Joint channel–spatial entropy modeling for efficient visual coding

Deep learning-based methods have recently achieved impressive performance in lossy image compression, surpassing traditional codecs in rate-distortion efficiency. However, current learned compressors still struggle to fully exploit crossed-channel redundancies and long-range spatial dependencies in...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Neural computing & applications Ročník 37; číslo 21; s. 17111 - 17128
Hlavní autoři:	Li, Yuan, Jiang, Xiaotong, Sun, Zitang
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London Springer London 01.07.2025 Springer Nature B.V
Témata:	Artificial Intelligence Codec Coding Compressors Computational Biology/Bioinformatics Computational Science and Engineering Computer Science Context Data Mining and Knowledge Discovery Decoding Entropy Image compression Image Processing and Computer Vision Lagrange multiplier Modelling Normal distribution Original Article Probability and Statistics in Computer Science Representations Semantics Spatial dependencies Wavelet transforms Self-attention mechanism Lossy image compression Joint channel-spatial context Adaptive neighbored information
ISSN:	0941-0643, 1433-3058
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Deep learning-based methods have recently achieved impressive performance in lossy image compression, surpassing traditional codecs in rate-distortion efficiency. However, current learned compressors still struggle to fully exploit crossed-channel redundancies and long-range spatial dependencies in their latent representations, and many rely on sequential context models that slow down decoding. To address these issues, we propose a novel compression framework that performs joint channel–spatial context modeling for improved entropy coding. Our approach introduces a Multi-Dimensional Conditional Context (MDCC) architecture, which integrates a new non-serial channel-wise context model with spatial context conditioning to capture inter-channel correlations and local dependencies simultaneously. In addition, we design a Residual Local–Global Enhancement module that combines ConvNeXt convolutional blocks and Swin Transformer-based to capture fine-grained textures and global image structure in the latent representation. By augmenting the standard hyperprior with these rich contextual cues, the proposed method more accurately estimates latent distributions, leading to superior compression performance. Experiments on the Kodak and CLIC image datasets demonstrate that the proposed approach achieves up to a 17% bit-rate reduction over the latest VVC (H.266) standard at comparable quality. Furthermore, our model eliminates the autoregressive decoding bottleneck, enabling nearly a 10× faster decoding speed compared to previous state-of-the-art learned compression models. These results establish the effectiveness of joint channel–spatial context modeling and highlight the potential of the proposed MDCC framework for practical, high-performance neural image compression.
AbstractList	Deep learning-based methods have recently achieved impressive performance in lossy image compression, surpassing traditional codecs in rate-distortion efficiency. However, current learned compressors still struggle to fully exploit crossed-channel redundancies and long-range spatial dependencies in their latent representations, and many rely on sequential context models that slow down decoding. To address these issues, we propose a novel compression framework that performs joint channel–spatial context modeling for improved entropy coding. Our approach introduces a Multi-Dimensional Conditional Context (MDCC) architecture, which integrates a new non-serial channel-wise context model with spatial context conditioning to capture inter-channel correlations and local dependencies simultaneously. In addition, we design a Residual Local–Global Enhancement module that combines ConvNeXt convolutional blocks and Swin Transformer-based to capture fine-grained textures and global image structure in the latent representation. By augmenting the standard hyperprior with these rich contextual cues, the proposed method more accurately estimates latent distributions, leading to superior compression performance. Experiments on the Kodak and CLIC image datasets demonstrate that the proposed approach achieves up to a 17% bit-rate reduction over the latest VVC (H.266) standard at comparable quality. Furthermore, our model eliminates the autoregressive decoding bottleneck, enabling nearly a 10× faster decoding speed compared to previous state-of-the-art learned compression models. These results establish the effectiveness of joint channel–spatial context modeling and highlight the potential of the proposed MDCC framework for practical, high-performance neural image compression. Deep learning-based methods have recently achieved impressive performance in lossy image compression, surpassing traditional codecs in rate-distortion efficiency. However, current learned compressors still struggle to fully exploit crossed-channel redundancies and long-range spatial dependencies in their latent representations, and many rely on sequential context models that slow down decoding. To address these issues, we propose a novel compression framework that performs joint channel–spatial context modeling for improved entropy coding. Our approach introduces a Multi-Dimensional Conditional Context (MDCC) architecture, which integrates a new non-serial channel-wise context model with spatial context conditioning to capture inter-channel correlations and local dependencies simultaneously. In addition, we design a Residual Local–Global Enhancement module that combines ConvNeXt convolutional blocks and Swin Transformer-based to capture fine-grained textures and global image structure in the latent representation. By augmenting the standard hyperprior with these rich contextual cues, the proposed method more accurately estimates latent distributions, leading to superior compression performance. Experiments on the Kodak and CLIC image datasets demonstrate that the proposed approach achieves up to a 17% bit-rate reduction over the latest VVC (H.266) standard at comparable quality. Furthermore, our model eliminates the autoregressive decoding bottleneck, enabling nearly a 10× faster decoding speed compared to previous state-of-the-art learned compression models. These results establish the effectiveness of joint channel–spatial context modeling and highlight the potential of the proposed MDCC framework for practical, high-performance neural image compression.
