Capture the Moment: High-speed Imaging with Spiking Cameras through Short-term Plasticity
High-speed imaging can help us understand some phenomena that our eyes cannot capture fast enough. Although ultra-fast frame-based cameras (e.g., Phantom) can record millions of fps at reduced resolution, are too expensive to be widely used. Recently, a retina-inspired vision sensor, spiking camera,...
Saved in:
Published in | IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 7; pp. 1 - 16 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
United States
IEEE
01.07.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | High-speed imaging can help us understand some phenomena that our eyes cannot capture fast enough. Although ultra-fast frame-based cameras (e.g., Phantom) can record millions of fps at reduced resolution, are too expensive to be widely used. Recently, a retina-inspired vision sensor, spiking camera, has been developed to record external information at 40, 000 Hz. The spiking camera uses the asynchronous binary spike streams to represent visual information. Despite this, how to reconstruct dynamic scenes from asynchronous spikes remains challenging. In this paper, we introduce novel high-speed image reconstruction models based on the short-term plasticity (STP) mechanism of the brain, termed TFSTP and TFMDSTP. We first derive the relationship between states of STP and spike patterns. Then, in TFSTP, by setting up the STP model at each pixel, the scene radiance can be inferred by the states of the models. In TFMDSTP, we use the STP to distinguish the moving and stationary regions, and then use two sets of STP models to reconstruct them respectively. In addition, we present a strategy for correcting error spikes. Experimental results show that the STP-based reconstruction methods can effectively reduce noise with less computing time, and achieve best the performances on both real-world and simulated datasets. |
---|---|
AbstractList | High-speed imaging can help us understand some phenomena that are too fast to be captured by our eyes. Although ultra-fast frame-based cameras (e.g., Phantom) can record millions of fps at reduced resolution, they are too expensive to be widely used. Recently, a retina-inspired vision sensor, spiking camera, has been developed to record external information at 40, 000 Hz. The spiking camera uses the asynchronous binary spike streams to represent visual information. Despite this, how to reconstruct dynamic scenes from asynchronous spikes remains challenging. In this paper, we introduce novel high-speed image reconstruction models based on the short-term plasticity (STP) mechanism of the brain, termed TFSTP and TFMDSTP. We first derive the relationship between states of STP and spike patterns. Then, in TFSTP, by setting up the STP model at each pixel, the scene radiance can be inferred by the states of the models. In TFMDSTP, we use the STP to distinguish the moving and stationary regions, and then use two sets of STP models to reconstruct them respectively. In addition, we present a strategy for correcting error spikes. Experimental results show that the STP-based reconstruction methods can effectively reduce noise with less computing time, and achieve the best performances on both real-world and simulated datasets. High-speed imaging can help us understand some phenomena that our eyes cannot capture fast enough. Although ultra-fast frame-based cameras (e.g., Phantom) can record millions of fps at reduced resolution, are too expensive to be widely used. Recently, a retina-inspired vision sensor, spiking camera, has been developed to record external information at 40, 000 Hz. The spiking camera uses the asynchronous binary spike streams to represent visual information. Despite