Serial Decoders-Based Auto-Encoders for Image Reconstruction
Auto-encoders are composed of coding and decoding units; hence, they hold an inherent potential of being used for high-performance data compression and signal-compressed sensing. The main disadvantages of current auto-encoders comprise the following aspects: the research objective is not to achieve...
Uloženo v:
| Vydáno v: | Applied sciences Ročník 12; číslo 16; s. 8256 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Basel
MDPI AG
01.08.2022
Multidisciplinary digital publishing institute (MDPI) |
| Témata: | |
| ISSN: | 2076-3417, 2076-3417 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Auto-encoders are composed of coding and decoding units; hence, they hold an inherent potential of being used for high-performance data compression and signal-compressed sensing. The main disadvantages of current auto-encoders comprise the following aspects: the research objective is not to achieve lossless data reconstruction but efficient feature representation; the evaluation of data recovery performance is neglected; it is difficult to achieve lossless data reconstruction using pure auto-encoders, even with pure deep learning. This paper aims at performing image reconstruction using auto-encoders, employs cascade decoders-based auto-encoders, perfects the performance of image reconstruction, approaches gradually lossless image recovery, and provides a solid theoretical and applicational basis for auto-encoders-based image compression and compressed sensing. The proposed serial decoders-based auto-encoders include the architectures of multi-level decoders and their related progressive optimization sub-problems. The cascade decoders consist of general decoders, residual decoders, adversarial decoders, and their combinations. The effectiveness of residual cascade decoders for image reconstruction is proven in mathematics. Progressive training can efficiently enhance the quality, stability, and variation of image reconstruction. It has been shown by the experimental results that the proposed auto-encoders outperform classical auto-encoders in the performance of image reconstruction. |
|---|---|
| AbstractList | Featured ApplicationThe proposed method can be utilized for highly efficient data compression, signal-compressed sensing, data restoration, etc.AbstractAuto-encoders are composed of coding and decoding units; hence, they hold an inherent potential of being used for high-performance data compression and signal-compressed sensing. The main disadvantages of current auto-encoders comprise the following aspects: the research objective is not to achieve lossless data reconstruction but efficient feature representation; the evaluation of data recovery performance is neglected; it is difficult to achieve lossless data reconstruction using pure auto-encoders, even with pure deep learning. This paper aims at performing image reconstruction using auto-encoders, employs cascade decoders-based auto-encoders, perfects the performance of image reconstruction, approaches gradually lossless image recovery, and provides a solid theoretical and applicational basis for auto-encoders-based image compression and compressed sensing. The proposed serial decoders-based