{"id":"https://openalex.org/W4360594820","doi":"https://doi.org/10.1109/tpami.2023.3260684","title":"Insights From Generative Modeling for Neural Video Compression","display_name":"Insights From Generative Modeling for Neural Video Compression","publication_year":2023,"publication_date":"2023-03-22","ids":{"openalex":"https://openalex.org/W4360594820","doi":"https://doi.org/10.1109/tpami.2023.3260684","pmid":"https://pubmed.ncbi.nlm.nih.gov/37030706"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3260684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3260684","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5085270850","display_name":"Ruihan Yang","orcid":"https://orcid.org/0000-0003-3154-4150"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruihan Yang","raw_affiliation_strings":["Department of Computer Science, University of California Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3154-4150","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073343865","display_name":"Yibo Yang","orcid":"https://orcid.org/0000-0001-8943-0354"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yibo Yang","raw_affiliation_strings":["Department of Computer Science, University of California Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8943-0354","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103092941","display_name":"Joseph Marino","orcid":"https://orcid.org/0000-0001-6387-8062"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Marino","raw_affiliation_strings":["DeepMind, California Institute of Technology, Pasadena, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6387-8062","affiliations":[{"raw_affiliation_string":"DeepMind, California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036302820","display_name":"Stephan Mandt","orcid":"https://orcid.org/0000-0001-7836-7839"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephan Mandt","raw_affiliation_strings":["Department of Computer Science, University of California Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7836-7839","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1626,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.7696329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"45","issue":"8","first_page":"9908","last_page":"9921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"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":0.998199999332428,"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":0.9980000257492065,"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":0.7477005124092102},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7383933663368225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.650729775428772},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5779227614402771},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45728179812431335},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.44983750581741333},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4306694269180298},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.42705345153808594},{"id":"https://openalex.org/keywords/entropy-encoding","display_name":"Entropy encoding","score":0.4225742220878601},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4192752242088318},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36403167247772217},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.34949153661727905},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1281522810459137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477005124092102},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7383933663368225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.650729775428772},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5779227614402771},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45728179812431335},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.44983750581741333},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4306694269180298},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.42705345153808594},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.4225742220878601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4192752242088318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36403167247772217},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34949153661727905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1281522810459137},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3260684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3260684","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37030706","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37030706","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G304896731","display_name":"DISCOVERING PHYSICALLY MEANINGFUL STRUCTURES FROM CLIMATE EXTREME DATA","funder_award_id":"DESC0022331","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1580389772","https://openalex.org/W1583912456","https://openalex.org/W1634005169","https://openalex.org/W1959608418","https://openalex.org/W2042941801","https://openalex.org/W2099111195","https://openalex.org/W2105934661","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2166816543","https://openalex.org/W2169161136","https://openalex.org/W2242818861","https://openalex.org/W2490784316","https://openalex.org/W2511458122","https://openalex.org/W2552465432","https://openalex.org/W2597747080","https://openalex.org/W2769654144","https://openalex.org/W2785562966","https://openalex.org/W2789625992","https://openalex.org/W2798514732","https://openalex.org/W2963149687","https://openalex.org/W2963189365","https://openalex.org/W2969260367","https://openalex.org/W2970264339","https://openalex.org/W2982853315","https://openalex.org/W2984671549","https://openalex.org/W2987947587","https://openalex.org/W2992051623","https://openalex.org/W2998444797","https://openalex.org/W3015214864","https://openalex.org/W3018065762","https://openalex.org/W3031546776","https://openalex.org/W3034802763","https://openalex.org/W3035195755","https://openalex.org/W3038130890","https://openalex.org/W3080588957","https://openalex.org/W3091266734","https://openalex.org/W3095497211","https://openalex.org/W3098284407","https://openalex.org/W3102015846","https://openalex.org/W3110286842","https://openalex.org/W3150807214","https://openalex.org/W4283028628","https://openalex.org/W4287992216","https://openalex.org/W4297798428","https://openalex.org/W4298157202","https://openalex.org/W4367465468","https://openalex.org/W4385245566","https://openalex.org/W6610566761","https://openalex.org/W6617744952","https://openalex.org/W6631190155","https://openalex.org/W6635084905","https://openalex.org/W6640963894","https://openalex.org/W6680537413","https://openalex.org/W6687045409","https://openalex.org/W6690026940","https://openalex.org/W6714644935","https://openalex.org/W6726983635","https://openalex.org/W6733471323","https://openalex.org/W6734035190","https://openalex.org/W6738536549","https://openalex.org/W6745420753","https://openalex.org/W6748392304","https://openalex.org/W6750411654","https://openalex.org/W6750642828","https://openalex.org/W6752738198","https://openalex.org/W6752910514","https://openalex.org/W6754634825","https://openalex.org/W6762845226","https://openalex.org/W6764882207","https://openalex.org/W6770167780","https://openalex.org/W6770847983","https://openalex.org/W6772273962","https://openalex.org/W6772406126","https://openalex.org/W6772911725","https://openalex.org/W6778914582","https://openalex.org/W6779301693","https://openalex.org/W6781514527","https://openalex.org/W6782786913","https://openalex.org/W6839976848"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"While":[0],"recent":[1],"machine":[2],"learning":[3],"research":[4],"has":[5,26],"revealed":[6],"connections":[7],"between":[8],"deep":[9,46],"generative":[10,142],"models":[11,110],"such":[12],"as":[13,56],"VAEs":[14],"and":[15,48,65,76,92,96,113,116],"rate-distortion":[16],"losses":[17],"used":[18],"in":[19],"learned":[20],"compression,":[21],"most":[22],"of":[23,45,58,121,133],"this":[24],"work":[25],"focused":[27],"on":[28,89],"images.":[29],"In":[30,98],"a":[31,59,130],"similar":[32],"spirit,":[33],"we":[34,100,136],"view":[35],"recently":[36],"proposed":[37],"neural":[38,148],"video":[39,86,91,149],"coding":[40,150],"algorithms":[41],"through":[42],"the":[43,141,147],"lens":[44],"autoregressive":[47,63,105],"latent":[49],"variable":[50,118],"modeling.":[51],"We":[52,79],"present":[53],"these":[54],"codecs":[55],"instances":[57],"generalized":[60],"stochastic":[61],"temporal":[62,104,114],"transform,":[64],"propose":[66,80,101],"new":[67],"avenues":[68],"for":[69],"further":[70,138],"improvements":[71,126],"inspired":[72],"by":[73],"normalizing":[74],"flows":[75],"structured":[77,112],"priors.":[78],"several":[81],"architectures":[82],"that":[83,140],"yield":[84],"state-of-the-art":[85],"compression":[87],"performance":[88],"high-resolution":[90],"discuss":[93],"their":[94],"tradeoffs":[95],"ablations.":[97],"particular,":[99],"(i)":[102],"improved":[103,108],"transforms,":[106],"(ii)":[107],"entropy":[109],"with":[111,129],"dependencies,":[115],"(iii)":[117],"bitrate":[119],"versions":[120],"our":[122,125],"algorithms.":[123],"Since":[124],"are":[127],"compatible":[128],"large":[131],"class":[132],"existing":[134],"models,":[135],"provide":[137],"evidence":[139],"modeling":[143],"viewpoint":[144],"can":[145],"advance":[146],"field.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}