{"id":"https://openalex.org/W4406047244","doi":"https://doi.org/10.1109/tpami.2025.3525526","title":"Instruction-Guided Scene Text Recognition","display_name":"Instruction-Guided Scene Text Recognition","publication_year":2025,"publication_date":"2025-01-03","ids":{"openalex":"https://openalex.org/W4406047244","doi":"https://doi.org/10.1109/tpami.2025.3525526","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030880"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3525526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3525526","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/A5102915298","display_name":"Yongkun Du","orcid":"https://orcid.org/0009-0005-3114-2188"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkun Du","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-3114-2188","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080463909","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1543-6889","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101940296","display_name":"Yuchen Su","orcid":"https://orcid.org/0000-0001-7743-8260"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Su","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7743-8260","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085282915","display_name":"Caiyan Jia","orcid":"https://orcid.org/0000-0003-0650-9564"},"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":"Caiyan Jia","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0650-9564","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.014,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.98994076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"47","issue":"4","first_page":"2723","last_page":"2738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9966999888420105,"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":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9624000191688538,"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"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7009553909301758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6400760412216187},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.47988998889923096},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4496331214904785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42922258377075195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40288299322128296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38385242223739624},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22871440649032593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009553909301758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6400760412216187},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.47988998889923096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4496331214904785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42922258377075195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40288299322128296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38385242223739624},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22871440649032593}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3525526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3525526","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:40030880","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030880","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/G1952609169","display_name":null,"funder_award_id":"2022YFB3104703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6146631126","display_name":null,"funder_award_id":"62172103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7791778128","display_name":null,"funder_award_id":"32341012","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1933349210","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2127141656","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2810983211","https://openalex.org/W2896457183","https://openalex.org/W2963526661","https://openalex.org/W2965066169","https://openalex.org/W2978036638","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W3003642782","https://openalex.org/W3034414401","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3110267192","https://openalex.org/W3175855397","https://openalex.org/W3177505580","https://openalex.org/W3179897446","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3206651063","https://openalex.org/W4225562651","https://openalex.org/W4226329156","https://openalex.org/W4229030834","https://openalex.org/W4283805255","https://openalex.org/W4283821822","https://openalex.org/W4310335763","https://openalex.org/W4312298799","https://openalex.org/W4312787220","https://openalex.org/W4312800234","https://openalex.org/W4312843595","https://openalex.org/W4312879041","https://openalex.org/W4312956471","https://openalex.org/W4313045695","https://openalex.org/W4385245566","https://openalex.org/W4385767840","https://openalex.org/W4385767967","https://openalex.org/W4386065575","https://openalex.org/W4386410320","https://openalex.org/W4388157921","https://openalex.org/W4389524500","https://openalex.org/W4390463734","https://openalex.org/W4390871832","https://openalex.org/W4390872070","https://openalex.org/W4390872592","https://openalex.org/W4390873548","https://openalex.org/W4390873795","https://openalex.org/W4390874575","https://openalex.org/W4391128821","https://openalex.org/W4393148058","https://openalex.org/W4393148285","https://openalex.org/W4402716330","https://openalex.org/W4402753732","https://openalex.org/W4404612908","https://openalex.org/W4407937981","https://openalex.org/W6629590909","https://openalex.org/W6726497184","https://openalex.org/W6757817989","https://openalex.org/W6771043271","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6810334672","https://openalex.org/W6810773572","https://openalex.org/W6839015040","https://openalex.org/W6839401645","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852818750","https://openalex.org/W6854989695","https://openalex.org/W6856754025","https://openalex.org/W6862276026"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Multi-modal":[0],"models":[1,24,151],"have":[2],"shown":[3],"appealing":[4],"performance":[5],"in":[6],"visual":[7,20],"recognition":[8,32,51,121,180],"tasks,":[9],"as":[10,57],"free-form":[11],"text-guided":[12],"training":[13],"evokes":[14],"the":[15,36,168,179],"ability":[16],"to":[17,29,35,177],"understand":[18],"fine-grained":[19],"content.":[21],"However,":[22],"current":[23,137],"cannot":[25],"be":[26],"trivially":[27],"applied":[28],"scene":[30,49],"text":[31,42,50,64,114,131],"(STR)":[33],"due":[34],"compositional":[37],"difference":[38],"between":[39],"natural":[40],"and":[41,62,82,106,143,161,184],"images.":[43],"We":[44],"propose":[45],"a":[46,97,101,107,129,157],"novel":[47],"instruction-guided":[48],"(IGTR)":[52],"paradigm":[53,133],"that":[54,134,147],"formulates":[55],"STR":[56],"an":[58,174],"instruction":[59,78,99],"learning":[60],"problem":[61],"understands":[63],"images":[65],"by":[66,124,152,166],"predicting":[67],"character":[68,71,86],"attributes,":[69],"e.g.,":[70],"frequency,":[72],"position,":[73],"etc.":[74],"IGTR":[75,95,118,148,172],"first":[76],"devises":[77],"triplets,":[79],"providing":[80],"rich":[81],"diverse":[83],"descriptions":[84],"of":[85,170,181],"attributes.":[87],"To":[88],"effectively":[89],"learn":[90],"these":[91],"attributes":[92],"through":[93],"question-answering,":[94],"develops":[96],"lightweight":[98],"encoder,":[100],"cross-modal":[102],"feature":[103],"fusion":[104],"module":[105],"multi-task":[108],"answer":[109],"head,":[110],"which":[111,188],"guides":[112],"nuanced":[113],"image":[115],"understanding.":[116],"Furthermore,":[117],"realizes":[119],"different":[120,126],"pipelines":[122],"simply":[123],"using":[125],"instructions,":[127,171],"enabling":[128],"character-understanding-based":[130],"reasoning":[132],"differs":[135],"from":[136],"methods":[138],"considerably.":[139],"Experiments":[140],"on":[141],"English":[142],"Chinese":[144],"benchmarks":[145],"show":[146],"outperforms":[149],"existing":[150],"significant":[153],"margins,":[154],"while":[155],"maintaining":[156],"small":[158],"model":[159],"size":[160],"fast":[162],"inference":[163],"speed.":[164],"Moreover,":[165],"adjusting":[167],"sampling":[169],"offers":[173],"elegant":[175],"way":[176],"tackle":[178],"rarely":[182],"appearing":[183],"morphologically":[185],"similar":[186],"characters,":[187],"were":[189],"previous":[190],"challenges.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}