this, how to reconstruct dynamic scenes from asynchronous spikes remains challenging. In this paper, we introduce novel high-speed image reconstruction models based on the short-term plasticity (STP) mechanism of the brain, termed TFSTP and TFMDSTP. We first derive the relationship between states of STP and spike patterns. Then, in TFSTP, by setting up the STP model at each pixel, the scene radiance can be inferred by the states of the models. In TFMDSTP, we use the STP to distinguish the moving and stationary regions, and then use two sets of STP models to reconstruct them respectively. In addition, we present a strategy for correcting error spikes. Experimental results show that the STP-based reconstruction methods can effectively reduce noise with less computing time, and achieve best the performances on both real-world and simulated datasets. |
Author | Yu, Zhaofei Wang, Song Zheng, Yajing Zheng, Lingxiao Huang, Tiejun |
Author_xml | – sequence: 1 givenname: Yajing orcidid: 0000-0002-6355-7354 surname: Zheng fullname: Zheng, Yajing organization: National Engineering Laboratory for Video Technology, School of Computer Science, Peking University, Beijing, China – sequence: 2 givenname: Lingxiao surname: Zheng fullname: Zheng, Lingxiao organization: National Engineering Laboratory for Video Technology, School of Computer Science, Peking University, Beijing, China – sequence: 3 givenname: Zhaofei orcidid: 0000-0002-6913-7553 surname: Yu fullname: Yu, Zhaofei organization: Institute for Artificial Intelligence, Peking University, Beijing, China – sequence: 4 givenname: Tiejun orcidid: 0000-0002-4234-6099 surname: Huang fullname: Huang, Tiejun organization: National Engineering Laboratory for Video Technology, School of Computer Science, Peking University, Beijing, China – sequence: 5 givenname: Song orcidid: 0000-0003-4152-5295 surname: Wang fullname: Wang, Song organization: Department of Computer Science and Engineering, University of South Carolina, SC, USA |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37021865$$D View this record in MEDLINE/PubMed |
BookMark | eNpdkMtKxDAUhoMoOl5eQEQKbtx0zLVN3MngZUBRUBeuQtqczkSnF5MU8e3tOKOIq8M5fP_P4dtFm03bAEKHBI8Jwers6eHibjqmmLIxoyyXIttAI6KYSplgahONMMloKiWVO2g3hFeMCReYbaMdlmNKZCZG6GViuth7SOIckru2hiaeJzduNk9DB2CTaW1mrpklHy7Ok8fOvS2XianBmzBkfNvPhvu89TGN4OvkYWFCdKWLn_toqzKLAAfruYeery6fJjfp7f31dHJxm5ZM0JhaXgpuikJxWwK2IuOVoMwKIpjhhbJMVhQsiKrAlgLHoMAqWfGSK0OF4GwPna56O9--9xCirl0oYbEwDbR90DRXOeE8l0v05B_62va-Gb7TVFJGJM4IGyi6okrfhuCh0p13tfGfmmC9FK-_xeuleL0WP4SO19V9UYP9jfyYHoCjFeAA4E8jJkoozr4APWyJDQ |
CODEN | ITPIDJ |
CitedBy_id | crossref_primary_10_1109_TCSVT_2023_3272375 |
Cites_doi | 10.1523/JNEUROSCI.22-02-00584.2002 10.1126/science.288.5469.1189 10.1109/CVPR.2019.00398 10.1145/3386569.3392470 10.1109/CVPR46437.2021.01182 10.1109/CVPR.2019.00953 10.1038/nature01248 10.1109/CVPR.2019.00698 10.1016/j.neuron.2012.10.002 10.1109/ICME.2019.00248 10.1109/TPAMI.2019.2903179 10.1109/CVPR42600.2020.00174 10.1109/LSP.2012.2227726 10.1038/nature03010 10.1109/TPAMI.2019.2963386 10.1109/CVPR.2019.01032 10.1073/pnas.94.2.719 10.1109/ISCAS.2008.4541871 10.1109/TPAMI.2019.2946567 10.1109/CVPR42600.2020.00168 10.1109/DCC.2019.00080 10.1109/CVPR42600.2020.00180 10.1038/nrn1497 10.1109/DCC.2017.69 10.1109/JSSC.2014.2342715 10.1126/science.275.5297.221 10.1109/CVPR46437.2021.00629 10.1109/NCC.2015.7084843 10.1016/S0893-6080(97)00011-7 10.1063/1.1146268 10.5220/0008934700370047 10.1103/PhysRevE.85.016108 10.1162/089976698300017502 10.1117/1.JEI.28.6.063012 10.1109/ISCAS.2014.6865228 10.1109/CVPR.2018.00407 10.1109/7.805442 10.1109/JSSC.2007.914337 10.1109/ISCAS45731.2020.9181055 10.1109/LSP.2010.2043888 10.1109/TIP.2012.2214050 10.1109/CVPR42600.2020.00834 10.1007/s00371-017-1372-y 10.1152/jn.00806.2011 10.1109/TPAMI.2020.2986944 10.1109/TPAMI.2013.129 10.1109/CVPR42600.2020.00151 10.1007/978-3-030-01267-0_11 10.1109/ICCVW.2019.00532 10.1109/ICCV.2017.89 10.1103/PhysRevLett.88.173903 10.3389/fncom.2013.00075 10.1007/s11263-020-01410-2 10.15607/RSS.2018.XIV.062 10.1109/ISCAS.2017.8050397 10.1109/ISCAS.2010.5537149 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
