{"id":"https://openalex.org/W4402915824","doi":"https://doi.org/10.1109/icip51287.2024.10647444","title":"Learned Image Compression With Text Quality Enhancement","display_name":"Learned Image Compression With Text Quality Enhancement","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915824","doi":"https://doi.org/10.1109/icip51287.2024.10647444"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647444","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078710992","display_name":"Chih-Yu Lai","orcid":"https://orcid.org/0000-0001-5789-4234"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Yu Lai","raw_affiliation_strings":["Massachusetts Institute of Technology Electrical Engineering and Computer Science,Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Electrical Engineering and Computer Science,Cambridge,MA,USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054814160","display_name":"Dung Viet Tran","orcid":"https://orcid.org/0000-0002-3673-9160"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dung Tran","raw_affiliation_strings":["Microsoft Corporation Applied Sciences Group,Redmond,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation Applied Sciences Group,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation Applied Sciences Group,Redmond,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation Applied Sciences Group,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs/2111.02249,2021","issue":null,"first_page":"1809","last_page":"1815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9912999868392944,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9912999868392944,"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":0.9463000297546387,"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":0.6758661270141602},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.6630276441574097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5356440544128418},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5339834690093994},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5327140688896179},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5042978525161743},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.48532241582870483},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4796200692653656},{"id":"https://openalex.org/keywords/texture-compression","display_name":"Texture compression","score":0.41664043068885803},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40141990780830383},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2469126582145691},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11906489729881287},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.07128068804740906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758661270141602},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.6630276441574097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356440544128418},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5339834690093994},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5327140688896179},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5042978525161743},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.48532241582870483},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4796200692653656},{"id":"https://openalex.org/C54243161","wikidata":"https://www.wikidata.org/wiki/Q39333","display_name":"Texture compression","level":5,"score":0.41664043068885803},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40141990780830383},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2469126582145691},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11906489729881287},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.07128068804740906},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647444","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2552465432","https://openalex.org/W2785562966","https://openalex.org/W2786429113","https://openalex.org/W2967615747","https://openalex.org/W3034469748","https://openalex.org/W3097448661","https://openalex.org/W3116647679","https://openalex.org/W3134748538","https://openalex.org/W3206996732","https://openalex.org/W3208962647","https://openalex.org/W4308235774","https://openalex.org/W4312806968","https://openalex.org/W4319300002","https://openalex.org/W4361271623","https://openalex.org/W4377246807","https://openalex.org/W4385080004","https://openalex.org/W4386075611","https://openalex.org/W4390723232","https://openalex.org/W6803627629","https://openalex.org/W6810067190","https://openalex.org/W6810910217","https://openalex.org/W6851622878"],"related_works":["https://openalex.org/W2129829718","https://openalex.org/W2595043295","https://openalex.org/W2751842002","https://openalex.org/W3165542721","https://openalex.org/W4313046148","https://openalex.org/W4243608781","https://openalex.org/W142455045","https://openalex.org/W2096442341","https://openalex.org/W2387043686","https://openalex.org/W3180760233"],"abstract_inverted_index":{"Learned":[0],"image":[1,145,166],"compression":[2,146,167],"has":[3],"gained":[4],"widespread":[5],"popularity":[6],"for":[7,109,117,130,140],"their":[8],"efficiency":[9],"in":[10,50,82,144],"achieving":[11],"ultra-low":[12],"bit-rates.":[13],"Yet,":[14],"images":[15,22],"containing":[16],"substantial":[17],"textual":[18],"content,":[19],"particularly":[20],"screen-content":[21],"(SCI),":[23],"often":[24],"suffers":[25],"from":[26],"text":[27,42,51,87,127,142,159],"distortion":[28],"at":[29],"such":[30],"compressed":[31],"levels.":[32],"To":[33],"address":[34],"this,":[35],"we":[36,99,135],"propose":[37],"to":[38,46],"minimize":[39],"a":[40,101],"novel":[41],"logit":[43,128,160],"loss":[44,93,129,161],"designed":[45],"quantify":[47],"the":[48,53,60,64,83,91,126,151],"disparity":[49],"between":[52],"original":[54],"and":[55,73,114,153],"reconstructed":[56,65,86],"images,":[57],"thereby":[58],"improving":[59],"perceptual":[61],"quality":[62,84,143],"of":[63,85,90,106,156],"text.":[66],"Through":[67],"rigorous":[68],"experimentation":[69],"across":[70,163],"diverse":[71],"datasets":[72],"employing":[74],"state-of-the-art":[75],"algorithms,":[76],"our":[77,157],"findings":[78,149],"reveal":[79],"significant":[80],"enhancements":[81],"upon":[88],"integration":[89],"proposed":[92,158],"function":[94,162],"with":[95],"appropriate":[96],"weighting.":[97],"Notably,":[98],"achieve":[100],"Bjontegaard":[102],"delta":[103],"(BD)":[104],"rate":[105],"$-32.64":[107],"\\%$":[108,116],"Character":[110],"Error":[111,119],"Rate":[112,120],"(CER)":[113],"$-28.03":[115],"Word":[118],"(WER)":[121],"on":[122],"average":[123],"by":[124],"applying":[125],"two":[131],"screenshot":[132],"datasets.":[133],"Additionally,":[134],"present":[136],"quantitative":[137],"metrics":[138],"tailored":[139],"evaluating":[141],"tasks.":[147],"Our":[148],"underscore":[150],"efficacy":[152],"potential":[154],"applicability":[155],"various":[164],"text-aware":[165],"contexts.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}