{"id":"https://openalex.org/W4408352466","doi":"https://doi.org/10.1109/icassp49660.2025.10888375","title":"Improving Irregular Text Recognition with Adaptive Feature Compression","display_name":"Improving Irregular Text Recognition with Adaptive Feature Compression","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352466","doi":"https://doi.org/10.1109/icassp49660.2025.10888375"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100724447","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-1647-2323"},"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":true,"raw_author_name":"Yin Liu","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083641967","display_name":"Zhineng Chen","orcid":null},"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":["Fudan University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100724447"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04136351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9046000242233276,"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":0.9046000242233276,"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":0.7336512804031372},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.555436372756958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5175480246543884},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5099526643753052},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4988670349121094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47832226753234863},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4711174964904785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4401409327983856},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36917805671691895},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07294955849647522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336512804031372},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.555436372756958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175480246543884},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5099526643753052},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4988670349121094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47832226753234863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4711174964904785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4401409327983856},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36917805671691895},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07294955849647522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/icassp49660.2025.10888375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1569614731","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2122221966","https://openalex.org/W2127141656","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/W2810983211","https://openalex.org/W2965066169","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3034414401","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3082397598","https://openalex.org/W3110267192","https://openalex.org/W3134064484","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W3206651063","https://openalex.org/W4229030834","https://openalex.org/W4283821822","https://openalex.org/W4292825881","https://openalex.org/W4310335763","https://openalex.org/W4312843595","https://openalex.org/W4312879041","https://openalex.org/W4313045695","https://openalex.org/W4385767840","https://openalex.org/W4385767967","https://openalex.org/W4386410320","https://openalex.org/W4390871832","https://openalex.org/W4390874533","https://openalex.org/W4392980188","https://openalex.org/W4402753732","https://openalex.org/W4402772614","https://openalex.org/W4403791624","https://openalex.org/W4406047244","https://openalex.org/W4407937981","https://openalex.org/W4409346384","https://openalex.org/W6629590909","https://openalex.org/W6784333009","https://openalex.org/W6875230513"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2256933480","https://openalex.org/W2027854990","https://openalex.org/W2370081953","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Scene":[0],"text":[1,8,81,88,110,122],"recognition":[2,53,123],"models":[3,105,150],"typically":[4],"do":[5],"not":[6],"handle":[7],"irregularities":[9,111],"well,":[10],"especially":[11],"for":[12,44],"connectionist":[13],"temporal":[14],"classification":[15],"(CTC)-based":[16],"ones.":[17],"In":[18],"CTC":[19,33,104,136,167],"models,":[20],"visual":[21],"features":[22,68,78,97],"must":[23],"be":[24],"compressed":[25],"into":[26],"a":[27,49,91,120],"one-dimensional":[28],"sequence":[29],"to":[30,65,75,80,87,101,134],"fit":[31],"the":[32,67,72,93,98,163],"decoding.":[34],"Current":[35],"solutions":[36],"adopt":[37],"simple":[38],"average":[39],"pooling":[40],"or":[41],"feature":[42,62,131],"shrinking":[43],"this":[45,115,129],"compression,":[46],"which":[47],"is":[48],"bottleneck":[50],"restricting":[51],"their":[52],"capabilities.":[54],"To":[55],"tackle":[56],"this,":[57],"we":[58,118],"introduce":[59],"an":[60],"adaptive":[61,130],"compression":[63,94,132],"block":[64,133],"compress":[66],"adaptively.":[69],"It":[70],"leverages":[71],"attention":[73],"mechanism":[74],"selectively":[76],"preserve":[77],"related":[79],"foreground":[82],"and":[83,103],"discard":[84],"those":[85],"belonging":[86],"background.":[89],"As":[90],"result,":[92],"adaptively":[95],"retains":[96],"mostly":[99],"important":[100],"recognition,":[102],"could":[106],"better":[107],"deal":[108],"with":[109,114],"when":[112],"equipped":[113],"block.":[116],"Correspondingly,":[117],"design":[119],"novel":[121],"model":[124],"termed":[125],"AFCTR":[126,146,160],"by":[127],"appending":[128],"existing":[135,148],"models.":[137,168],"Experimental":[138],"results":[139],"on":[140],"typical":[141],"English":[142],"benchmarks":[143],"show":[144],"that":[145],"outperforms":[147],"popular":[149],"in":[151],"terms":[152],"of":[153,166],"accuracy":[154],"under":[155],"multiple":[156],"evaluation":[157],"protocols.":[158],"Moreover,":[159],"also":[161],"preserves":[162],"efficiency":[164],"advantage":[165]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}