{"id":"https://openalex.org/W4414140786","doi":"https://doi.org/10.1109/icmew68306.2025.11152234","title":"ColorVideoVDP-ML: Visual Difference Predictor with a neural regressor for image and video quality prediction","display_name":"ColorVideoVDP-ML: Visual Difference Predictor with a neural regressor for image and video quality prediction","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414140786","doi":"https://doi.org/10.1109/icmew68306.2025.11152234"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5038646938","display_name":"Dounia Hammou","orcid":"https://orcid.org/0000-0001-7475-6722"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dounia Hammou","raw_affiliation_strings":["University of Cambridge,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244800","display_name":"Fei Yin","orcid":"https://orcid.org/0009-0000-8921-0140"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fei Yin","raw_affiliation_strings":["University of Cambridge,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006381834","display_name":"Rafa\u0142 Mantiuk","orcid":"https://orcid.org/0000-0003-2353-0349"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rafa\u0142 K. Mantiuk","raw_affiliation_strings":["University of Cambridge,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":2.4304,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90524895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9998000264167786,"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":0.9998000264167786,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9884999990463257,"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/T11666","display_name":"Color Science and Applications","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.73580002784729},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.6449000239372253},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6190999746322632},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5741999745368958},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4860000014305115},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48590001463890076},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43380001187324524}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7958999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365000247955322},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.73580002784729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6664999723434448},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6190999746322632},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5741999745368958},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43380001187324524},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.36399999260902405},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.28290000557899475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C3019635856","wikidata":"https://www.wikidata.org/wiki/Q1619726","display_name":"Background image","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1990873664","https://openalex.org/W1997746542","https://openalex.org/W2023612294","https://openalex.org/W2092409645","https://openalex.org/W2106517536","https://openalex.org/W2117535912","https://openalex.org/W2133665775","https://openalex.org/W2571200450","https://openalex.org/W2953590133","https://openalex.org/W2962785568","https://openalex.org/W2970470466","https://openalex.org/W3017136408","https://openalex.org/W3113727486","https://openalex.org/W3138218344","https://openalex.org/W3157639105","https://openalex.org/W3169674094","https://openalex.org/W3185070214","https://openalex.org/W3186150684","https://openalex.org/W4214745154","https://openalex.org/W4308236828","https://openalex.org/W4308236851","https://openalex.org/W4367190920","https://openalex.org/W4385245566","https://openalex.org/W4393078930","https://openalex.org/W4393931452","https://openalex.org/W4400822490","https://openalex.org/W4400878360"],"related_works":["https://openalex.org/W2391251536","https://openalex.org/W2362198218","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2375008505","https://openalex.org/W1982750869","https://openalex.org/W2085756966","https://openalex.org/W2350679292","https://openalex.org/W2086348228","https://openalex.org/W4390653028"],"abstract_inverted_index":{"ColorVideoVDP-ML":[0],"is":[1],"a":[2,11,16,33,37,128,138],"full-reference":[3],"image":[4,98,118],"and":[5,29,32,53,67,70,79,88,97,126,132],"video":[6,96],"quality":[7,42,99],"metric,":[8],"which":[9],"combines":[10],"visual":[12,27],"difference":[13],"predictor":[14],"with":[15],"machine":[17],"learning":[18],"regressor.":[19],"It":[20,44],"employs":[21],"ColorVideoVDP":[22],"as":[23,36,58,60,121],"an":[24],"encoder":[25],"of":[26,39,50,141],"information":[28],"visible":[30],"differences,":[31,125],"neural":[34,82],"architecture":[35],"regressor":[38],"the":[40,104,134,146],"final":[41],"scores.":[43],"benefits":[45],"from":[46],"low-level":[47],"vision":[48],"models":[49],"contrast":[51],"sensitivity":[52],"masking,":[54],"found":[55,150],"in":[56,103,136],"ColorVideoVDP,":[57],"well":[59],"its":[61],"ability":[62],"to":[63,71,73,130],"handle":[64],"both":[65],"SDR":[66],"HDR":[68],"content,":[69],"adapt":[72],"arbitrary":[74],"viewing":[75],"conditions,":[76],"display":[77],"resolution,":[78],"size.":[80],"Two":[81],"regressors,":[83],"one":[84,89],"based":[85],"on":[86,90,94],"MLPs":[87],"Transformers,":[91],"are":[92],"trained":[93],"multiple":[95],"datasets,":[100],"all":[101],"scaled":[102],"Just-Objectionable-Difference":[105],"(JOD)":[106],"units.":[107],"The":[108,143],"regressors":[109],"let":[110],"us":[111],"account":[112],"for":[113,145],"higher-level":[114],"factors":[115],"influencing":[116],"perceived":[117],"quality,":[119],"such":[120],"saliency":[122],"or":[123],"texture":[124],"provide":[127],"way":[129],"fine-tune":[131],"specialize":[133],"metric":[135,147],"handling":[137],"specific":[139],"type":[140],"distortions.":[142],"code":[144],"can":[148],"be":[149],"at":[151],"https://github.com/gfxdisp/ColorVideoVDP.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}