Wireless Image Retrieval at the Edge

We study the image retrieval problem at the wireless edge, where an edge device captures an image, which is then used to retrieve similar images from an edge server. These can be images of the same person or a vehicle taken from other cameras at different times and locations. Our goal is to maximize...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE journal on selected areas in communications Ročník 39; číslo 1; s. 89 - 100
Hlavní autoři:	Jankowski, Mikolaj, Gunduz, Deniz, Mikolajczyk, Krystian
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.01.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Ablation Artificial neural networks Bandwidths Deep learning Feature extraction Image coding Image compression Image edge detection Image management Image quality Image retrieval Image transmission Internet of Things joint source-channel coding Performance evaluation person re-identification Servers Task analysis Wireless communication
ISSN:	0733-8716, 1558-0008
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	We study the image retrieval problem at the wireless edge, where an edge device captures an image, which is then used to retrieve similar images from an edge server. These can be images of the same person or a vehicle taken from other cameras at different times and locations. Our goal is to maximize the accuracy of the retrieval task under power and bandwidth constraints over the wireless link. Due to the stringent delay constraint of the underlying application, sending the whole image at a sufficient quality is not possible. We propose two alternative schemes based on digital and analog communications, respectively. In the digital approach, we first propose a deep neural network (DNN) aided retrieval-oriented image compression scheme, whose output bit sequence is transmitted over the channel using conventional channel codes. In the analog joint source and channel coding (JSCC) approach, the feature vectors are directly mapped into channel symbols. We evaluate both schemes on image based re-identification (re-ID) tasks under different channel conditions, including both static and fading channels. We show that the JSCC scheme significantly increases the end-to-end accuracy, speeds up the encoding process, and provides graceful degradation with channel conditions. The proposed architecture is evaluated through extensive simulations on different datasets and channel conditions, as well as through ablation studies.
AbstractList	We study the image retrieval problem at the wireless edge, where an edge device captures an image, which is then used to retrieve similar images from an edge server. These can be images of the same person or a vehicle taken from other cameras at different times and locations. Our goal is to maximize the accuracy of the retrieval task under power and bandwidth constraints over the wireless link. Due to the stringent delay constraint of the underlying application, sending the whole image at a sufficient quality is not possible. We propose two alternative schemes based on digital and analog communications, respectively. In the digital approach, we first propose a deep neural network (DNN) aided retrieval-oriented image compression scheme, whose output bit sequence is transmitted over the channel using conventional channel codes. In the analog joint source and channel coding (JSCC) approach, the feature vectors are directly mapped into channel symbols. We evaluate both schemes on image based re-identification (re-ID) tasks under different channel conditions, including both static and fading channels. We show that the JSCC scheme significantly increases the end-to-end accuracy, speeds up the encoding process, and provides graceful degradation with channel conditions. The proposed architecture is evaluated through extensive simulations on different datasets and channel conditions, as well as through ablation studies.
