{"id":"https://openalex.org/W4285180923","doi":"https://doi.org/10.1109/access.2022.3173256","title":"Variable-Rate Deep Image Compression With Vision Transformers","display_name":"Variable-Rate Deep Image Compression With Vision Transformers","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285180923","doi":"https://doi.org/10.1109/access.2022.3173256"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3173256","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09770776.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09770776.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100649277","display_name":"Binglin Li","orcid":"https://orcid.org/0000-0003-2798-1710"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"funder","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Binglin Li","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Burnaby, BC V5A 1S6 Canada."],"affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Burnaby, BC V5A 1S6 Canada.","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108166775","display_name":"Jie Liang","orcid":"https://orcid.org/0000-0003-3003-4343"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"funder","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jie Liang","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Burnaby, BC V5A 1S6 Canada."],"affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Burnaby, BC V5A 1S6 Canada.","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046233912","display_name":"Jingning Han","orcid":"https://orcid.org/0000-0001-7168-2254"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"funder","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingning Han","raw_affiliation_strings":["WebM Codec team, Google LLC, Mountain View, CA 94043 USA."],"affiliations":[{"raw_affiliation_string":"WebM Codec team, Google LLC, Mountain View, CA 94043 USA.","institution_ids":["https://openalex.org/I1291425158"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.305,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":10,"citation_normalized_percentile":{"value":0.523442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":"10","issue":null,"first_page":"50323","last_page":"50334"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9997,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9997,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9996,"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":0.9991,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343562},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.6064338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.60620046},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.52423817},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47473535},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42669132},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.41753748},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35127956},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2551517},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21221465},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1714682},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1061385},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07913256},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3173256","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09770776.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/35f9ed78877b4b3b9c77d6051afff9e3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3173256","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09770776.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320309327","funder_display_name":"Google","award_id":null},{"funder":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada","award_id":"RGPIN-2020-04525"}],"datasets":[],"versions":[],"referenced_works_count":40,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1861492603","https://openalex.org/W2040109339","https://openalex.org/W2040903332","https://openalex.org/W2121927366","https://openalex.org/W2142683286","https://openalex.org/W2194775991","https://openalex.org/W2597747080","https://openalex.org/W2604392022","https://openalex.org/W2900996853","https://openalex.org/W2938908220","https://openalex.org/W2946005927","https://openalex.org/W2962676454","https://openalex.org/W2962891349","https://openalex.org/W2963447011","https://openalex.org/W2963645458","https://openalex.org/W2964098744","https://openalex.org/W2966821425","https://openalex.org/W2970340508","https://openalex.org/W2970830477","https://openalex.org/W2982853315","https://openalex.org/W2999096997","https://openalex.org/W3008242406","https://openalex.org/W3010647498","https://openalex.org/W3016076140","https://openalex.org/W3016310111","https://openalex.org/W3034469748","https://openalex.org/W3035197843","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3140627604","https://openalex.org/W3147173580","https://openalex.org/W3159663321","https://openalex.org/W3168649818","https://openalex.org/W3171125843","https://openalex.org/W3173590174","https://openalex.org/W3180355996","https://openalex.org/W3198243518","https://openalex.org/W4248310230","https://openalex.org/W4297659253"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2949601986","https://openalex.org/W2925692864","https://openalex.org/W2788972299","https://openalex.org/W2729981612","https://openalex.org/W2560215812","https://openalex.org/W2521347458","https://openalex.org/W2498789492","https://openalex.org/W2384362569","https://openalex.org/W2181948922"],"abstract_inverted_index":{"Recently,":[0],"vision":[1,9,37],"transformers":[2,106,180],"have":[3],"been":[4,21],"applied":[5,71],"in":[6,24,77,105,127,184,209],"many":[7],"computer":[8],"problems":[10],"due":[11],"to":[12,48,59,72,88,130,149,162,214],"its":[13],"long-range":[14],"learning":[15],"ability.":[16],"However,":[17],"it":[18],"has":[19],"not":[20],"throughly":[22],"explored":[23],"image":[25,32,41,177,237],"compression.":[26],"We":[27,80,171],"propose":[28,82],"a":[29,61,83,108,225],"patch-based":[30,175],"learned":[31,176,236],"compression":[33,137,165,178,192,238],"network":[34,148],"by":[35],"incorporating":[36],"transformers.":[38],"The":[39],"input":[40],"is":[42,107,160,212],"divided":[43],"into":[44,120],"patches":[45,53,142],"before":[46],"feeding":[47],"the":[49,52,57,74,78,90,98,102,112,117,125,136,152,156,164,189,195,200],"encoder":[50],"and":[51,123,143,211,233],"are":[54,70],"reconstructed":[55],"from":[56],"decoder":[58],"form":[60],"complete":[62],"image.":[63],"Different":[64],"kinds":[65],"of":[66,101,111,227],"transformer":[67,126],"blocks":[68],"(TransBlocks)":[69],"meet":[73],"various":[75],"requirements":[76],"subnetworks.":[79],"also":[81],"transformer-based":[84],"context":[85],"model":[86],"(TransContext)":[87],"facilitate":[89],"coding":[91,158,202],"based":[92],"on":[93,194],"previously":[94],"decoded":[95],"symbols.":[96],"Since":[97],"computational":[99,132],"complexity":[100],"attention":[103],"mechanism":[104],"quadratic":[109],"function":[110],"sequence":[113],"length,":[114],"we":[115,139,218],"partition":[116],"feature":[118],"tensor":[119],"different":[121],"segments":[122],"conduct":[124],"each":[128],"segment":[129],"save":[131],"cost.":[133],"To":[134],"alleviate":[135],"artifacts,":[138],"use":[140],"overlapping":[141],"apply":[144],"an":[145],"existing":[146],"deblocking":[147],"further":[150],"remove":[151],"artifacts.":[153],"At":[154],"last,":[155],"residual":[157,201],"scheme":[159],"adopted":[161],"get":[163,219],"performance":[166,208],"for":[167],"variable":[168],"bit":[169,228,242],"rates.":[170,243],"show":[172],"that":[173],"our":[174,204],"with":[179],"obtain":[181],"0.75dB":[182],"improvement":[183],"PSNR":[185,210],"at":[186,231,240],"0.15bpp":[187],"than":[188,222],"prior":[190],"variable-rate":[191,235],"work":[193],"Kodak":[196],"dataset.":[197],"When":[198],"using":[199],"strategy,":[203],"framework":[205],"keeps":[206],"good":[207],"comparable":[213],"BPG420.":[215],"For":[216],"MS-SSIM,":[217],"higher":[220],"results":[221],"BPG444":[223],"across":[224],"range":[226],"rates":[229],"(0.021":[230],"0.21bpp)":[232],"other":[234],"models":[239],"low":[241]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4285180923","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6}],"updated_date":"2025-04-19T05:09:36.768605","created_date":"2022-07-14"}