{"id":"https://openalex.org/W2034226292","doi":"https://doi.org/10.1117/12.2080529","title":"Perceptual vector quantization for video coding","display_name":"Perceptual vector quantization for video coding","publication_year":2015,"publication_date":"2015-03-04","ids":{"openalex":"https://openalex.org/W2034226292","doi":"https://doi.org/10.1117/12.2080529","mag":"2034226292"},"language":"en","primary_location":{"id":"doi:10.1117/12.2080529","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2080529","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1602.05209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jean-Marc Valin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Timothy B. Terriberry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy B. Terriberry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1872,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57960885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9410","issue":null,"first_page":"941009","last_page":"941009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.8154000043869019,"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":0.8154000043869019,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.11959999799728394,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.02019999921321869,"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/codec","display_name":"Codec","score":0.6729999780654907},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6585999727249146},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.46779999136924744},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.43470001220703125},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42800000309944153},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3587000072002411},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6729999780654907},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6585999727249146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.529699981212616},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.46779999136924744},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3903999924659729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.3400000035762787},{"id":"https://openalex.org/C91188154","wikidata":"https://www.wikidata.org/wiki/Q186247","display_name":"Vector field","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C80167644","wikidata":"https://www.wikidata.org/wiki/Q463990","display_name":"Harmonic Vector Excitation Coding","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C125864890","wikidata":"https://www.wikidata.org/wiki/Q1262687","display_name":"Intra-frame","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C160987145","wikidata":"https://www.wikidata.org/wiki/Q13043846","display_name":"Pulse-code modulation","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1117/12.2080529","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2080529","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1602.05209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.05209","pdf_url":"https://arxiv.org/pdf/1602.05209","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:1602.05209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.05209","pdf_url":"https://arxiv.org/pdf/1602.05209","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2020053595","https://openalex.org/W2041543977","https://openalex.org/W2063678710","https://openalex.org/W2096588881","https://openalex.org/W2164588373","https://openalex.org/W6630442970","https://openalex.org/W6639363673","https://openalex.org/W6642708267"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"applies":[2],"energy":[3,55,127],"conservation":[4,128],"principles":[5],"to":[6,15,45,61,106,165,183],"the":[7,33,37,47,59,84,87,93,101,108,112,122,136,149,177],"Daala":[8],"video":[9,57],"codec":[10],"using":[11],"gain-shape":[12],"vector":[13,18,109],"quantization":[14,154],"encode":[16],"a":[17,23,70,73,166,184],"of":[19,36,50,89,91,135,142,158],"AC":[20],"coefficients":[21],"as":[22,95],"length":[24],"(gain)":[25],"and":[26],"direction":[27],"(shape).":[28],"The":[29],"technique":[30,151],"originates":[31],"from":[32],"CELT":[34],"mode":[35],"Opus":[38],"audio":[39,52],"codec,":[40],"where":[41],"it":[42,114],"is":[43,115],"used":[44],"conserve":[46],"spectral":[48],"envelope":[49],"an":[51,133,156],"signal.":[53],"Conserving":[54],"in":[56,100,169,187],"has":[58],"potential":[60],"preserve":[62],"textures":[63],"rather":[64,118],"than":[65,119],"low-passing":[66],"them.":[67],"Explicitly":[68],"quantizing":[69,83],"gain":[71],"allows":[72],"simple":[74],"contrast":[75],"masking":[76],"model":[77],"with":[78],"no":[79],"signaling":[80],"cost.":[81],"Vector":[82],"shape":[85],"keeps":[86],"number":[88],"degrees":[90],"freedom":[92],"same":[94],"scalar":[96,153],"quantization,":[97],"avoiding":[98],"redundancy":[99],"representation.":[102],"We":[103,130,146],"demonstrate":[104],"how":[105],"predict":[107],"by":[110,155],"transforming":[111],"space":[113],"encoded":[116],"in,":[117],"subtracting":[120],"off":[121],"predictor,":[123],"which":[124],"would":[125],"make":[126],"impossible.":[129],"also":[131],"derive":[132],"encoding":[134],"vector-quantized":[137],"codewords":[138],"that":[139,148],"takes":[140],"advantage":[141],"their":[143],"non-uniform":[144],"distribution.":[145],"show":[147],"resulting":[150],"outperforms":[152],"average":[157],"0.90":[159],"dB":[160],"on":[161],"still":[162],"images,":[163],"equivalent":[164,182],"24.8%":[167],"reduction":[168,186],"bitrate":[170],"at":[171],"equal":[172],"quality,":[173],"while":[174],"for":[175],"videos,":[176],"improvement":[178],"averages":[179],"0.83":[180],"dB,":[181],"13.7%":[185],"bitrate.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}