Author	Gunduz, Deniz Mikolajczyk, Krystian Jankowski, Mikolaj
Author_xml	– sequence: 1 givenname: Mikolaj surname: Jankowski fullname: Jankowski, Mikolaj email: gunduz@imperial.ac.uk organization: Department of Electrical and Electronic Engineering, Imperial College London, London, U.K – sequence: 2 givenname: Deniz orcidid: 0000-0002-7725-395X surname: Gunduz fullname: Gunduz, Deniz organization: Department of Electrical and Electronic Engineering, Imperial College London, London, U.K – sequence: 3 givenname: Krystian surname: Mikolajczyk fullname: Mikolajczyk, Krystian organization: Department of Electrical and Electronic Engineering, Imperial College London, London, U.K
BookMark	eNp9kE1LAzEQQINUsK3-APGyoNetk-_NsZSqlYLgBx5DNp3WLdvdmqSC_94tLR48eJo5vDcDb0B6TdsgIZcURpSCuX18GU9GDBiMOHBlpDwhfSplkQNA0SN90JznhabqjAxiXANQIQrWJzfvVcAaY8xmG7fC7BlTqPDL1ZlLWfrAbLpY4Tk5Xbo64sVxDsnb3fR18pDPn-5nk_E895yrlJeOOy3Rc-ROeqOkLDU3XkqpSmEUMMEMFiAMCu-dXmhVCFl6qRVCtzg-JNeHu9vQfu4wJrtud6HpXlomNCiuioJ1lD5QPrQxBlxaXyWXqrZJwVW1pWD3Sew-id0nsccknUn_mNtQbVz4_te5OjgVIv7yhilKleE_E89rXg
CODEN	ISACEM
CitedBy_id	crossref_primary_10_1109_JSAC_2021_3087248 crossref_primary_10_1109_LWC_2021_3136045 crossref_primary_10_1109_TWC_2024_3369170 crossref_primary_10_1109_TWC_2024_3518399 crossref_primary_10_1109_TCCN_2025_3528891 crossref_primary_10_1109_JSAC_2021_3087240 crossref_primary_10_1109_TWC_2024_3371775 crossref_primary_10_1109_TWC_2024_3461336 crossref_primary_10_1109_TWC_2023_3240969 crossref_primary_10_1109_TCCN_2023_3326302 crossref_primary_10_1007_s11432_022_3652_2 crossref_primary_10_1109_TCOMM_2025_3535903 crossref_primary_10_1016_j_jfranklin_2025_107886 crossref_primary_10_1109_JIOT_2024_3456569 crossref_primary_10_1109_JIOT_2024_3450902 crossref_primary_10_1109_JSAC_2022_3180802 crossref_primary_10_1109_JSAC_2021_3118346 crossref_primary_10_1109_JSAC_2025_3559121 crossref_primary_10_1109_JSAC_2021_3126087 crossref_primary_10_1109_TMC_2023_3257268 crossref_primary_10_1109_TWC_2024_3427675 crossref_primary_10_1109_TGCN_2023_3275199 crossref_primary_10_1007_s11036_023_02267_8 crossref_primary_10_1109_TWC_2024_3397635 crossref_primary_10_1109_JIOT_2025_3555437 crossref_primary_10_1109_JSAC_2025_3559116 crossref_primary_10_1007_s11432_024_4408_1 crossref_primary_10_1109_ACCESS_2024_3516814 crossref_primary_10_1109_TCOMM_2025_3529221 crossref_primary_10_1016_j_future_2022_10_036 crossref_primary_10_1109_TWC_2024_3386807 crossref_primary_10_1016_j_phycom_2024_102582 crossref_primary_10_1109_TWC_2023_3334225 crossref_primary_10_1109_TWC_2023_3339239 crossref_primary_10_1109_COMST_2023_3333342 crossref_primary_10_1109_TWC_2023_3312115 crossref_primary_10_3390_electronics11101567 crossref_primary_10_1109_JSAC_2021_3126076 crossref_primary_10_1109_LWC_2023_3256006 crossref_primary_10_1109_LSP_2023_3265330 crossref_primary_10_1109_JPROC_2022_3190205 crossref_primary_10_3390_electronics11091358 