Causal Contextual Prediction for Learned Image Compression

Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent representations and then decode them for reconstruction purposes. To ca...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on circuits and systems for video technology Ročník 32; číslo 4; s. 2329 - 2341
Hlavní autoři:	Guo, Zongyu, Zhang, Zhizheng, Feng, Runsen, Chen, Zhibo
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.04.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	causal context model causal global prediction Codec Context Context modeling Correlation Decoding Distortion Entropy Entropy coding Image coding Image compression improved entropy model Learned image compression Optimization Prediction models Predictive models Spatial dependencies Transforms
ISSN:	1051-8215, 1558-2205
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent representations and then decode them for reconstruction purposes. To capture spatial dependencies in the latent space, prior works exploit hyperprior and spatial context model to build an entropy model, which estimates the bit-rate for end-to-end rate-distortion optimization. However, such an entropy model is suboptimal from two aspects: (1) It fails to capture global-scope spatial correlations among the latents. (2) Cross-channel relationships of the latents remain unexplored. In this paper, we propose the concept of separate entropy coding to leverage a serial decoding process for causal contextual entropy prediction in the latent space. A causal context model is proposed that separates the latents across channels and makes use of channel-wise relationships to generate highly informative adjacent contexts. Furthermore, we propose a causal global prediction model to find global reference points for accurate predictions of undecoded points. Both these two models facilitate entropy estimation without the transmission of overhead. In addition, we further adopt a new group-separated attention module to build more powerful transform networks. Experimental results demonstrate that our full image compression model outperforms standard VVC/H.266 codec on Kodak dataset in terms of both PSNR and MS-SSIM, yielding the state-of-the-art rate-distortion performance.
AbstractList	Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent representations and then decode them for reconstruction purposes. To capture spatial dependencies in the latent space, prior works exploit hyperprior and spatial context model to build an entropy model, which estimates the bit-rate for end-to-end rate-distortion optimization. However, such an entropy model is suboptimal from two aspects: (1) It fails to capture global-scope spatial correlations among the latents. (2) Cross-channel relationships of the latents remain unexplored. In this paper, we propose the concept of separate entropy coding to leverage a serial decoding process for causal contextual entropy prediction in the latent space. A causal context model is proposed that separates the latents across channels and makes use of channel-wise relationships to generate highly informative adjacent contexts. Furthermore, we propose a causal global prediction model to find global reference points for accurate predictions of undecoded points. Both these two models facilitate entropy estimation without the transmission of overhead. In addition, we further adopt a new group-separated attention module to build more powerful transform networks. Experimental results demonstrate that our full image compression model outperforms standard VVC/H.266 codec on Kodak dataset in terms of both PSNR and MS-SSIM, yielding the state-of-the-art rate-distortion performance.