Author	Li, Yuan Jiang, Xiaotong Sun, Zitang
Author_xml	– sequence: 1 givenname: Yuan surname: Li fullname: Li, Yuan organization: Graduate School of IPS, Waseda University – sequence: 2 givenname: Xiaotong surname: Jiang fullname: Jiang, Xiaotong organization: Graduate School of IPS, Waseda University – sequence: 3 givenname: Zitang orcidid: 0000-0003-2267-421X surname: Sun fullname: Sun, Zitang email: sun.zitang.c09@kyoto-u.jp organization: Graduate School of Informatics, Kyoto University
BookMark	eNp9kL1OwzAUhS1UJNrCCzBFYg5c_7sjKv-qxAKz5ThOSZXawU6RuvEOvCFPgiFIbEx3ON85V_pmaOKDdwidYjjHAPIiAXCCSyC8xBhTVcIBmmJGaUmBqwmawoLlWDB6hGYpbQCACcWn6OohtH4o7Ivx3nWf7x-pN0NrusL5IYZ-X2xD7brWr4smxMI1TWvbHBVvbdplyoY6Z8fosDFdcie_d46eb66flnfl6vH2fnm5Ki1WEkrGTOWksBXmhGLlCLeSVMQKIkldCcGYNJZWRkiraLXglgtHQKhaUgWqknSOzsbdPobXnUuD3oRd9PmlpnlxIRUX3xQZKRtDStE1uo_t1sS9xqC_benRls629I8tDblEx1LKsF-7-Df9T-sLbzFuoQ
Cites_doi	10.1109/CVPR52688.2022.00590 10.1109/CVPR52688.2022.00563 10.1109/TCSVT.2021.3072430 10.1109/TCSVT.2022.3150014 10.1109/TCSVT.2021.3089491 10.1109/WACV56688.2023.00493 10.1109/TIP.2020.2985225 10.1109/ICASSP49357.2023.10095875 10.1145/3474085.3475213 10.1109/WACV56688.2023.00028 10.1109/CVPR42600.2020.00796 10.1109/CVPR.2016.90 10.1109/DCC52660.2022.00080 10.1109/CVPR52688.2022.01167 10.1109/TPAMI.2023.3322904 10.1109/CVPR52688.2022.01697 10.1109/CVPR52729.2023.00599 10.1109/ICCVW54120.2021.00210 10.1109/CVPR46437.2021.01453 10.1109/TIP.2021.3058615 10.1109/ICCV48922.2021.00986 10.1109/TIT.1973.1055037 10.1109/ICIP40778.2020.9190935
ContentType	Journal Article
Copyright	The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.
Copyright_xml	– notice: The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.
DBID	AAYXX CITATION
DOI	10.1007/s00521-025-11138-0
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	1433-3058
EndPage	17128
ExternalDocumentID	10_1007_s00521_025_11138_0
GroupedDBID	-Y2 -~C .4S .86 .DC .VR 06D 0R~ 0VY 123 1N0 1SB 2.D 203 28- 29N 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 53G 5QI 5VS 67Z 6NX 8FE 8FG 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAOBN AAPKM AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBRH ABBXA ABDBE ABDBF ABDZT ABECU ABFSG ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABLJU ABMNI ABMQK ABNWP ABQBU ABQSL ABRTQ ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACSTC ACUHS ACZOJ ADHHG ADHIR ADHKG ADIMF ADKFA ADKNI ADKPE ADMLS ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AEZWR AFBBN AFDZB AFEXP AFGCZ AFHIU AFKRA AFLOW AFOHR AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGQPQ AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHPBZ AHSBF AHWEU AHYZX AIAKS AIGIU AIIXL AILAN AITGF AIXLP AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG ATHPR AVWKF AXYYD AYFIA AYJHY AZFZN B-. B0M BA0 BBWZM BDATZ BENPR BGLVJ BGNMA BSONS CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 EAD EAP EBLON EBS ECS EDO EIOEI EJD EMI EMK EPL ESBYG EST ESX F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IHE IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV KOW LAS LLZTM M4Y MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM P19 P2P P62 P9O PF0 PHGZM PHGZT PQGLB PT4 PT5 QOK QOS R4E R89 R9I RHV RIG RNI RNS ROL RPX RSV RZK S16 S1Z S26 S27 S28 S3B SAP SCJ SCLPG SCO SDH SDM SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 ZMTXR ~8M ~EX AAYXX AFFHD CITATION
ID	FETCH-LOGICAL-c1870-44abe76cb152318e25c72b2c6272db66447ac3ba67c83b95c56e2068d73808b73
IEDL.DBID	RSV
ISSN	0941-0643
IngestDate	Wed Nov 05 06:25:16 EST 2025 Sat Nov 29 07:33:27 EST 2025 Tue Jul 22 01:11:29 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	21
Keywords	Self-attention mechanism Lossy image compression Joint channel-spatial context Adaptive neighbored information
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c1870-44abe76cb152318e25c72b2c6272db66447ac3ba67c83b95c56e2068d73808b73
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2267-421X
PQID	3231978567
PQPubID	2043988
PageCount	18
ParticipantIDs	proquest_journals_3231978567 crossref_primary_10_1007_s00521_025_11138_0 springer_journals_10_1007_s00521_025_11138_0
PublicationCentury	2000
PublicationDate	20250700 2025-07-00 20250701
PublicationDateYYYYMMDD	2025-07-01
PublicationDate_xml	– month: 7 year: 2025 text: 20250700
PublicationDecade	2020
PublicationPlace	London
PublicationPlace_xml	– name: London – name: Heidelberg
PublicationTitle	Neural computing & applications
PublicationTitleAbbrev	Neural Comput & Applic
PublicationYear	2025
Publisher	Springer London Springer Nature B.V
Publisher_xml	– name: Springer London – name: Springer Nature B.V
References	11138_CR19 M Rabbani (11138_CR2) 2002; 17 T Xiao (11138_CR32) 2021; 34 11138_CR23 J Pfaff (11138_CR4) 2021; 31 11138_CR5 11138_CR22 11138_CR44 11138_CR6 11138_CR25 11138_CR7 11138_CR24 11138_CR46 11138_CR27 D Slepian (11138_CR30) 1973; 19 11138_CR26 GK Wallace (11138_CR1) 1991; 38 11138_CR29 11138_CR3 11138_CR28 11138_CR40 11138_CR21 11138_CR43 11138_CR20 Z Duan (11138_CR41) 2024; 46 11138_CR42 Z Guo (11138_CR45) 2021; 32 11138_CR8 11138_CR9 11138_CR12 11138_CR34 11138_CR11 H Liu (11138_CR15) 2022; 32 11138_CR33 11138_CR14 11138_CR36 11138_CR13 11138_CR38 11138_CR37 11138_CR18 11138_CR17 11138_CR39 M Li (11138_CR35) 2020; 29 11138_CR10 T Chen (11138_CR16) 2021; 30 11138_CR31
References_xml	– ident: 11138_CR34 doi: 10.1109/CVPR52688.2022.00590 – ident: 11138_CR11 doi: 10.1109/CVPR52688.2022.00563 – ident: 11138_CR31 – volume: 31 start-page: 3834 issue: 10 year: 2021 ident: 11138_CR4 publication-title: IEEE Trans Circuits Syst Video Technol doi: 10.1109/TCSVT.2021.3072430 – volume: 32 start-page: 5650 issue: 8 year: 2022 ident: 11138_CR15 publication-title: IEEE Trans Circuits Syst Video Technol doi: 10.1109/TCSVT.2022.3150014 – ident: 11138_CR37 – ident: 11138_CR14 – volume: 32 start-page: 2329 issue: 4 year: 2021 ident: 11138_CR45 publication-title: IEEE Trans Circuits Syst Video Technol doi: 10.1109/TCSVT.2021.3089491 – ident: 11138_CR10 – ident: 11138_CR44 doi: 10.1109/WACV56688.2023.00493 – volume: 29 start-page: 5900 year: 2020 ident: 11138_CR35 publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2020.2985225 – ident: 11138_CR25 doi: 10.1109/ICASSP49357.2023.10095875 – ident: 11138_CR42 doi: 10.1145/3474085.3475213 – ident: 11138_CR18 – ident: 11138_CR46 – ident: 11138_CR19 doi: 10.1109/WACV56688.2023.00028 – ident: 11138_CR39 – ident: 11138_CR7 – ident: 11138_CR12 doi: 10.1109/CVPR42600.2020.00796 – ident: 11138_CR33 doi: 10.1109/CVPR.2016.90 – ident: 11138_CR17 doi: 10.1109/DCC52660.2022.00080 – volume: 38 start-page: 43 issue: 1 year: 1991 ident: 11138_CR1 publication-title: Commun ACM – volume: 17 start-page: 3 year: 2002 ident: 11138_CR2 publication-title: ELSEVIER Signal Process: Image Commun – ident: 11138_CR27 – ident: 11138_CR40 – ident: 11138_CR21 – ident: 11138_CR22 doi: 10.1109/CVPR52688.2022.01167 – volume: 46 start-page: 436 issue: 1 year: 2024 ident: 11138_CR41 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2023.3322904 – ident: 11138_CR3 – ident: 11138_CR5 – volume: 34 start-page: 30392 year: 2021 ident: 11138_CR32 publication-title: Adv Neural Inf Process Syst – ident: 11138_CR38 – ident: 11138_CR36 – ident: 11138_CR13 doi: 10.1109/CVPR52688.2022.01697 – ident: 11138_CR29 doi: 10.1109/CVPR52729.2023.00599 – ident: 11138_CR28 doi: 10.1109/ICCVW54120.2021.00210 – ident: 11138_CR43 – ident: 11138_CR8 – ident: 11138_CR6 doi: 10.1109/CVPR46437.2021.01453 – ident: 11138_CR24 – volume: 30 start-page: 3179 year: 2021 ident: 11138_CR16 publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2021.3058615 – ident: 11138_CR26 – ident: 11138_CR23 doi: 10.1109/ICCV48922.2021.00986 – volume: 19 start-page: 471 issue: 4 year: 1973 ident: 11138_CR30 publication-title: IEEE Trans Inf Theor doi: 10.1109/TIT.1973.1055037 – ident: 11138_CR9 doi: 10.1109/ICIP40778.2020.9190935 – ident: 11138_CR20
SSID	ssj0004685
Score	2.3847444
Snippet	Deep learning-based methods have recently achieved impressive performance in lossy image compression, surpassing traditional codecs in rate-distortion...
SourceID	proquest crossref springer
SourceType	Aggregation Database Index Database Publisher
StartPage	17111
SubjectTerms	Artificial Intelligence Codec Coding Compressors Computational Biology/Bioinformatics Computational Science and Engineering Computer Science Context Data Mining and Knowledge Discovery Decoding Entropy Image compression Image Processing and Computer Vision Lagrange multiplier Modelling Normal distribution Original Article Probability and Statistics in Computer Science Representations Semantics Spatial dependencies Wavelet transforms
Title	Joint channel–spatial entropy modeling for efficient visual coding
URI	https://link.springer.com/article/10.1007/s00521-025-11138-0 https://www.proquest.com/docview/3231978567
Volume	37
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAVX databaseName: SpringerLINK Contemporary Journals customDbUrl: eissn: 1433-3058 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004685 issn: 0941-0643 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NSgMxEB6kevBi_cVqlRy8aWDNZjfZo6hFRIr4R29Lkk2hILul2xa8-Q6-oU_iJN1tVfSg52SzYTKTbyaZyQdwhAjEuOaK6kQYypllVLEsof0gixKZKBHMCoVvRLcre73ktioKK-ts9_pK0u_U82I3d4KJoS-LqKNHlxQD9WWEO-kIG-7unz5VQ3oiToxbXE4PD6tSmZ_H-ApHCx_z27WoR5tO83_zXIe1yrskZzN12IAlm29Cs2ZuIJUhb8HFdTHIx8RV_eb2-f31rXSJ1filO-sthi_EE-TgXwn6tMT6ZyawiUwH5QR7mcIh3jY8di4fzq9oxadAzSmaJeVcaStioxGz0ZQti4xgmpmYCZbpGD0joUyoVSyMDHUSmSi2LIhlJkIZSC3CHWjkRW53gaCjpzmaO0cNQETrK2Eyi6ttpRAqULoFx7VY0-Hs2Yx0_kCyF1CKAkq9gNKgBe1a8mllQmUa4hwxxI1i0YKTWtKL5t9H2_tb931YZW6xfApuGxrj0cQewIqZjgfl6NCr1gff1sfU
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1PS8MwFA8yBb04_-J0ag_eNFDTtEmPoo6pc4hO2S0kaQYDace6Dbz5HfyGfhJfsnZT0YOek6bhl7z83kveH4SOgIEIVVRiFTONKTEES5LEuOcnYcxjyfxpoHCLtdu8243viqCwvPR2L58k3Uk9C3azN5hg-pIQ2_LoHIOhvkiBsWzG_PuHp0_RkK4QJ9gt1qeHBkWozM9jfKWjuY757VnUsU2j-r95rqHVQrv0zqbbYR0tmHQDVcvKDV4hyJvo4jrrpyPPRv2m5vn99S23jtXwpb3rzQYvniuQA3_1QKf1jEszAU3epJ-PoZfOLONtocfGZee8iYt6ClifglhiSqUyLNIKOBtE2ZBQM6KIjggjiYpAM2JSB0pGTPNAxaEOI0P8iCcs4D5XLNhGlTRLzQ7yQNFTFMSdwg4ARutJphMDq204Y9KXqoaOS1jFYJo2Q8wSJDuABAAkHEDCr6F6ibwoRCgXAcwRTNwwYjV0UiI9b_59tN2_dT9Ey83ObUu0rto3e2iF2IVz7rh1VBkNx2YfLenJqJ8PD9w2-wBH48q4
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dS8MwEA-iIr44P3E6tQ--aVhN0yZ9FOfwY4yBH-ytJGkGA2nH2g1883_wP_Qv8ZK22xR9EJ-ThnC56-8uud8dQqeAQIRKKrAMmcKUaIIFiUM8cGM_5KFgbkEU7rBul_f7YW-BxW-z3asnyYLTYKo0JXlzFA-aM-Kbuc2EMJj42LRK5xiC9hVqEulNvP7wvMCMtE05IYYx-T3UK2kzP6_xFZrm_ua3J1KLPO3a__e8iTZKr9O5LNRkCy3pZBvVqo4OTmngO6h1lw6T3DFs4ES_fLy9ZybhGr40d8Dp6NWxjXNgBw74uo625SdgyJkOswnMUqlBwl301L5-vLrBZZ8FrC7AXDGlQmoWKAlYDiauia8YkUQFhJFYBuAxMaE8KQKmuCdDX_mBJm7AY-Zxl0vm7aHlJE30PnLAAZQUfgMUNAOQbiCYijVogeaMCVfIOjqrRByNinIa0axwshVQBAKKrIAit44a1SlEpWllkQd7hNDXD1gdnVdSnw__vtrB36afoLVeqx11brv3h2idmHOzWboNtJyPJ_oIrappPszGx1bjPgFxSdOc
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=Joint+channel%E2%80%93spatial+entropy+modeling+for+efficient+visual+coding&rft.jtitle=Neural+computing+%26+applications&rft.au=Li%2C+Yuan&rft.au=Jiang%2C+Xiaotong&rft.au=Sun%2C+Zitang&rft.date=2025-07-01&rft.pub=Springer+London&rft.issn=0941-0643&rft.eissn=1433-3058&rft.volume=37&rft.issue=21&rft.spage=17111&rft.epage=17128&rft_id=info:doi/10.1007%2Fs00521-025-11138-0&rft.externalDocID=10_1007_s00521_025_11138_0
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0941-0643&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0941-0643&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0941-0643&client=summon