crossref_primary_10_1109_TWC_2023_3306465 crossref_primary_10_1109_JIOT_2024_3429391 crossref_primary_10_1109_TCOMM_2021_3128423 crossref_primary_10_1109_JSAC_2022_3191326 crossref_primary_10_1109_TVT_2024_3396426 crossref_primary_10_1109_TWC_2023_3314888 crossref_primary_10_1109_OJCOMS_2025_3586462 crossref_primary_10_1109_COMST_2024_3416309 crossref_primary_10_1109_JSAC_2023_3242701 crossref_primary_10_3390_e27080813 crossref_primary_10_1109_JSTSP_2024_3405853 crossref_primary_10_1109_LCOMM_2024_3436816 crossref_primary_10_1109_TSP_2024_3411692 crossref_primary_10_1109_TWC_2022_3221778 crossref_primary_10_1109_TWC_2021_3090048 crossref_primary_10_1109_TCSVT_2025_3539226 crossref_primary_10_1109_TWC_2024_3450697 crossref_primary_10_1109_MNET_2023_3321547 crossref_primary_10_1109_TVT_2024_3390213 crossref_primary_10_1109_JSAC_2025_3574605 crossref_primary_10_1186_s13634_022_00958_0 crossref_primary_10_1016_j_fmre_2023_08_002 crossref_primary_10_1109_JSAC_2023_3310089 crossref_primary_10_1109_JIOT_2024_3350656 crossref_primary_10_3390_jmse11122280 crossref_primary_10_1109_JSAC_2023_3288236 crossref_primary_10_1016_j_icte_2022_09_002 crossref_primary_10_1016_j_comnet_2025_111531 crossref_primary_10_1016_j_iot_2024_101383 crossref_primary_10_1109_TCCN_2024_3375496 crossref_primary_10_1109_JIOT_2025_3582442 crossref_primary_10_1109_TCOMM_2024_3487513 crossref_primary_10_1109_JSTSP_2023_3310654 crossref_primary_10_1109_JSTSP_2023_3239189 crossref_primary_10_1109_JSAC_2025_3559160 crossref_primary_10_1109_MCOM_001_2200962 crossref_primary_10_1109_TWC_2022_3191118 crossref_primary_10_1109_JSAC_2023_3288243 crossref_primary_10_1109_JSAC_2023_3288246 crossref_primary_10_1109_TWC_2023_3349330 crossref_primary_10_1109_TCOMM_2024_3364990 crossref_primary_10_1109_JIOT_2023_3347234 crossref_primary_10_1038_s41598_025_86860_9 crossref_primary_10_3390_app15094608 crossref_primary_10_1109_JSAC_2022_3223408 crossref_primary_10_1109_TWC_2025_3534995 crossref_primary_10_1109_TWC_2024_3497167 crossref_primary_10_1109_JSTSP_2023_3300509 crossref_primary_10_1109_TWC_2024_3388329 crossref_primary_10_1109_LWC_2022_3204837 crossref_primary_10_1007_s11432_024_4465_3 crossref_primary_10_1109_TCCN_2024_3392803 crossref_primary_10_1016_j_jfranklin_2024_106739 crossref_primary_10_1109_JSAC_2023_3288252 crossref_primary_10_1109_JSAC_2025_3536557 crossref_primary_10_1109_JSAC_2022_3221977 crossref_primary_10_1109_JIOT_2024_3440313 crossref_primary_10_1109_JSYST_2022_3198711 crossref_primary_10_1109_MCOM_004_2200819 crossref_primary_10_1109_ACCESS_2023_3238795 crossref_primary_10_1109_TCCN_2023_3346481 crossref_primary_10_1109_TWC_2024_3386052 crossref_primary_10_1109_JIOT_2025_3531910 crossref_primary_10_1109_MIE_2022_3174331 crossref_primary_10_1109_TWC_2023_3265201 crossref_primary_10_1109_LWC_2025_3527145 crossref_primary_10_3390_app12094534 crossref_primary_10_1109_JIOT_2024_3388260 crossref_primary_10_1109_JIOT_2023_3305011 crossref_primary_10_1109_LCOMM_2024_3450598 crossref_primary_10_1016_j_icte_2022_04_001 crossref_primary_10_1109_JSAC_2025_3560359 crossref_primary_10_1109_TCCN_2024_3510586 crossref_primary_10_1109_MBITS_2023_3322667
Cites_doi	10.1109/ICASSP40776.2020.9054634 10.1109/JSAIT.2020.2987203 10.1109/TWC.2020.2974748 10.1109/TCCN.2019.2919300 10.1609/aaai.v33i01.33018295 10.1002/j.1538-7305.1948.tb01338.x 10.1109/ISLPED.2019.8824955 10.1109/ICCV.2019.00844 10.1109/18.720541 10.1109/ICCWorkshops49005.2020.9145068 10.1109/ACCESS.2019.2920929 10.1109/IJCNN.2019.8852059 10.1109/CVPR.2018.00679 10.1109/CVPR.2016.90 10.1109/TCOMM.2019.2944169 10.1109/CVPR.2014.27 10.1109/CVPR42600.2020.00667 10.1007/s11263-015-0816-y 10.1109/TIP.2019.2910414 10.1109/ICASSP.2018.8461983 10.1109/CVPR.2019.00412 10.1109/SPAWC.2019.8815416 10.1109/SPAWC48557.2020.9154306 10.1016/B978-012119792-6/50124-8 10.1109/TMM.2017.2751966 10.1109/VETEC.1995.504941 10.1109/ICCV.2015.133 10.1109/ISIT.2019.8849334 10.1109/JSAC.2019.2933969 10.1109/TIT.2019.2953750 10.1117/12.258246 10.1109/CVPR.2018.00225 10.1145/3240508.3240552 10.1109/JPROC.2019.2941458
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/JSAC.2020.3036955
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
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	1558-0008
EndPage	100
ExternalDocumentID	10_1109_JSAC_2020_3036955 9261169
Genre	orig-research
GrantInformation_xml	– fundername: European Research Council (ERC) through Starting Grant BEACON grantid: 677854 funderid: 10.13039/501100000781 – fundername: U.K. Engineering and Physical Sciences Research Council (EPSRC) grantid: EP/N007743/1; EP/S032398/1; EP/T023600/1 funderid: 10.13039/501100000266
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 41~ 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IBMZZ ICLAB IES IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 VH1 AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c336t-ba3a75ec3e3a5c9655b739c5556b49602429e8049e4cca7d76845bc576e045ba3
IEDL.DBID	RIE
ISICitedReferencesCount	186
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000599495400008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0733-8716
IngestDate	Mon Jun 30 10:24:12 EDT 2025 Tue Nov 18 20:55:38 EST 2025 Sat Nov 29 03:23:03 EST 2025 Wed Aug 27 02:33:27 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c336t-ba3a75ec3e3a5c9655b739c5556b49602429e8049e4cca7d76845bc576e045ba3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-7725-395X
OpenAccessLink	http://hdl.handle.net/11380/1247347
PQID	2470636882
PQPubID	85481
PageCount	12
ParticipantIDs	crossref_citationtrail_10_1109_JSAC_2020_3036955 crossref_primary_10_1109_JSAC_2020_3036955 ieee_primary_9261169 proquest_journals_2470636882
PublicationCentury	2000
PublicationDate	2021-Jan. 2021-1-00 20210101
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– month: 01 year: 2021 text: 2021-Jan.
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE journal on selected areas in communications
PublicationTitleAbbrev	J-SAC
PublicationYear	2021
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	ref35 ref34 ref12 ref15 minnen (ref37) 2018 ref36 ref14 jankowski (ref1) 2020 ref31 li (ref13) 2018 hermans (ref25) 2017 ref33 ref11 ref32 ref2 ref39 ref17 ref38 ref19 ref18 liu (ref41) 2016 rumelhart (ref30) 1987 shi (ref10) 2019 zhai (ref27) 2005 ref24 ref23 ref26 ref20 ref42 ref22 ref21 gündüz (ref5) 2019; 37 ref28 ref29 ref8 zheng (ref16) 2016 ref7 gallager (ref43) 1968 ref9 ref4 ref3 ref6 ref40
References_xml	– start-page: 10771 year: 2018 ident: ref37 article-title: Joint autoregressive and hierarchical priors for learned image compression publication-title: Advances in Neural IInformation Processing Systems – ident: ref9 doi: 10.1109/ICASSP40776.2020.9054634 – ident: ref3 doi: 10.1109/JSAIT.2020.2987203 – ident: ref8 doi: 10.1109/TWC.2020.2974748 – ident: ref2 doi: 10.1109/TCCN.2019.2919300 – start-page: 5070 year: 2020 ident: ref1 article-title: Deep joint source-channel coding for wireless image retrieval publication-title: Proc ICASSP-IEEE Int Conf Acoust Speech Signal Process (ICASSP) – start-page: 1 year: 2019 ident: ref10 article-title: Improving device-edge cooperative inference of deep learning via 2-step pruning publication-title: Proc IEEE INFOCOM-IEEE Conf Comput Commun Workshops (INFOCOM WKSHPS) – ident: ref21 doi: 10.1609/aaai.v33i01.33018295 – ident: ref26 doi: 10.1002/j.1538-7305.1948.tb01338.x – ident: ref11 doi: 10.1109/ISLPED.2019.8824955 – ident: ref20 doi: 10.1109/ICCV.2019.00844 – ident: ref36 doi: 10.1109/18.720541 – ident: ref12 doi: 10.1109/ICCWorkshops49005.2020.9145068 – ident: ref14 doi: 10.1109/ACCESS.2019.2920929 – ident: ref19 doi: 10.1109/IJCNN.2019.8852059 – ident: ref22 doi: 10.1109/CVPR.2018.00679 – ident: ref34 doi: 10.1109/CVPR.2016.90 – ident: ref4 doi: 10.1109/TCOMM.2019.2944169 – ident: ref39 doi: 10.1109/CVPR.2014.27 – year: 1968 ident: ref43 publication-title: Information Theory and Reliable Communication – ident: ref38 doi: 10.1109/CVPR42600.2020.00667 – ident: ref35 doi: 10.1007/s11263-015-0816-y – ident: ref18 doi: 10.1109/TIP.2019.2910414 – ident: ref31 doi: 10.1109/ICASSP.2018.8461983 – ident: ref17 doi: 10.1109/CVPR.2019.00412 – ident: ref32 doi: 10.1109/SPAWC.2019.8815416 – ident: ref15 doi: 10.1109/SPAWC48557.2020.9154306 – year: 2017 ident: ref25 article-title: In defense of the triplet loss for person re-identification publication-title: arXiv 1703 07737 – start-page: 318 year: 1987 ident: ref30 publication-title: Learning Internal Representations by Error Propagation – year: 2005 ident: ref27 article-title: Joint source-channel coding for video communications publication-title: Handbook of Image and Video Processing doi: 10.1016/B978-012119792-6/50124-8 – ident: ref42 doi: 10.1109/TMM.2017.2751966 – year: 2016 ident: ref16 article-title: Person re-identification: Past, present and future publication-title: arXiv 1610 02984 – ident: ref29 doi: 10.1109/VETEC.1995.504941 – ident: ref40 doi: 10.1109/ICCV.2015.133 – ident: ref7 doi: 10.1109/ISIT.2019.8849334 – volume: 37 start-page: 2184 year: 2019 ident: ref5 article-title: Machine learning in the air publication-title: IEEE J Sel Areas Commun doi: 10.1109/JSAC.2019.2933969 – ident: ref33 doi: 10.1109/TIT.2019.2953750 – start-page: 869 year: 2016 ident: ref41 article-title: A deep learning-based approach to progressive vehicle re-identification for urban surveillance publication-title: Vision Computer – start-page: 671 year: 2018 ident: ref13 article-title: JALAD: Joint accuracy-and latency-aware deep structure decoupling for edge-cloud execution publication-title: Proc IEEE 24th Int Conf Parallel Distrib Syst (ICPADS) – ident: ref28 doi: 10.1117/12.258246 – ident: ref24 doi: 10.1109/CVPR.2018.00225 – ident: ref23 doi: 10.1145/3240508.3240552 – ident: ref6 doi: 10.1109/JPROC.2019.2941458
SSID	ssj0014482
Score	2.7024684
Snippet	We study the image retrieval problem at the wireless edge, where an edge device captures an image, which is then used to retrieve similar images from an edge...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	89
SubjectTerms	Ablation Artificial neural networks Bandwidths Deep learning Feature extraction Image coding Image compression Image edge detection Image management Image quality Image retrieval Image transmission Internet of Things joint source-channel coding Performance evaluation person re-identification Servers Task analysis Wireless communication
Title	Wireless Image Retrieval at the Edge
URI	https://ieeexplore.ieee.org/document/9261169 https://www.proquest.com/docview/2470636882
Volume	39
WOSCitedRecordID	wos000599495400008&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: 1558-0008 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014482 issn: 0733-8716 databaseCode: RIE dateStart: 19830101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEB3a4kEPflWxWmUPPYlrdzebZHMspUVFivhFb0s2nYpQW2m3_n4n6XYpKIK3PSSwvCQz72UmMwAtlpDbC0bMDzSiH2Og_UQY42eayLUOw0y4ZMzXezkYJMOheqjAVfkWBhFd8hle208Xyx_NzNJelbUV0f1QqCpUpRSrt1plxIBkhosYSMZ8KwKKCGYYqPbdU6dLSjAigUr2WtlXfRs-yDVV-WGJnXvp7_3vx_Zht6CRXme17gdQwekh7GwUF6xDyya2TsiQebcfZDS8R9c7izaWp3OPaJ_XG73hEbz0e8_dG7_oieAbxkROGDItORqGTHOjBOeZZMpwzkUWkxohj6swIdqPMa2NHNk4G88MqQok8kazj6E2nU3xBDwkHc0jK0jCsUUvCbUWY66V7UJtRNaAYI1SaoqC4bZvxSR1wiFQqQU2tcCmBbANuCynfK6qZfw1uG6RLAcWIDaguV6KtDhPizSKJXEpQXLg9PdZZ7Ad2WwTdznShFo-X-I5bJmv_H0xv3Bb5RsjHrfO
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEJ0gmqgHv9CIou6Bk3Fld7vtbo-EQECRGEXDbdMtgzFBMHz4-52WhZBoTLztoU02r-3Me53pDECZxeT2vD5zPYXohugpNxZau6kicq18PxU2GfO1HXU6ca8nH3Nws3oLg4g2-QxvzaeN5ffHem6uyiqS6L4v5AZs8jAMvMVrrVXMgISGjRlEjLlGBmQxTN-Tlbvnao20YEASlSy2NO_61ryQbavywxZbB9PY_9-vHcBeRiSd6mLlDyGHoyPYXSsvWICySW0dkilzWh9kNpwn2z2LtpajZg4RP6fef8NjeGnUu7Wmm3VFcDVjYkYoMhVx1AyZ4loKztOISc05F2lIeoR8rsSYiD-GtDpR30TaeKpJVyDRN5p9AvnReISn4CApaR4YSeIPDHqxr5QYcCVNH2ot0iJ4S5QSnZUMN50rhomVDp5MDLCJATbJgC3C9WrK56Jexl-DCwbJ1cAMxCKUlkuRZCdqmgRhRGxKkCA4-33WFWw3uw_tpN3q3J_DTmByT-xVSQnys8kcL2BLf83ep5NLu22-AeVwuxU
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=Wireless+Image+Retrieval+at+the+Edge&rft.jtitle=IEEE+journal+on+selected+areas+in+communications&rft.au=Jankowski%2C+Mikolaj&rft.au=Gunduz%2C+Deniz&rft.au=Mikolajczyk%2C+Krystian&rft.date=2021-01-01&rft.issn=0733-8716&rft.eissn=1558-0008&rft.volume=39&rft.issue=1&rft.spage=89&rft.epage=100&rft_id=info:doi/10.1109%2FJSAC.2020.3036955&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSAC_2020_3036955
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0733-8716&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0733-8716&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0733-8716&client=summon