DBID | 97E RIA RIE NPM AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
DOI | 10.1109/TPAMI.2023.3237856 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library Online PubMed 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 MEDLINE - Academic |
DatabaseTitle | PubMed 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 MEDLINE - Academic |
DatabaseTitleList | Technology Research Database PubMed |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library Online url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Computer Science |
EISSN | 1939-3539 2160-9292 |
EndPage | 16 |
ExternalDocumentID | 10_1109_TPAMI_2023_3237856 37021865 10019594 |
Genre | orig-research Journal Article |
GrantInformation_xml | – fundername: China Postdoctoral Science Foundation – fundername: National Natural Science Foundation of China grantid: 62176003; 62088102; U1803264; 2022M720238 |
GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AASAJ ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AKJIK ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIC RIE RIG RNS RXW TAE TN5 UHB ~02 5VS 9M8 AAYOK ABFSI ADRHT AETIX AI. AIBXA ALLEH F20 FA8 H~9 IBMZZ ICLAB IFJZH NPM RNI RZB VH1 XJT AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
ID | FETCH-LOGICAL-c352t-d4c54abb94dce0d564f523d5153a4b9d38f2ede5fb0d2e40e9ed98f4c49a25543 |
IEDL.DBID | RIE |
ISSN | 0162-8828 |
IngestDate | Thu Jul 25 08:15:39 EDT 2024 Fri Sep 13 03:00:11 EDT 2024 Thu Sep 26 17:26:28 EDT 2024 Sat Sep 28 08:11:56 EDT 2024 Wed Jun 26 19:28:16 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 7 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c352t-d4c54abb94dce0d564f523d5153a4b9d38f2ede5fb0d2e40e9ed98f4c49a25543 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0002-6355-7354 0000-0002-4234-6099 0000-0002-6913-7553 0000-0003-4152-5295 |
PMID | 37021865 |
PQID | 2823180613 |
PQPubID | 85458 |
PageCount | 16 |
ParticipantIDs | proquest_journals_2823180613 crossref_primary_10_1109_TPAMI_2023_3237856 pubmed_primary_37021865 ieee_primary_10019594 proquest_miscellaneous_2797144784 |
PublicationCentury | 2000 |
PublicationDate | 2023-07-01 |
PublicationDateYYYYMMDD | 2023-07-01 |
PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | United States |
PublicationPlace_xml | – name: United States – name: New York |
PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
PublicationTitleAbbrev | TPAMI |
PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
PublicationYear | 2023 |
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 | ref57 ref12 ref56 ref15 ref59 ref14 ref58 ref53 ref55 ref10 ref54 ref17 ref16 scheerlinck (ref40) 2018 ref18 pan (ref39) 2019 ref51 ref50 goodfellow (ref48) 2014 guerrieri (ref4) 2009 ref45 ref47 ref42 ref41 ref44 liu (ref6) 2014; 36 ref43 ref49 ref7 ref9 ref5 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref38 ref24 ref23 ref67 ref26 ref25 ref20 ref64 (ref61) 2013 ref63 ref22 ref66 ref21 ref65 (ref3) 2021 ref28 ref27 ref29 choi (ref52) 2020 dorozynska (ref8) 2020 gallego (ref13) 2019 duan (ref19) 2022; 44 ref60 ref62 ronneberger (ref46) 2015 patrick (ref11) 2008; 43 |
