{"id":"https://openalex.org/W4415593702","doi":"https://doi.org/10.1109/tcsvt.2025.3625758","title":"Summarize Before Glimpse: Brain-Inspired Non-Autoregressive Scene Text Recognizer","display_name":"Summarize Before Glimpse: Brain-Inspired Non-Autoregressive Scene Text Recognizer","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415593702","doi":"https://doi.org/10.1109/tcsvt.2025.3625758"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3625758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3625758","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5013971053","display_name":"Dekang Liu","orcid":"https://orcid.org/0000-0003-1630-5928"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dekang Liu","raw_affiliation_strings":["Machine Learning and I-health International Cooperation Base of Zhejiang Province and the Artificial Intelligence Institute, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","Artificial Intelligence Institute, Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-1630-5928","affiliations":[{"raw_affiliation_string":"Machine Learning and I-health International Cooperation Base of Zhejiang Province and the Artificial Intelligence Institute, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"Artificial Intelligence Institute, Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Zhejiang, China","institution_ids":["https://openalex.org/I50760025","https://openalex.org/I105126617"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075474564","display_name":"Tianlei Wang","orcid":"https://orcid.org/0000-0002-4498-4326"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlei Wang","raw_affiliation_strings":["Machine Learning and I-health International Cooperation Base of Zhejiang Province and the Artificial Intelligence Institute, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","Artificial Intelligence Institute, Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-4498-4326","affiliations":[{"raw_affiliation_string":"Machine Learning and I-health International Cooperation Base of Zhejiang Province and the Artificial Intelligence Institute, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"Artificial Intelligence Institute, Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Zhejiang, China","institution_ids":["https://openalex.org/I50760025","https://openalex.org/I105126617"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049506273","display_name":"Zhiping Lin","orcid":"https://orcid.org/0000-0002-1587-1226"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiping Lin","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1587-1226","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074063024","display_name":"Jiuwen Cao","orcid":"https://orcid.org/0000-0002-6480-5794"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuwen Cao","raw_affiliation_strings":["Machine Learning and I-health International Cooperation Base of Zhejiang Province and the Artificial Intelligence Institute, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","Artificial Intelligence Institute, Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-6480-5794","affiliations":[{"raw_affiliation_string":"Machine Learning and I-health International Cooperation Base of Zhejiang Province and the Artificial Intelligence Institute, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"Artificial Intelligence Institute, Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Zhejiang, China","institution_ids":["https://openalex.org/I50760025","https://openalex.org/I105126617"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27267636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"3","first_page":"3131","last_page":"3144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9577999711036682,"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":0.9577999711036682,"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/constraint","display_name":"Constraint (computer-aided design)","score":0.6288999915122986},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6065000295639038},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6061999797821045},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5248000025749207},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5242999792098999},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4320000112056732},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.40959998965263367},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.387800008058548},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.38670000433921814},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3517000079154968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597000241279602},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6061999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286999940872192},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.38670000433921814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3625758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3625758","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1327000608","display_name":null,"funder_award_id":"2021YFE0100100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2680912405","display_name":null,"funder_award_id":"LZ24F030010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G287901162","display_name":null,"funder_award_id":"2021YFE0205400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7151297541","display_name":null,"funder_award_id":"U1909209","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":46,"referenced_works":["https://openalex.org/W1984279162","https://openalex.org/W2066380143","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2810983211","https://openalex.org/W2962858109","https://openalex.org/W2963526661","https://openalex.org/W2965066169","https://openalex.org/W2978036638","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W2998382406","https://openalex.org/W3003642782","https://openalex.org/W3003921261","https://openalex.org/W3034414401","https://openalex.org/W3034447740","https://openalex.org/W3035106683","https://openalex.org/W3035449864","https://openalex.org/W3110267192","https://openalex.org/W3177505580","https://openalex.org/W3177684257","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W3206651063","https://openalex.org/W4207058148","https://openalex.org/W4225562651","https://openalex.org/W4229030834","https://openalex.org/W4312787220","https://openalex.org/W4312879041","https://openalex.org/W4313045695","https://openalex.org/W4318832749","https://openalex.org/W4361762480","https://openalex.org/W4365807615","https://openalex.org/W4385245566","https://openalex.org/W4385767840","https://openalex.org/W4385768208","https://openalex.org/W4386410320","https://openalex.org/W4389665150","https://openalex.org/W4390463734","https://openalex.org/W4390871832","https://openalex.org/W4390872070","https://openalex.org/W4402468542","https://openalex.org/W4402753732","https://openalex.org/W4403780826","https://openalex.org/W4407937981"],"related_works":[],"abstract_inverted_index":{"The":[0],"language":[1],"modeling":[2],"paradigm":[3],"for":[4,78],"scene":[5,71],"text":[6,27,72],"recognition":[7],"(STR)":[8],"has":[9],"demonstrated":[10],"impressive":[11],"universal":[12],"capabilities":[13],"across":[14],"extensive":[15],"STR":[16,178,218],"scenarios.":[17],"However,":[18],"existing":[19,211],"methods":[20,212],"still":[21],"encounter":[22],"challenges":[23],"in":[24,62,102,147,176,183],"effectively":[25],"handling":[26,177],"images":[28],"with":[29,140,180],"irregular":[30],"shapes":[31],"and":[32,157,182,200,216,225],"diverse":[33],"appearances":[34],"(e.g.,":[35],"curve,":[36],"artistic,":[37],"multi-oriented)":[38],"due":[39],"to":[40,118,136,162],"the":[41,54,79,90,103,113,120,133,164,171,188,193],"absence":[42],"of":[43,56,75,92,122,195],"contextual":[44],"information":[45,116,174],"during":[46],"initial":[47],"decoding.":[48],"In":[49],"this":[50],"work,":[51],"inspired":[52],"by":[53,111,170],"principle":[55],"\u2018<italic":[57],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[58],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">forest":[59],"before":[60],"trees</i>\u2019":[61],"human":[63,104],"visual":[64,95,106],"perception,":[65],"we":[66,83,153],"introduce":[67],"NASTR,":[68],"a":[69,85,148],"non-autoregressive":[70],"recognizer":[73],"capable":[74],"endowing":[76],"global-aware":[77],"attentional":[80],"decoder.":[81],"Specifically,":[82],"design":[84],"global-to-local":[86],"attention":[87],"procedure,":[88],"simulating":[89],"mechanism":[91],"globally":[93],"holistic":[94],"signal":[96],"processing":[97],"preceding":[98],"locally":[99],"detailed":[100],"response":[101],"brain":[105],"system.":[107],"This":[108,130],"is":[109],"achieved":[110],"leveraging":[112],"global":[114,172,189,196,198],"image":[115,173,190],"queries":[117,175],"condition":[119],"generation":[121],"glimpse":[123],"vectors":[124],"at":[125,229],"each":[126],"decoding":[127],"time":[128],"step.":[129],"procedure":[131],"empowers":[132],"NASTR":[134,208],"model":[135],"achieve":[137],"on-par":[138],"performance":[139],"its":[141],"state-of-the-art":[142],"autoregressive":[143],"counterparts,":[144],"while":[145],"operating":[146],"fully":[149],"parallel":[150],"manner.":[151],"Moreover,":[152],"propose":[154],"multiple":[155],"optional":[156],"flexible":[158],"encoding":[159],"constraint":[160],"components":[161,186],"alleviate":[163],"representation":[165],"quality":[166],"degradation":[167],"issue":[168],"caused":[169],"tasks":[179],"multilingual":[181],"multi-domains.":[184],"These":[185],"constrain":[187],"features":[191],"from":[192],"perspective":[194],"structural,":[197],"semantic,":[199],"linguistic":[201],"knowledge.":[202],"Extensive":[203],"experimental":[204],"results":[205],"demonstrate":[206],"that":[207],"consistently":[209],"outperforms":[210],"on":[213],"both":[214],"Chinese":[215],"English":[217],"benchmarks.":[219],"Our":[220],"source":[221],"code,":[222],"trained":[223],"models,":[224],"logs":[226],"are":[227],"available":[228],"https://github.com/ML-HDU/NASTR.":[230]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-28T00:00:00"}