auto-encoders include the architectures of multi-level decoders and their related progressive optimization sub-problems. The cascade decoders consist of general decoders, residual decoders, adversarial decoders, and their combinations. The effectiveness of residual cascade decoders for image reconstruction is proven in mathematics. Progressive training can efficiently enhance the quality, stability, and variation of image reconstruction. It has been shown by the experimental results that the proposed auto-encoders outperform classical auto-encoders in the performance of image reconstruction. Auto-encoders are composed of coding and decoding units; hence, they hold an inherent potential of being used for high-performance data compression and signal-compressed sensing. The main disadvantages of current auto-encoders comprise the following aspects: the research objective is not to achieve lossless data reconstruction but efficient feature representation; the evaluation of data recovery performance is neglected; it is difficult to achieve lossless data reconstruction using pure auto-encoders, even with pure deep learning. This paper aims at performing image reconstruction using auto-encoders, employs cascade decoders-based auto-encoders, perfects the performance of image reconstruction, approaches gradually lossless image recovery, and provides a solid theoretical and applicational basis for auto-encoders-based image compression and compressed sensing. The proposed serial decoders-based auto-encoders include the architectures of multi-level decoders and their related progressive optimization sub-problems. The cascade decoders consist of general decoders, residual decoders, adversarial decoders, and their combinations. The effectiveness of residual cascade decoders for image reconstruction is proven in mathematics. Progressive training can efficiently enhance the quality, stability, and variation of image reconstruction. It has been shown by the experimental results that the proposed auto-encoders outperform classical auto-encoders in the performance of image reconstruction. |
| Author | Trocan, Maria Sawan, Mohamad Galayko, Dimitri Li, Honggui |
| Author_xml | – sequence: 1 givenname: Honggui orcidid: 0000-0002-6294-1581 surname: Li fullname: Li, Honggui – sequence: 2 givenname: Maria surname: Trocan fullname: Trocan, Maria – sequence: 3 givenname: Mohamad surname: Sawan fullname: Sawan, Mohamad – sequence: 4 givenname: Dimitri surname: Galayko fullname: Galayko, Dimitri |
| BackLink | https://hal.science/hal-04031141$$DView record in HAL |
| BookMark | eNptkVtLxDAQhYMoeH3yDxR8EqnONG3Sgi_rfWFB8PIcpkmqXWqzJl3Bf2_WKqg4LzMcvjmcZLbZeu96y9g-wjHnFZzQYoEZijIrxBrbykCKlOco13_Mm2wvhDnEqpCXCFvs9N76lrrkwmpnrA_pGQVrkslycOllP2pJ43wyfaEnm9xFrA-DX-qhdf0u22ioC3bvq--wx6vLh_ObdHZ7PT2fzFLNq3JItYmRMmOFyCuBRIDEbWE5JyAZE9dAmqPMTSMrIlnrCsrGAI8jGBG5HTYdfY2juVr49oX8u3LUqk_B-SdFfmh1Z1WhtakAy1w3RW5FUXMjpDANz2tRS1NFr8PR65m6X1Y3k5laaZADR8zxDSN7MLIL716XNgxq7pa-j09VmQSBILNyReFIae9C8LZRuh1o9T-Dp7ZTCGp1H_XjPnHn6M_Od5T_6A_b6JBX |
| CitedBy_id | crossref_primary_10_1002_dac_6140 crossref_primary_10_3390_rs15245739 crossref_primary_10_3390_app13105922 |