Author	Chen, Zhibo Zhang, Zhizheng Feng, Runsen Guo, Zongyu
Author_xml	– sequence: 1 givenname: Zongyu orcidid: 0000-0002-3770-3442 surname: Guo fullname: Guo, Zongyu organization: Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China – sequence: 2 givenname: Zhizheng orcidid: 0000-0002-5360-7565 surname: Zhang fullname: Zhang, Zhizheng organization: Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China – sequence: 3 givenname: Runsen orcidid: 0000-0001-6608-0785 surname: Feng fullname: Feng, Runsen organization: Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China – sequence: 4 givenname: Zhibo orcidid: 0000-0002-8525-5066 surname: Chen fullname: Chen, Zhibo email: chenzhibo@ustc.edu.cn organization: Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China
BookMark	eNp9kE9Lw0AQxRepYFv9AnoJeE7dnd1Ndr1J8B8UFKxel-lmIiltUncT0G9vaosHD57mwbzfPOZN2KhpG2LsXPCZENxeLYqXt8UMOIiZ5MYqK47YWGhtUgCuR4PmWqQGhD5hkxhXnAtlVD5m1wX2EddJ0TYdfXb9IJ8DlbXv6rZJqjYkc8LQUJk8bvCdBt9mGyjGYXvKjitcRzo7zCl7vbtdFA_p_On-sbiZpx6s7lIp0IBBZYmX1kv0FrUxACC8QgDNtUQ0VGGZYaZI47L0XFdyKXIvl7mUU3a5v7sN7UdPsXOrtg_NEOkgU7kCrTM-uGDv8qGNMVDltqHeYPhygrtdR-6nI7fryB06GiDzB_J1h7vXu4D1-n_0Yo_WRPSbZZXWUln5DYfmdis
CODEN	ITCTEM
CitedBy_id	crossref_primary_10_1109_TNNLS_2023_3330864 crossref_primary_10_1109_TCSVT_2023_3323015 crossref_primary_10_1109_TIP_2023_3276333 crossref_primary_10_1109_TCSVT_2025_3551780 crossref_primary_10_1007_s10586_025_05133_2 crossref_primary_10_1109_TCSVT_2022_3199472 crossref_primary_10_1109_TCSVT_2024_3369638 crossref_primary_10_1109_TCSVT_2024_3395481 crossref_primary_10_1145_3661824 crossref_primary_10_1109_TMM_2025_3535279 crossref_primary_10_1109_TIP_2025_3550013 crossref_primary_10_1109_TIP_2025_3567830 crossref_primary_10_1016_j_dsp_2024_104953 crossref_primary_10_1109_TGRS_2024_3483312 crossref_primary_10_1016_j_jvcir_2025_104544 crossref_primary_10_1109_TGRS_2024_3483871 crossref_primary_10_1016_j_sigpro_2023_109128 crossref_primary_10_1109_TCSVT_2024_3415823 crossref_primary_10_1016_j_sigpro_2023_109005 crossref_primary_10_1109_TGRS_2023_3272588 crossref_primary_10_1016_j_sigpro_2022_108778 crossref_primary_10_1109_TCSVT_2023_3313974 crossref_primary_10_1145_3652148 crossref_primary_10_1109_JSTARS_2024_3476990 crossref_primary_10_1109_TII_2022_3204681 crossref_primary_10_1109_TCE_2024_3485179 crossref_primary_10_1016_j_sigpro_2024_109741 crossref_primary_10_1016_j_knosys_2025_112996 crossref_primary_10_1109_TCSVT_2022_3231789 crossref_primary_10_3390_bdcc9010014 crossref_primary_10_56294_dm20251055 crossref_primary_10_1016_j_jvcir_2024_104294 crossref_primary_10_1145_3719011 crossref_primary_10_1109_JSEN_2025_3569520 crossref_primary_10_1109_TCSVT_2023_3237274 crossref_primary_10_1109_TCSVT_2024_3371178 crossref_primary_10_1109_TCSVT_2024_3455576 crossref_primary_10_1109_TCSVT_2024_3376704 crossref_primary_10_1109_TCSVT_2023_3300316 crossref_primary_10_1109_TCSVT_2024_3401872 crossref_primary_10_1016_j_jvcir_2025_104456 crossref_primary_10_1109_JETCAS_2024_3403524 crossref_primary_10_1109_JETCAS_2024_3385653 crossref_primary_10_1016_j_neunet_2024_106909 crossref_primary_10_1109_TBC_2024_3443470 crossref_primary_10_1016_j_image_2024_117227 