{"id":"https://openalex.org/W3200120316","doi":"https://doi.org/10.1109/vcip53242.2021.9675350","title":"DVC-P: Deep Video Compression with Perceptual Optimizations","display_name":"DVC-P: Deep Video Compression with Perceptual Optimizations","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W3200120316","doi":"https://doi.org/10.1109/vcip53242.2021.9675350","mag":"3200120316"},"language":"en","primary_location":{"id":"doi:10.1109/vcip53242.2021.9675350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip53242.2021.9675350","pdf_url":null,"source":{"id":"https://openalex.org/S4363608378","display_name":"2021 International Conference on Visual Communications and Image Processing (VCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Visual Communications and Image Processing (VCIP)","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/A5042977321","display_name":"Saiping Zhang","orcid":"https://orcid.org/0000-0002-2442-1104"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Saiping Zhang","raw_affiliation_strings":["Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083550803","display_name":"Marta Mrak","orcid":"https://orcid.org/0000-0002-7777-0252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marta Mrak","raw_affiliation_strings":["BBC Research & Development, The Lighthouse, White City Place,London,UK"],"affiliations":[{"raw_affiliation_string":"BBC Research & Development, The Lighthouse, White City Place,London,UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079201773","display_name":"Luis Herranz","orcid":"https://orcid.org/0000-0002-7022-3395"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Herranz","raw_affiliation_strings":["Universitat Autònoma de Barcelona,Computer Vision Center,Barcelona,Spain,08193"],"affiliations":[{"raw_affiliation_string":"Universitat Autònoma de Barcelona,Computer Vision Center,Barcelona,Spain,08193","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068183945","display_name":"Marc G\u00f3rriz Blanch","orcid":"https://orcid.org/0000-0002-7636-4981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Gorriz Blanch","raw_affiliation_strings":["BBC Research & Development, The Lighthouse, White City Place,London,UK"],"affiliations":[{"raw_affiliation_string":"BBC Research & Development, The Lighthouse, White City Place,London,UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055653807","display_name":"Shuai Wan","orcid":"https://orcid.org/0000-0001-8617-149X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wan","raw_affiliation_strings":["Northwestern Polytechnical University,School of Electronics and Information,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Electronics and Information,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055433813","display_name":"Fuzheng Yang","orcid":"https://orcid.org/0000-0002-8369-8015"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzheng Yang","raw_affiliation_strings":["Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042977321"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.5161,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.63935527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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":0.767866849899292},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6159316897392273},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5707820653915405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5395893454551697},{"id":"https://openalex.org/keywords/compression-artifact","display_name":"Compression artifact","score":0.487253338098526},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.4532996714115143},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4512091279029846},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.44627976417541504},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4320807158946991},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.42967545986175537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.372078001499176},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33874762058258057},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33037900924682617},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.28911900520324707},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10842195153236389},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.084723562002182},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08149492740631104},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.07133752107620239},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07030141353607178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767866849899292},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6159316897392273},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5707820653915405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5395893454551697},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.487253338098526},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.4532996714115143},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4512091279029846},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.44627976417541504},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4320807158946991},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.42967545986175537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.372078001499176},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33874762058258057},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33037900924682617},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.28911900520324707},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10842195153236389},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.084723562002182},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08149492740631104},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.07133752107620239},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07030141353607178},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip53242.2021.9675350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip53242.2021.9675350","pdf_url":null,"source":{"id":"https://openalex.org/S4363608378","display_name":"2021 International Conference on Visual Communications and Image Processing (VCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2140199336","https://openalex.org/W2173520492","https://openalex.org/W2535388113","https://openalex.org/W2548527721","https://openalex.org/W2593414223","https://openalex.org/W2902437806","https://openalex.org/W2956024009","https://openalex.org/W2962676454","https://openalex.org/W2962835968","https://openalex.org/W2969260367","https://openalex.org/W3013418937","https://openalex.org/W3018065762","https://openalex.org/W3035001409","https://openalex.org/W3035209157","https://openalex.org/W3037150605","https://openalex.org/W3102015846","https://openalex.org/W3110286842","https://openalex.org/W3126473426","https://openalex.org/W6637373629","https://openalex.org/W6730007070","https://openalex.org/W6756789066","https://openalex.org/W6785343060"],"related_works":["https://openalex.org/W2356067764","https://openalex.org/W2907129173","https://openalex.org/W4283718665","https://openalex.org/W2379432963","https://openalex.org/W2950365799","https://openalex.org/W4289036997","https://openalex.org/W2008459483","https://openalex.org/W3171444750","https://openalex.org/W3202870363","https://openalex.org/W4307983865"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"the":[4,105,119],"significant":[5],"development":[6],"of":[7,41,108],"learning-based":[8],"video":[9,29],"compression":[10,30],"methods,":[11],"which":[12,35,91],"aim":[13],"at":[14,37],"optimizing":[15],"objective":[16],"or":[17],"perceptual":[18,32,39,59,106,130,137],"quality":[19,40,107,131],"and":[20,65,80],"bit":[21],"rates.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"introduce":[27],"deep":[28],"with":[31,58,97,118,128],"op-timizations":[33],"(DVC-P),":[34],"aims":[36],"increasing":[38],"decoded":[42,109],"videos.":[43],"Our":[44],"proposed":[45,123],"DVC-P":[46],"is":[47,85,111],"based":[48],"on":[49,141],"Deep":[50],"Video":[51],"Compression":[52],"(DVC)":[53],"network,":[54],"but":[55],"improves":[56],"it":[57],"optimizations.":[60],"Specifically,":[61],"a":[62,66,136],"discriminator":[63],"network":[64,74],"mixed":[67],"loss":[68],"are":[69],"employed":[70],"to":[71,87,101],"help":[72],"our":[73,122],"trade":[75],"off":[76],"among":[77],"distortion,":[78],"perception":[79],"rate.":[81],"Furthermore,":[82],"nearest-neighbor":[83],"interpolation":[84],"used":[86],"eliminate":[88],"checkerboard":[89],"artifacts":[90],"can":[92,125],"appear":[93],"in":[94,135],"sequences":[95,110],"encoded":[96],"DVC":[98],"frameworks.":[99],"Thanks":[100],"these":[102],"two":[103],"improvements,":[104],"improved.":[112],"Experimental":[113],"results":[114],"demonstrate":[115],"that,":[116],"compared":[117],"baseline":[120],"DVC,":[121],"method":[124],"generate":[126],"videos":[127],"higher":[129],"achieving":[132],"12.27%":[133],"reduction":[134],"BD-":[138],"rate":[139],"equivalent,":[140],"average.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}