References_xml | – ident: ref55 doi: 10.1523/JNEUROSCI.22-02-00584.2002 – ident: ref10 doi: 10.1126/science.288.5469.1189 – ident: ref18 doi: 10.1109/CVPR.2019.00398 – ident: ref5 doi: 10.1145/3386569.3392470 – ident: ref27 doi: 10.1109/CVPR46437.2021.01182 – ident: ref54 doi: 10.1109/CVPR.2019.00953 – ident: ref57 doi: 10.1038/nature01248 – start-page: 308 year: 2018 ident: ref40 article-title: Continuous-time intensity estimation using event cameras publication-title: Proc Asian Conf Comput Vis contributor: fullname: scheerlinck – ident: ref38 doi: 10.1109/CVPR.2019.00698 – ident: ref21 doi: 10.1016/j.neuron.2012.10.002 – ident: ref24 doi: 10.1109/ICME.2019.00248 – ident: ref15 doi: 10.1109/TPAMI.2019.2903179 – ident: ref44 doi: 10.1109/CVPR42600.2020.00174 – ident: ref64 doi: 10.1109/LSP.2012.2227726 – year: 2020 ident: ref8 article-title: Frequency recognition algorithm for multiple exposures: Snapshot imaging using coded light contributor: fullname: dorozynska – ident: ref58 doi: 10.1038/nature03010 – ident: ref16 doi: 10.1109/TPAMI.2019.2963386 – ident: ref50 doi: 10.1109/CVPR.2019.01032 – year: 2019 ident: ref39 article-title: High frame rate video reconstruction based on an event camera contributor: fullname: pan – ident: ref28 doi: 10.1073/pnas.94.2.719 – ident: ref32 doi: 10.1109/ISCAS.2008.4541871 – ident: ref7 doi: 10.1109/TPAMI.2019.2946567 – ident: ref34 doi: 10.1109/CVPR42600.2020.00168 – ident: ref23 doi: 10.1109/DCC.2019.00080 – ident: ref35 doi: 10.1109/CVPR42600.2020.00180 – ident: ref20 doi: 10.1038/nrn1497 – ident: ref22 doi: 10.1109/DCC.2017.69 – ident: ref33 doi: 10.1109/JSSC.2014.2342715 – ident: ref67 doi: 10.1126/science.275.5297.221 – ident: ref31 doi: 10.1109/CVPR46437.2021.00629 – ident: ref66 doi: 10.1109/NCC.2015.7084843 – ident: ref30 doi: 10.1016/S0893-6080(97)00011-7 – ident: ref1 doi: 10.1063/1.1146268 – start-page: 234 year: 2015 ident: ref46 article-title: U-Net: Convolutional networks for biomedical image segmentation publication-title: Proc Int Conf Med Image Comput Comput - Assist Intervention contributor: fullname: ronneberger – ident: ref49 doi: 10.5220/0008934700370047 – year: 2021 ident: ref3 – year: 2019 ident: ref13 article-title: Event-based vision: A survey contributor: fullname: gallego – ident: ref59 doi: 10.1103/PhysRevE.85.016108 – ident: ref29 doi: 10.1162/089976698300017502 – ident: ref43 doi: 10.1117/1.JEI.28.6.063012 – ident: ref37 doi: 10.1109/ISCAS.2014.6865228 – year: 2013 ident: ref61 – ident: ref14 doi: 10.1109/CVPR.2018.00407 – ident: ref63 doi: 10.1109/7.805442 – volume: 43 start-page: 566 year: 2008 ident: ref11 article-title: A 128x 128 120 dB 15 ? s latency asynchronous temporal contrast vision sensor publication-title: IEEE J Solid-State Circuits doi: 10.1109/JSSC.2007.914337 contributor: fullname: patrick – ident: ref26 doi: 10.1109/ISCAS45731.2020.9181055 – ident: ref62 doi: 10.1109/LSP.2010.2043888 – ident: ref65 doi: 10.1109/TIP.2012.2214050 – ident: ref51 doi: 10.1109/CVPR42600.2020.00834 – ident: ref42 doi: 10.1007/s00371-017-1372-y – start-page: 2672 year: 2014 ident: ref48 article-title: Generative adversarial nets publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: goodfellow – ident: ref56 doi: 10.1152/jn.00806.2011 – ident: ref9 doi: 10.1109/TPAMI.2020.2986944 – volume: 36 start-page: 248 year: 2014 ident: ref6 article-title: Efficient space-time sampling with pixel-wise coded exposure for high-speed imaging publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2013.129 contributor: fullname: liu – ident: ref25 doi: 10.1109/CVPR42600.2020.00151 – year: 2009 ident: ref4 article-title: Fast single-photon imager acquires 1024pixels at 100 kframe/s publication-title: Sensors Cameras Syst Industrial/Scientific Appl X vol 7249 Int Soc Opt Photon contributor: fullname: guerrieri – ident: ref47 doi: 10.1007/978-3-030-01267-0_11 – ident: ref41 doi: 10.1109/ICCVW.2019.00532 – ident: ref53 doi: 10.1109/ICCV.2017.89 – start-page: 2768 year: 2020 ident: ref52 article-title: Learning to super resolve intensity images from events publication-title: Proc IEEE Conf Comput Vis and Pattern Recog contributor: fullname: choi – ident: ref2 doi: 10.1103/PhysRevLett.88.173903 – ident: ref60 doi: 10.3389/fncom.2013.00075 – ident: ref17 doi: 10.1007/s11263-020-01410-2 – ident: ref45 doi: 10.15607/RSS.2018.XIV.062 – ident: ref36 doi: 10.1109/ISCAS.2017.8050397 – volume: 44 start-page: 8261 year: 2022 ident: ref19 article-title: Guided event filtering: Synergy between intensity images and neuromorphic events for high performance imaging publication-title: IEEE Trans Pattern Anal Mach Intell contributor: fullname: duan – ident: ref12 doi: 10.1109/ISCAS.2010.5537149 |
SSID | ssj0014503 |
Score | 2.4830472 |
Snippet | High-speed imaging can help us understand some phenomena that our eyes cannot capture fast enough. Although ultra-fast frame-based cameras (e.g., Phantom) can... High-speed imaging can help us understand some phenomena that are too fast to be captured by our eyes. Although ultra-fast frame-based cameras (e.g., Phantom)... |
SourceID | proquest crossref pubmed ieee |
SourceType | Aggregation Database Index Database Publisher |
StartPage | 1 |
SubjectTerms | Cameras Computing time Error correction Firing High speed High-speed Reconstruction Image reconstruction Low latency communication Motion-dependent Noise reduction Plastic properties Reconstruction algorithms Short-term Plasticity Spiking Spiking Cameras Streaming media Vision sensors |
Title | Capture the Moment: High-speed Imaging with Spiking Cameras through Short-term Plasticity |
URI | https://ieeexplore.ieee.org/document/10019594 https://www.ncbi.nlm.nih.gov/pubmed/37021865 https://www.proquest.com/docview/2823180613/abstract/ https://search.proquest.com/docview/2797144784 |
Volume | 45 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Na9wwEB2anNJD06Rpu20aVOityLGtkW31FpaGJJAQSALpyVgfpqF0d-l6D8mv74xsL0sh0JvBQpY1Gs0bzYwewBdlVYnaZ9LmeZCoikyatnDSN1nhs6KkLTEmyF4VZ3d4ca_vh2L1WAsTQojJZyHhxxjL93O34qOy4yyWtxncgq0qzftirXXIAHWkQSYIQypOfsRYIZOa49vrk8vzhInCE5WrsmK26g0rFGlVnkeY0dKc7sLVOMY-weRXsups4p7-ub7xv3_iNbwaMKc46RfJHrwIs33YHfkcxKDe-_By43LCN_Bj2iw4vCAIIopLvqih-yY4LUQuF2TyxPnvSHAk-CRX3Cwe-MxdTBs-5FqKgf5H3PwkeC95-xfXhNM5hbt7PIC70--30zM5EDFIR_iskx6dxsZag96F1OsCW_JfPUEh1aA1XlVtHnzQrU19HjANJnhTtejQNOSyoHoL27P5LLwHEVqymZg57XSKwfiG_eKyUhm2aGymJvB1FEy96O_bqKOfkpo6irFmMdaDGCdwwBO80bKf2wkcjsKsB51c1jlHPCvGLxP4vH5N2sQhkmYW5itqU5qSXMyyoi7e9Ytg3bkqI4GX_vDMRz_CDo-tz-U9hO3uzyp8IsTS2aO4Uv8CUqXljA |
link.rule.ids | 315,786,790,802,27957,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3Pb9MwFH6CcQAODMaAwgAjcUPOkvg5iblNFVMLazVpnTROURw7AiHaiqYH-Ot5z0mqCmkSt0iJHMfPzvvezw_gvbIqR-0SadPUS1RZIk2T1dJVSeaSLKdfYkiQnWeTa_x8o2_6YvVQC-O9D8lnPuLLEMt3q3rLrrLTJJS3GbwL90jRx6Yr19oFDVAHImQCMXTIyZIYamRic7q4PJtNI6YKj1Sq8oL5qvf0UCBWuR1jBl1zfgjzYZZdismPaNvaqP7zTwPH__6Mx_CoR53irNsmT-COXx7B4cDoIPoDfgQP99oTPoWv42rNAQZBIFHMuFVD-1FwYojcrEnpienPQHEk2Jcrrtbf2esuxhW7uTaiJwASV98I4EtWAOKSkDoncbe_j-H6_NNiPJE9FYOsCaG10mGtsbLWoKt97HSGDVmwjsCQqtAap4om9c7rxsYu9Rh7450pGqzRVGS0oHoGB8vV0r8A4RvSmpjUutYxeuMqtozzQiXYoLGJGsGHQTDluuu4UQZLJTZlEGPJYix7MY7gmBd478lubUdwMgiz7E_lpkw55lkwghnBu91tOk8cJKmWfrWlZ3KTk5GZFzTE824T7AZXeaDw0i9veelbuD9ZzC7Ki-n8yyt4wPPsMntP4KD9tfWvCb-09k3YtX8Blxzo4g |
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=Capture+the+Moment%3A+High-Speed+Imaging+With+Spiking+Cameras+Through+Short-Term+Plasticity&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Zheng%2C+Yajing&rft.au=Zheng%2C+Lingxiao&rft.au=Yu%2C+Zhaofei&rft.au=Huang%2C+Tiejun&rft.date=2023-07-01&rft.eissn=1939-3539&rft.volume=45&rft.issue=7&rft.spage=8127&rft_id=info:doi/10.1109%2FTPAMI.2023.3237856&rft_id=info%3Apmid%2F37021865&rft.externalDocID=37021865 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |