,171],"another":[71],"alternative":[72],"other":[77],"than":[78],"word":[79],"or":[80],"character?\u201d":[81],"To":[82],"this":[83],"end,":[84],"our":[85,180],"proposed":[86],"leverages":[90],"advanced":[91],"PLMs":[92],"enhance":[94],"performance":[95,178],"fine-grained":[97],"detection.":[98],"Specifically,":[99],"first":[101],"use":[102],"simple":[104],"detector":[105],"block-level":[107],"obtain":[111],"rough":[112],"positional":[113],"information.":[114],"Then,":[115],"fine-tune":[117],"PLM":[119],"using":[120],"large-scale":[122],"OCR":[123],"dataset":[124],"accurate":[127],"recognition.":[128],"Benefiting":[129],"comprehensive":[132],"language":[133,160],"knowledge":[134],"gained":[135],"during":[136],"pre-training":[138],"phase,":[139],"PLM-based":[141],"module":[143],"effectively":[144],"handles":[145],"complex":[146],"scenarios,":[147],"including":[148],"multi-line,":[149],"reversed,":[150],"occluded,":[151],"incomplete-detection":[153],"texts.":[154],"Taking":[155],"advantage":[156],"fine-tuned":[159],"model":[161],"benchmarks":[165],"paradigm":[168],"detection,":[172],"extensive":[173],"experiments":[174],"demonstrate":[175,201],"superior":[177],"across":[184],"multiple":[185],"public":[186],"benchmarks.":[187],"Additionally,":[188],"attempt":[190],"directly":[194],"an":[196],"entire":[197],"image":[199],"potential":[203],"PLMs,":[205],"even":[206],"Large":[207],"(LLMs).":[210]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