crossref_primary_10_1117_1_JEI_32_4_043023 crossref_primary_10_1109_TCSVT_2024_3360248 crossref_primary_10_1109_TCSVT_2022_3216713 crossref_primary_10_1109_TCSVT_2025_3552971 crossref_primary_10_1109_TIP_2023_3287495 crossref_primary_10_1109_TCSVT_2024_3371686 crossref_primary_10_1109_TCSVT_2024_3395275 crossref_primary_10_1007_s00521_025_11138_0 crossref_primary_10_1109_TPAMI_2024_3356557 crossref_primary_10_1109_ACCESS_2023_3236086 crossref_primary_10_3390_s22041357 crossref_primary_10_3390_e26050357 crossref_primary_10_1109_TMM_2024_3416831 crossref_primary_10_1109_JETCAS_2025_3538652 crossref_primary_10_1007_s00530_025_01945_9 crossref_primary_10_1109_JSTARS_2025_3584931 crossref_primary_10_3390_rs17132189 crossref_primary_10_1109_TCSVT_2025_3556708 crossref_primary_10_1109_TII_2024_3431082 crossref_primary_10_1109_TCSVT_2022_3195322 crossref_primary_10_3390_rs17142419 crossref_primary_10_1016_j_engappai_2023_106361 crossref_primary_10_1109_TMM_2022_3220421 crossref_primary_10_1109_TCSVT_2022_3150014 crossref_primary_10_1007_s00371_024_03571_4
Cites_doi	10.1109/CVPR42600.2020.00796 10.1109/76.911157 10.1109/CVPR.2016.90 10.1109/TCSVT.2012.2221191 10.1109/CVPR.2017.577 10.1109/TCSVT.2003.815165 10.1109/CVPR42600.2020.01042 10.1109/ICCV.2019.00031 10.1109/TCSVT.2015.2478706 10.1109/TIP.2003.819861 10.1109/CVPR.2019.00440 10.1109/30.125072 10.1109/CVPR.2018.00813 10.1117/1.1469618 10.1109/CVPR.2018.00339 10.1109/TNNLS.2021.3104974 10.1109/ICME.2019.00249 10.1109/CVPR.2018.00461 10.1109/TCOM.1974.1092258 10.1109/CVPR.2009.5206848 10.1109/CVPR.2018.00462 10.1109/CVPRW50498.2020.00066 10.1109/79.952802 10.1109/CVPRW.2019.00261
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TCSVT.2021.3089491
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-2205
EndPage	2341
ExternalDocumentID	10_1109_TCSVT_2021_3089491 9455349
Genre	orig-research
GrantInformation_xml	– fundername: NSFC grantid: U1908209; 61632001 funderid: 10.13039/501100001809 – fundername: National Key Research and Development Program of China grantid: 2018AAA0101400 funderid: 10.13039/501100012166
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c295t-31a828a49e0d9c3ac9a5882221c4a225053aa8efad6a64e5abdc05f3b17c3b733
IEDL.DBID	RIE
ISICitedReferencesCount	113
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000778973700051&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1051-8215
IngestDate	Sun Jun 29 16:17:21 EDT 2025 Tue Nov 18 22:32:14 EST 2025 Sat Nov 29 01:44:16 EST 2025 Wed Aug 27 02:40:50 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c295t-31a828a49e0d9c3ac9a5882221c4a225053aa8efad6a64e5abdc05f3b17c3b733
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3770-3442 0000-0002-5360-7565 0000-0002-8525-5066 0000-0001-6608-0785
PQID	2647425560
PQPubID	85433
PageCount	13
ParticipantIDs	proquest_journals_2647425560 crossref_citationtrail_10_1109_TCSVT_2021_3089491 crossref_primary_10_1109_TCSVT_2021_3089491 ieee_primary_9455349
PublicationCentury	2000
PublicationDate	2022-04-01
PublicationDateYYYYMMDD	2022-04-01
PublicationDate_xml	– month: 04 year: 2022 text: 2022-04-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on circuits and systems for video technology
PublicationTitleAbbrev	TCSVT