| Cites_doi | 10.1016/j.joes.2018.04.002 10.1109/ICCV.2019.00355 10.1088/2058-9565/aa8072 10.1109/JSEN.2018.2877360 10.1016/j.inffus.2017.10.006 10.1109/LSP.2017.2697970 10.1109/5.726791 10.1016/j.neucom.2017.09.093 10.1088/1741-2552/aae18d 10.1016/j.mri.2018.06.003 10.1109/ACCESS.2018.2830661 10.1109/ISBI48211.2021.9434062 10.1109/TBME.2016.2631620 10.1109/TIP.2018.2817044 10.1109/ICIP.2018.8451841 10.1109/MGRS.2018.2853555 10.1109/TSMC.2016.2637279 10.1016/j.neunet.2018.07.016 10.1109/ICECS.2018.8617908 10.1109/TNNLS.2018.2838679 10.1117/1.JEI.26.5.053016 10.1109/CVPR.2019.01126 10.1016/j.cogsys.2018.07.004 |
| ContentType | Journal Article |
| Copyright | 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Distributed under a Creative Commons Attribution 4.0 International License |
| Copyright_xml | – notice: 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Distributed under a Creative Commons Attribution 4.0 International License |
| DBID | AAYXX CITATION ABUWG AFKRA AZQEC BENPR CCPQU DWQXO PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI PRINS 1XC DOA |
| DOI | 10.3390/app12168256 |
| DatabaseName | CrossRef ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One ProQuest Central Korea Proquest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China Hyper Article en Ligne (HAL) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | Publicly Available Content Database CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Sciences (General) |
| EISSN | 2076-3417 |
| ExternalDocumentID | oai_doaj_org_article_5ccd90184cf54e65b3d676df34b6b7d9 oai:HAL:hal-04031141v1 10_3390_app12168256 |
| GroupedDBID | .4S 2XV 5VS 7XC 8CJ 8FE 8FG 8FH AADQD AAFWJ AAYXX ADBBV ADMLS AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS APEBS ARCSS BCNDV BENPR CCPQU CITATION CZ9 D1I D1J D1K GROUPED_DOAJ IAO IGS ITC K6- K6V KC. KQ8 L6V LK5 LK8 M7R MODMG M~E OK1 P62 PHGZM PHGZT PIMPY PROAC TUS ABUWG AZQEC DWQXO PKEHL PQEST PQQKQ PQUKI PRINS 1XC IPNFZ RIG |
| ID | FETCH-LOGICAL-c398t-cd2562de664961aa01a3e5e33a0a7216b0ac3174df79aa7bc908fd03a7b0d6e33 |
| IEDL.DBID | BENPR |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000846158600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2076-3417 |
| IngestDate | Tue Oct 14 19:07:15 EDT 2025 Tue Oct 14 20:05:29 EDT 2025 Mon Jun 30 11:14:20 EDT 2025 Sat Nov 29 07:18:18 EST 2025 Tue Nov 18 21:08:21 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 16 |
| Language | English |
| License | Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c398t-cd2562de664961aa01a3e5e33a0a7216b0ac3174df79aa7bc908fd03a7b0d6e33 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-6294-1581 0000-0002-7056-7489 |
| OpenAccessLink | https://www.proquest.com/docview/2706107281?pq-origsite=%requestingapplication% |
| PQID | 2706107281 |
| PQPubID | 2032433 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_5ccd90184cf54e65b3d676df34b6b7d9 hal_primary_oai_HAL_hal_04031141v1 proquest_journals_2706107281 crossref_citationtrail_10_3390_app12168256 crossref_primary_10_3390_app12168256 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-08-01 |
| PublicationDateYYYYMMDD | 2022-08-01 |
| PublicationDate_xml | – month: 08 year: 2022 text: 2022-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Basel |
| PublicationPlace_xml | – name: Basel |
| PublicationTitle | Applied sciences |
| PublicationYear | 2022 |
| Publisher | MDPI AG Multidisciplinary digital publishing institute (MDPI) |
| Publisher_xml | – name: MDPI AG – name: Multidisciplinary digital publishing institute (MDPI) |
| References | LeCun (ref_29) 1998; 86 Angshul (ref_16) 2018; 106 Majid (ref_23) 2019; 19 ref_11 ref_10 ref_32 Angshul (ref_21) 2018; 52 ref_31 ref_30 Li (ref_25) 2018; 27 ref_18 ref_15 Cho (ref_24) 2018; 23 Grant (ref_2) 2018; 6 Li (ref_17) 2017; 26 Angshul (ref_6) 2019; 30 Yang (ref_22) 2018; 48 Dong (ref_3) 2018; 6 ref_28 ref_27 ref_26 Anupriya (ref_8) 2017; 64 ref_9 Zhang (ref_1) 2018; 42 Sun (ref_20) 2017; 24 Perera (ref_19) 2018; 3 Jonathan (ref_13) 2017; 2 ref_5 ref_4 Wu (ref_7) 2018; 15 Ozal (ref_12) 2018; 52 Han (ref_14) 2018; 275 |
| References_xml | – ident: ref_28 – volume: 3 start-page: 133 year: 2018 ident: ref_19 article-title: Ship performance and navigation data compression and communication under autoencoder system architecture publication-title: J. Ocean Eng. Sci. doi: 10.1016/j.joes.2018.04.002 – ident: ref_9 – ident: ref_30 – ident: ref_5 – ident: ref_10 doi: 10.1109/ICCV.2019.00355 – volume: 2 start-page: 045001 year: 2017 ident: ref_13 article-title: Quantum autoencoders for efficient compression of quantum data publication-title: Quantum Sci. Technol. doi: 10.1088/2058-9565/aa8072 – ident: ref_11 – volume: 19 start-page: 632 year: 2019 ident: ref_23 article-title: A deep learning-based compression algorithm for 9-DOF inertial measurement unit signals along with an error compensating mechanism publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2018.2877360 – volume: 42 start-page: 146 year: 2018 ident: ref_1 article-title: A survey on deep learning for big data publication-title: Inf. Fusion doi: 10.1016/j.inffus.2017.10.006 – volume: 24 start-page: 863 year: 2017 ident: ref_20 article-title: Efficient compressed sensing for wireless neural recording: A deep learning approach publication-title: IEEE Signal Proc. Lett. doi: 10.1109/LSP.2017.2697970 – volume: 86 start-page: 2278 year: 1998 ident: ref_29 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE doi: 10.1109/5.726791 – volume: 275 start-page: 1500 year: 2018 ident: ref_14 article-title: A sparse autoencoder compressed sensing method for acquiring the pressure array information of clothing publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.09.093 – volume: 15 start-page: 066019 year: 2018 ident: ref_7 article-title: Deep compressive autoencoder for action potential compression in large-scale neural recording publication-title: J. Neural Eng. doi: 10.1088/1741-2552/aae18d – volume: 52 start-page: 62 year: 2018 ident: ref_21 article-title: An autoencoder based formulation for compressed sensing reconstruction publication-title: Magn. Reson. Imaging doi: 10.1016/j.mri.2018.06.003 – volume: 23 start-page: 383 year: 2018 ident: ref_24 article-title: A technical analysis on deep learning based image and video compression publication-title: J. Broadcast Eng. – volume: 6 start-page: 24411 year: 2018 ident: ref_2 article-title: A survey of deep learning: Platforms, applications and emerging research trends publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2830661 – ident: ref_32 doi: 10.1109/ISBI48211.2021.9434062 – volume: 64 start-page: 2196 year: 2017 ident: ref_8 article-title: Semi-supervised stacked label consistent autoencoder for reconstruction and analysis of biomedical signals publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2016.2631620 – volume: 27 start-page: 3236 year: 2018 ident: ref_25 article-title: Fully connected network-based intra prediction for image coding publication-title: IEEE Trans. Image Proc. doi: 10.1109/TIP.2018.2817044 – ident: ref_27 doi: 10.1109/ICIP.2018.8451841 – volume: 6 start-page: 44 year: 2018 ident: ref_3 article-title: A Review of the autoencoder and its variants: A comparative perspective from target recognition in synthetic-aperture radar images publication-title: IEEE Geosci. Remote Sens. Mag. doi: 10.1109/MGRS.2018.2853555 – ident: ref_4 – ident: ref_31 – volume: 48 start-page: 1065 year: 2018 ident: ref_22 article-title: Autoencoder with invertible functions for dimension reduction and image reconstruction publication-title: IEEE Trans. Syst. Man Cybern. Syst. doi: 10.1109/TSMC.2016.2637279 – ident: ref_15 – volume: 106 start-page: 271 year: 2018 ident: ref_16 article-title: Graph structured autoencoder publication-title: Neural Netw. doi: 10.1016/j.neunet.2018.07.016 – ident: ref_18 doi: 10.1109/ICECS.2018.8617908 – volume: 30 start-page: 312 year: 2019 ident: ref_6 article-title: Blind denoising autoencoder publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2018.2838679 – volume: 26 start-page: 053016 year: 2017 ident: ref_17 article-title: Deep linear autoencoder and patch clustering based unified 1D coding of image and video publication-title: J. Electron. Imaging doi: 10.1117/1.JEI.26.5.053016 – ident: ref_26 doi: 10.1109/CVPR.2019.01126 – volume: 52 start-page: 198 year: 2018 ident: ref_12 article-title: An efficient compression of ECG signals using deep convolutional autoencoders publication-title: Cogn. Syst. Res. doi: 10.1016/j.cogsys.2018.07.004 |
| SSID | ssj0000913810 |
| Score | 2.2336085 |
| Snippet | Auto-encoders are composed of coding and decoding units; hence, they hold an inherent potential of being used for high-performance data compression and... Featured ApplicationThe proposed method can be utilized for highly efficient data compression, signal-compressed sensing, data restoration,... |
| SourceID | doaj hal proquest crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database |
| StartPage | 8256 |
| SubjectTerms | adversarial decoders auto-encoders cascade decoders Data compression Deep learning Engineering Sciences general decoders Neural networks residual decoders Sensors serial decoders Video compression |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3dS8MwED9EfNAHcX7gdEqRPagQTJo0acCXTTcmDPFBwbeSJikKOsXN_f1e2m5uIvjiWzmOktw199Hc_Q6grRJjJcsZkdQoIgzXROfWEHR1XHjrNTMlzuxQ3d6mj4_6bmHUV6gJq-CBK8FdJNY69FmpsEUivExy7qSSruAil7lyZeseVXohmSptsGYBuqpqyOOY14f7YBYziQmRXHJBJVI_OpanUAf5wxyXPqa_BZt1cBh1qkU1YMWPtmFjATJwGxr1YRxHpzVi9NkOXFb_uKJrHzrUP8aki77JRZ3PyRvpjSpahNFpdPOK5iMKKec3cOwuPPR791cDUo9FIJbrdEKswz3EzksptGTGUGa4TzznBsWNW8ypsRgVCFcobYzKraZp4SjHR-ok8u3B6uht5PchKpRhHmNCZ6UTvAhYgkIazzzVPsm1a8L5TFKZrTHDw-iKlwxzhyDWbEGsTWjPmd8rqIzf2bpB5HOWgG9dElDrWa317C-tN-EEFbb0jkFnmAUaWiWOSR6bsia0ZvrM6pM5zmKFEQxVccoO_mMhh7Aeh4aIsiSwBauoO38Ea3Y6eR5_HJcf5RfkyOUR priority: 102 providerName: Directory of Open Access Journals |
| Title | Serial Decoders-Based Auto-Encoders for Image Reconstruction |
| URI | https://www.proquest.com/docview/2706107281 https://hal.science/hal-04031141 https://doaj.org/article/5ccd90184cf54e65b3d676df34b6b7d9 |
| Volume | 12 |
| WOSCitedRecordID | wos000846158600001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bSxwxFD5Y7UP7YL1Uut4Yig-tEJpMMskEhLKrKwp2WUoL-jRkkowW6q7ubP39PZnJrhfEF99mksMw5EvOLcl3APZUZqxkJSOSGkWE4Zro0hqCpo4Lb71mpuGZPVODQX5-rocx4VbHY5Uzndgoaje2IUf-LVVoeahKc_b95paEqlFhdzWW0HgDS4GpDOf5Uq8_GP6cZ1kC62XOaHsxj2N8H_aFWcokBkbykSlqGPvRwFyF85BP1HJja44_vPYvV2A5eplJt50Wq7DgR2vw_gH34BqsxlVdJ18i9fTXdThok2XJkQ9X3Sc16aGRc0n333RM-qO2LUE3Nzm9Rj2UhNj1noH2I_w-7v86PCGxvgKxXOdTYh0OQuq8lEJLZgxlhvvMc24QNxyjkhqL7oVwldLGqNJqmleOcnykTqLcBiyOxiP_CZJKGebRuXRWOsGrQEoopPHMU-2zUrsO7M-GurCRfDzUwPhbYBAScCke4NKBvbnwTcu58bxYL2A2FwlE2U3DeHJZxHVXZNY6dHlyYatMeJmV3EklXcVFKUvldAc-I-KPvnHSPStCG6o3jtEiu2Md2J6hXcQlXhf3UG--3L0F79JwZ6I5NbgNi4iK34G39m76p57sxhm72yQD8G14-mN48R_1OPZn |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3faxQxEB7KVVAf1FbF06qLVFAhmGyyyQYUudqWO3o97qFCfYrZJKuC3tXbs-I_5d_oZH9cWxHf-uDbkg1hd_PtfJlJ5huAbZVZJ1nBiKRWEWG5JrpwliDVcRFc0MzWOrNjNZnkx8d6uga_ulyYeKyys4m1ofZzF2PkL1OFzENVmrM3J99IrBoVd1e7EhoNLA7Czx_oslWvR7s4v0_TdH_v6O2QtFUFiOM6XxLnkeVTH6QUWjJrKbM8ZIFzi0-bMllQ65BUhS-VtlYVTtO89JTjJfUyxAAomvx1EcHeg_Xp6HD6fhXViSqbOaNNIiDnmsZ9aIajoiMmL1BfXSEACe1TPH_5Bw3U3LZ_83_7KrfgRruKTgYN7DdgLcw24fo5bcVN2GitVpU8a6W1n9-GV00wMNkNMZV_UZEdJHGfDL4v52Rv1rQluIxPRl_RzibRNz9T2L0D7y7lne5CbzafhXuQlMqygItn76QXvIyii0LawALVISu078OLbmqNa8XVY42PLwadrIgDcw4HfdhedT5pNEX-3m0nYmTVJQqB1w3zxUfT2hWTOedxSZcLV2YiyKzgXirpSy4KWSiv-_AEEXZhjOFgbGIbmm-O3jA7ZX3Y6tBlWhNWmTNo3f_37cdwdXh0ODbj0eTgAVxLY35IfUJyC3o4Q-EhXHGny8_V4lH7tyTw4bKh-Bu6LlFz |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3fb9MwED5NHULwAGyAKBsQoSEBkjU7duxY2oQ6umrVStUHkMZT5tgOmwTt1pQh_jX-Os750W0I8bYH3iLHipL48313Z_s7gC2VGCtZzoikRhFhuCY6t4Yg1XHhrdfMVDqzIzUep0dHerICv9qzMGFbZWsTK0PtZjbkyLdjhcxDVZyy7aLZFjHpD96dnZNQQSqstLblNGqIHPqfPzB8K3eHfRzrV3E82P_4_oA0FQaI5TpdEOuQ8WPnpRRaMmMoM9wnnnODbx4zmVNjkWCFK5Q2RuVW07RwlOMlddKHZCia_1V0yUXcgdXJ8MPk8zLDExQ3U0brQ4GcaxrWpBk-FYMyeY0Gq2oBSG4nYS_mH5RQ8dzg_v_8hx7Avca7jnr1dFiDFT9dh7tXNBfXYa2xZmX0upHcfvMQduokYdT34Yj_vCR7SO4u6n1fzMj-tG6L0L2Pht_Q_kYhZr9U3n0En27kmx5DZzqb-icQFcowj061s9IJXgQxRiGNZ55qn-TadeFtO8yZbUTXQ-2PrxkGXwET2RVMdGFr2fms1hr5e7e9gJdllyAQXjXM5l-yxt5kibUOXb1U2CIRXiY5d1JJV3CRy1w53YWXiLZrzzjojbLQhmadY5TMLlgXNlukZY1pK7NLmD399-0XcBvxl42G48MNuBOHYyPVxslN6OAA-Wdwy14sTsv582biRHB800j8Db1hWjM |
| 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=Serial+Decoders-Based+Auto-Encoders+for+Image+Reconstruction&rft.jtitle=Applied+sciences&rft.au=Li%2C+Honggui&rft.au=Trocan%2C+Maria&rft.au=Sawan%2C+Mohamad&rft.au=Galayko%2C+Dimitri&rft.date=2022-08-01&rft.issn=2076-3417&rft.eissn=2076-3417&rft.volume=12&rft.issue=16&rft.spage=8256&rft_id=info:doi/10.3390%2Fapp12168256&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_app12168256 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2076-3417&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2076-3417&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2076-3417&client=summon |