{"id":"https://openalex.org/W2980441643","doi":"https://doi.org/10.1109/tip.2020.3036752","title":"ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression","display_name":"ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression","publication_year":2020,"publication_date":"2020-11-13","ids":{"openalex":"https://openalex.org/W2980441643","doi":"https://doi.org/10.1109/tip.2020.3036752","mag":"2980441643","pmid":"https://pubmed.ncbi.nlm.nih.gov/33186110"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.3036752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3036752","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.08845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li-Heng Chen","orcid":"https://orcid.org/0000-0003-3800-0682"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Li-Heng Chen","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christos G. Bampis","orcid":"https://orcid.org/0000-0003-0570-048X"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos G. Bampis","raw_affiliation_strings":["Netflix Inc., Los Gatos, CA, USA"],"affiliations":[{"raw_affiliation_string":"Netflix Inc., Los Gatos, CA, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Li","raw_affiliation_strings":["Netflix Inc., Los Gatos, CA, USA"],"affiliations":[{"raw_affiliation_string":"Netflix Inc., Los Gatos, CA, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andrey Norkin","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrey Norkin","raw_affiliation_strings":["Netflix Inc., Los Gatos, CA, USA"],"affiliations":[{"raw_affiliation_string":"Netflix Inc., Los Gatos, CA, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alan C. Bovik","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan C. Bovik","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":4.0227,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.94981715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"360","last_page":"373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.4016999900341034,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.4016999900341034,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.1518000066280365,"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":0.08649999648332596,"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/image-compression","display_name":"Image compression","score":0.6567000150680542},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5958999991416931},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.527999997138977},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5083000063896179},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48989999294281006},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45399999618530273},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.421999990940094},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.39239999651908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848000288009644},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.6567000150680542},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5958999991416931},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.527999997138977},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.29499998688697815},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2778192920","wikidata":"https://www.wikidata.org/wiki/Q16874989","display_name":"Signal compression","level":4,"score":0.26109999418258667},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2522999942302704}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2020.3036752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3036752","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:33186110","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33186110","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:1910.08845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08845","pdf_url":"https://arxiv.org/pdf/1910.08845","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.08845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08845","pdf_url":"https://arxiv.org/pdf/1910.08845","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1580389772","https://openalex.org/W1607233498","https://openalex.org/W2009272644","https://openalex.org/W2013784666","https://openalex.org/W2015196405","https://openalex.org/W2037642501","https://openalex.org/W2046119925","https://openalex.org/W2099474155","https://openalex.org/W2103997799","https://openalex.org/W2108598243","https://openalex.org/W2129768577","https://openalex.org/W2133665775","https://openalex.org/W2134227958","https://openalex.org/W2137136191","https://openalex.org/W2141983208","https://openalex.org/W2164287382","https://openalex.org/W2171349048","https://openalex.org/W2178576682","https://openalex.org/W2194775991","https://openalex.org/W2395611524","https://openalex.org/W2550673061","https://openalex.org/W2552465432","https://openalex.org/W2556068545","https://openalex.org/W2557414982","https://openalex.org/W2562637781","https://openalex.org/W2563786098","https://openalex.org/W2586275201","https://openalex.org/W2597747080","https://openalex.org/W2607041014","https://openalex.org/W2768814045","https://openalex.org/W2785562966","https://openalex.org/W2904829482","https://openalex.org/W2905530235","https://openalex.org/W2914826019","https://openalex.org/W2923664668","https://openalex.org/W2948654165","https://openalex.org/W2955863859","https://openalex.org/W2962785568","https://openalex.org/W2963037581","https://openalex.org/W2963149687","https://openalex.org/W2963189365","https://openalex.org/W2963470893","https://openalex.org/W2963711615","https://openalex.org/W2963713691","https://openalex.org/W2973013219","https://openalex.org/W2981613960","https://openalex.org/W2983979703","https://openalex.org/W3015735582","https://openalex.org/W3015863973","https://openalex.org/W3045512288","https://openalex.org/W3088230179","https://openalex.org/W3090186338","https://openalex.org/W6602211262","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6674553587","https://openalex.org/W6674855086","https://openalex.org/W6687214662","https://openalex.org/W6694251005","https://openalex.org/W6696118455","https://openalex.org/W6702130928","https://openalex.org/W6754634825","https://openalex.org/W6793689815","https://openalex.org/W6947897824"],"related_works":[],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,13,32,81,106,121],"l<sub>p</sub>":[3],"(p":[4],"=":[5],"1,2)":[6],"norms":[7,37],"has":[8],"largely":[9],"dominated":[10],"the":[11,30,72,82],"measurement":[12],"loss":[14,31,79],"in":[15],"neural":[16],"networks":[17,56],"due":[18],"to":[19,28,52,94,116],"their":[20],"simplicity":[21],"and":[22],"analytical":[23],"properties.":[24],"However,":[25],"when":[26],"used":[27],"assess":[29],"visual":[33],"information,":[34],"these":[35],"simple":[36],"are":[38,114],"not":[39],"very":[40],"consistent":[41],"with":[42],"human":[43],"perception.":[44],"Here,":[45],"we":[46,62,113],"describe":[47],"a":[48,64,78,118,130],"different":[49],"\"proximal\"":[50],"approach":[51],"optimize":[53],"image":[54,99,110],"analysis":[55],"against":[57],"quantitative":[58],"perceptual":[59,73,132],"models.":[60],"Specifically,":[61],"construct":[63],"proxy":[65],"network,":[66],"broadly":[67],"termed":[68],"ProxIQA,":[69],"which":[70],"mimics":[71],"model":[74],"while":[75],"serving":[76],"as":[77,122,124],"layer":[80],"network.":[83,101],"We":[84],"experimentally":[85],"demonstrate":[86,117],"how":[87],"this":[88],"optimization":[89],"framework":[90],"can":[91],"be":[92],"applied":[93],"train":[95],"an":[96,107],"end-to-end":[97],"optimized":[98],"compression":[100,111],"By":[102],"building":[103],"on":[104],"top":[105],"existing":[108],"deep":[109],"model,":[112],"able":[115],"bitrate":[119],"reduction":[120],"much":[123],"31%":[125],"over":[126],"MSE":[127],"optimization,":[128],"given":[129],"specified":[131],"quality":[133],"(VMAF)":[134],"level.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2019-10-25T00:00:00"}