{"id":"https://openalex.org/W4313170256","doi":"https://doi.org/10.1109/icpr56361.2022.9956029","title":"IterVM: Iterative Vision Modeling Module for Scene Text Recognition","display_name":"IterVM: Iterative Vision Modeling Module for Scene Text Recognition","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4313170256","doi":"https://doi.org/10.1109/icpr56361.2022.9956029"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956029","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5073628283","display_name":"Xiaojie Chu","orcid":"https://orcid.org/0000-0003-3345-9283"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojie Chu","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781631","display_name":"Yongtao Wang","orcid":"https://orcid.org/0000-0003-1379-2206"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtao Wang","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073628283"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.301,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65014972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1393","last_page":"1399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9948999881744385,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9934999942779541,"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":0.8488278388977051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6450755596160889},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5592870116233826},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.513036847114563},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4820317029953003},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.45897147059440613},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4435093402862549},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.44101226329803467},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4110383987426758},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40018197894096375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11312973499298096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8488278388977051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6450755596160889},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5592870116233826},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.513036847114563},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4820317029953003},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.45897147059440613},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4435093402862549},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.44101226329803467},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4110383987426758},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40018197894096375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11312973499298096},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956029","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"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":52,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1660460062","https://openalex.org/W1686810756","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2593572697","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2752225195","https://openalex.org/W2788069964","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2896034938","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2963712589","https://openalex.org/W2965066169","https://openalex.org/W2998382406","https://openalex.org/W3004846386","https://openalex.org/W3005436539","https://openalex.org/W3013224334","https://openalex.org/W3034414401","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3042760913","https://openalex.org/W3092894544","https://openalex.org/W3103667010","https://openalex.org/W3106271744","https://openalex.org/W3110267192","https://openalex.org/W3134064484","https://openalex.org/W3173990630","https://openalex.org/W3175618949","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3202912918","https://openalex.org/W3206651063","https://openalex.org/W4385245566","https://openalex.org/W6629590909","https://openalex.org/W6637201659","https://openalex.org/W6637373629","https://openalex.org/W6649973027","https://openalex.org/W6739901393","https://openalex.org/W6744310024","https://openalex.org/W6752486419","https://openalex.org/W6780775906"],"related_works":["https://openalex.org/W1771726367","https://openalex.org/W2788561539","https://openalex.org/W2034475059","https://openalex.org/W144062141","https://openalex.org/W3006775069","https://openalex.org/W2895720711","https://openalex.org/W82507644","https://openalex.org/W2528330837","https://openalex.org/W2159155511","https://openalex.org/W1562083549"],"abstract_inverted_index":{"Scene":[0],"text":[1,140,156,163,169],"recognition":[2,157],"(STR)":[3],"is":[4],"a":[5,137],"challenging":[6,29],"problem":[7],"due":[8],"to":[9,26,39,78],"the":[10,42,46,55,61,81,85,93,97,104,111,114,121,126,148,154,166],"imperfect":[11],"imagery":[12],"conditions":[13],"in":[14],"natural":[15],"images.":[16,164],"State-of-the-art":[17],"methods":[18],"utilize":[19],"both":[20],"visual":[21,47],"cues":[22],"and":[23,96,107,181],"linguistic":[24],"knowledge":[25],"tackle":[27],"this":[28,68],"problem.":[30],"Specifically,":[31,84],"they":[32],"propose":[33,72,136],"iterative":[34,73,130],"language":[35,131],"modeling":[36,48,57,75,132],"module":[37,49,58,76],"(IterLM)":[38],"repeatedly":[40],"refine":[41],"output":[43],"sequence":[44],"from":[45,92,103],"(VM).":[50],"Though":[51],"achieving":[52],"promising":[53],"results,":[54],"vision":[56,74],"has":[59],"become":[60],"performance":[62],"bottleneck":[63],"of":[64],"these":[65],"methods.":[66],"In":[67],"paper,":[69],"we":[70,134],"newly":[71],"(IterVM)":[77],"further":[79,135],"improve":[80,153],"STR":[82],"accuracy.":[83],"first":[86],"VM":[87],"directly":[88],"extracts":[89],"multi-level":[90,101],"features":[91,102],"input":[94,105],"image,":[95],"following":[98],"VMs":[99],"re-extract":[100],"image":[106],"fuse":[108],"them":[109],"with":[110,129],"high-level":[112],"(i.e.,":[113],"most":[115],"semantic":[116],"one)":[117],"feature":[118],"extracted":[119],"by":[120],"previous":[122],"VM.":[123],"By":[124],"combining":[125],"proposed":[127,149,167],"IterVM":[128,150],"module,":[133],"powerful":[138],"scene":[139,155,162,168],"recognizer":[141,170],"called":[142],"IterNet.":[143],"Extensive":[144],"experiments":[145],"demonstrate":[146],"that":[147],"can":[151],"significantly":[152],"accuracy,":[158],"especially":[159],"on":[160,176],"low-quality":[161],"Moreover,":[165],"IterNet":[171],"achieves":[172],"new":[173],"state-of-the-art":[174],"results":[175],"several":[177],"public":[178],"benchmarks.":[179],"Codes":[180],"models":[182],"are":[183],"available":[184],"at":[185],"https://github.com/VDIGPKU/IterNet.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}