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref15 ref14 ref36 ref31 Lee (ref29) 2019 Sullivan (ref22) ref1 ref17 ref38 Ballé (ref9) Lee (ref11) Van Oord (ref12) ref19 ref18 Ballé (ref40) Chen (ref30) 2019 van den Oord (ref35) 2016 Helminger (ref45) 2020 ref23 Agustsson (ref25) ref26 ref20 ref42 ref41 ref21 ref43 Salimans (ref34) 2017 Chen (ref39) ref28 ref27 ref8 Minnen (ref10) Zhang (ref16) 2020 ref7 ref4 ref3 Higgins (ref33) ref6 Kingma (ref32) 2013 Kingma (ref44) 2014 Wiegand (ref37) 2003 Theis (ref24) 2017 Forchheimer (ref2) Ballé (ref5) 2018
References_xml	– year: 2017 ident: ref34 article-title: PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications publication-title: arXiv:1701.05517 – start-page: 15 volume-title: Proc. Picture Coding Symp. (PCS) ident: ref2 article-title: Differential transform coding: A new hybrid coding scheme – ident: ref7 doi: 10.1109/CVPR42600.2020.00796 – ident: ref26 doi: 10.1109/76.911157 – volume-title: Draft ITU-T Recommendation and Final Draft International Standard of Joint Video Specification (ITU-T Rec. H. 264\|ISO/IEC 14496-10 AVC) year: 2003 ident: ref37 – ident: ref41 doi: 10.1109/CVPR.2016.90 – ident: ref21 doi: 10.1109/TCSVT.2012.2221191 – ident: ref4 doi: 10.1109/CVPR.2017.577 – ident: ref3 doi: 10.1109/TCSVT.2003.815165 – ident: ref15 doi: 10.1109/CVPR42600.2020.01042 – ident: ref6 doi: 10.1109/ICCV.2019.00031 – start-page: 1747 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref12 article-title: Pixel recurrent neural networks – ident: ref23 doi: 10.1109/TCSVT.2015.2478706 – ident: ref17 doi: 10.1109/TIP.2003.819861 – ident: ref36 doi: 10.1109/CVPR.2019.00440 – volume-title: Proc. Picture Coding Symp. (PCS) ident: ref22 article-title: Versatile video coding–towards the next generation of video compression – ident: ref19 doi: 10.1109/30.125072 – year: 2020 ident: ref45 article-title: Lossy image compression with normalizing flows publication-title: arXiv:2008.10486 – start-page: 10771 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref10 article-title: Joint autoregressive and hierarchical priors for learned image compression – volume-title: Proc. ICLR ident: ref33 article-title: beta-VAE: Learning basic visual concepts with a constrained variational framework – ident: ref38 doi: 10.1109/CVPR.2018.00813 – year: 2016 ident: ref35 article-title: WaveNet: A generative model for raw audio publication-title: arXiv:1609.03499 – ident: ref20 doi: 10.1117/1.1469618 – ident: ref13 doi: 10.1109/CVPR.2018.00339 – year: 2019 ident: ref30 article-title: Neural image compression via non-local attention optimization and improved context modeling publication-title: arXiv:1910.06244 – ident: ref31 doi: 10.1109/TNNLS.2021.3104974 – year: 2013 ident: ref32 article-title: Auto-encoding variational Bayes publication-title: arXiv:1312.6114 – ident: ref27 doi: 10.1109/ICME.2019.00249 – ident: ref14 doi: 10.1109/CVPR.2018.00461 – volume-title: Proc. 7th Int. Conf. Learn. Represent. (ICLR) ident: ref11 article-title: Context-adaptive entropy model for end-to-end optimized image compression – ident: ref1 doi: 10.1109/TCOM.1974.1092258 – year: 2017 ident: ref24 article-title: Lossy image compression with compressive autoencoders publication-title: arXiv:1703.00395 – ident: ref43 doi: 10.1109/CVPR.2009.5206848 – ident: ref28 doi: 10.1109/CVPR.2018.00462 – year: 2019 ident: ref29 article-title: An end-to-end joint learning scheme of image compression and quality enhancement with improved entropy minimization publication-title: arXiv:1912.12817 – start-page: 864 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref39 article-title: PixelSNAIL: An improved autoregressive generative model – year: 2018 ident: ref5 article-title: Variational image compression with a scale hyperprior publication-title: arXiv:1802.01436 – volume-title: Proc. 5th Int. Conf. Learn. Representation (ICLR) ident: ref9 article-title: End-to-end optimized image compression – ident: ref18 doi: 10.1109/CVPRW50498.2020.00066 – start-page: 1141 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref25 article-title: Soft-to-hard vector quantization for end-to-end learning compressible representations – year: 2020 ident: ref16 article-title: ResNeSt: Split-attention networks publication-title: arXiv:2004.08955 – volume-title: Proc. 4th Int. Conf. Learn. Represent. (ICLR) ident: ref40 article-title: Density modeling of images using a generalized normalization transformation – ident: ref8 doi: 10.1109/79.952802 – year: 2014 ident: ref44 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – ident: ref42 doi: 10.1109/CVPRW.2019.00261
SSID	ssj0014847
Score	2.6412916
Snippet	Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	2329
SubjectTerms	causal context model causal global prediction Codec Context Context modeling Correlation Decoding Distortion Entropy Entropy coding Image coding Image compression improved entropy model Learned image compression Optimization Prediction models Predictive models Spatial dependencies Transforms
Title	Causal Contextual Prediction for Learned Image Compression
URI	https://ieeexplore.ieee.org/document/9455349 https://www.proquest.com/docview/2647425560
Volume	32
WOSCitedRecordID	wos000778973700051&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2205 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014847 issn: 1051-8215 databaseCode: RIE dateStart: 19910101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB7a4kEPvqpYrZKDN02bzW4e602KRS-lYJXewmYzAUHT0of4853dpEFRBG8h7ECYSWa-ycx8A3CZSgqLuYhcIVPuCkIcbmqm0TKlQ-6zUKeRtssmotEonk7luAHX9SwMItrmM-yZS1vLz2Z6bX6V9aUIAi5kE5pRFJazWnXFQMR2mRjBBebGFMc2AzKe7E8Gj88TSgV91uNeLIVk34KQ3arywxXb-DLc-9-T7cNuhSOd29LwB9DA4hB2vrALtuFmoNZLOmMJqD7MnIgzXpi6jLGFQ2DVseSqmDkPb-RVHOMayq7Y4giehneTwb1brUpwtS-DFXlSRamTEhK9TGqutFRBbGI_00L5BuZwpWLMVRaqUGCg0kx7Qc5TFmmeRpwfQ6uYFXgCDorcZ-hpn-4LT5CUIWxhGBO0yZDrDrCN7hJd8YibdRavic0nPJlYfSdG30ml7w5c1TLzkkXjz9Nto-H6ZKXcDnQ3JkqqD22ZEJ6j5D4g3Hb6u9QZbPtmYsE223ShtVqs8Ry29PvqZbm4sO_QJ5rgwoE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5qFdSDryrWZw7eNG02u3msNymWFmspGKW3ZbPZgKCt9CH-fGe3aVAUwVsIOxBmkplvMjPfAFykHMNiziKX8ZS6DBGHm5pptEyqkPokVGmk7LKJqN-Ph0M-qMBVOQujtbbNZ7phLm0tPxuruflV1uQsCCjjK7BqNmcV01plzYDFdp0YAgbixhjJliMyHm8mrYenBJNBnzSoF3PGybcwZPeq_HDGNsK0t__3bDuwVSBJ52Zh-l2o6NEebH7hF6zBdUvOp3jGUlB9mEkRZzAxlRljDQfhqmPpVXXmdF_RrzjGOSz6Ykf78Ni-TVodt1iW4CqfBzP0pRKTJ8m49jKuqFRcBrGJ_kQx6RugQ6WMdS6zUIZMBzLNlBfkNCWRomlE6QFUR-ORPgRHs9wn2lM-3mceQylD2UJ0jOAm01TVgSx1J1TBJG4WWrwIm1F4XFh9C6NvUei7DpelzNuCR-PP0zWj4fJkodw6nCxNJIpPbSoQ0WF6HyByO_pd6hzWO8l9T_S6_btj2PDN_IJtvTmB6mwy16ewpt5nz9PJmX2fPgHqicXK
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Causal+Contextual+Prediction+for+Learned+Image+Compression&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Guo%2C+Zongyu&rft.au=Zhang%2C+Zhizheng&rft.au=Feng%2C+Runsen&rft.au=Chen%2C+Zhibo&rft.date=2022-04-01&rft.pub=IEEE&rft.issn=1051-8215&rft.volume=32&rft.issue=4&rft.spage=2329&rft.epage=2341&rft_id=info:doi/10.1109%2FTCSVT.2021.3089491&rft.externalDocID=9455349
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon