Self-Supervised Audio-Visual Feature Learning for Single-modal Incremental Terrain Type Clustering

The key to an accurate understanding of terrain is to extract the informative features from the multi-modal data obtained from different devices. Sensors, such as RGB cameras, depth sensors, vibration sensors, and microphones, are used as the multi-modal data. Many studies have explored ways to use...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE Access Ročník 9; s. 1
Hlavní autoři:	Ishikawa, Reina, Hachiuma, Ryo, Saito, Hideo
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 01.01.2021 Institute of Electrical and Electronics Engineers (IEEE) The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Ablation Algorithms Audio data Cameras Clustering Data mining Electrical engineering. Electronics. Nuclear engineering Electronic devices Feature extraction Machine learning Microphones Modal data Multi-modal learning Probabilistic models Robotics Robots Self-supervised Sensors Terrain Terrain type clustering Testing TK1-9971 Training Visualization
ISSN:	2169-3536, 2169-3536
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The key to an accurate understanding of terrain is to extract the informative features from the multi-modal data obtained from different devices. Sensors, such as RGB cameras, depth sensors, vibration sensors, and microphones, are used as the multi-modal data. Many studies have explored ways to use them, especially in the robotics field. Some papers have successfully introduced single-modal or multi-modal methods. However, in practice, robots can be faced with extreme conditions; microphones do not work well in crowded scenes, and an RGB camera cannot capture terrains well in the dark. In this paper, we present a novel framework using the multi-modal variational autoencoder and the Gaussian mixture model clustering algorithm on image data and audio data for terrain type clustering by forcing the features to be closer together in the feature space. Our method enables the terrain type clustering even if one of the modalities (either image or audio) is missing at the test-time.We evaluated the clustering accuracy with a conventional multi-modal terrain type clustering method and we conducted ablation studies to show the effectiveness of our approach.
AbstractList	The key to an accurate understanding of terrain is to extract the informative features from the multi-modal data obtained from different devices. Sensors, such as RGB cameras, depth sensors, vibration sensors, and microphones, are used as the multi-modal data. Many studies have explored ways to use them, especially in the robotics field. Some papers have successfully introduced single-modal or multi-modal methods. However, in practice, robots can be faced with extreme conditions; microphones do not work well in crowded scenes, and an RGB camera cannot capture terrains well in the dark. In this paper, we present a novel framework using the multi-modal variational autoencoder and the Gaussian mixture model clustering algorithm on image data and audio data for terrain type clustering by forcing the features to be closer together in the feature space. Our method enables the terrain type clustering even if one of the modalities (either image or audio) is missing at the test-time. We evaluated the clustering accuracy with a conventional multi-modal terrain type clustering method and we conducted ablation studies to show the effectiveness of our approach.
Author	Ishikawa, Reina Hachiuma, Ryo Saito, Hideo
Author_xml	– sequence: 1 givenname: Reina surname: Ishikawa fullname: Ishikawa, Reina organization: Department of Information and Computer Science, Keio University, Yokohama, Japan. (e-mail: reina-ishikawa@keio.jp) – sequence: 2 givenname: Ryo surname: Hachiuma fullname: Hachiuma, Ryo organization: Department of Information and Computer Science, Keio University, Yokohama, Japan – sequence: 3 givenname: Hideo surname: Saito fullname: Saito, Hideo organization: Department of Information and Computer Science, Keio University, Yokohama, Japan
BackLink	https://cir.nii.ac.jp/crid/1874242817766052608$$DView record in CiNii
BookMark	eNp9kUtr3DAUhU1JoWmaX5CNod16ovdjOZikHRjowtNuhSxdBw0eaSrbhfz7auq0lC6ihXS5fOfci8776iqmCFV1h9EGY6Tvt2370HUbggjeUCQ5V-RNdU2w0A3lVFz9U7-rbqfpiMpRpcXlddV3MA5Nt5wh_wwT-Hq7-JCa72Fa7Fg_gp2XDPUebI4hPtVDynVXihGaU_KF2EWX4QRxLvUBcrYh1ofnM9TtuEwz5MJ-qN4Odpzg9uW9qb49PhzaL83-6-ddu903jks6NwS0760UBIT32LKhd5Jb7jHhGkuFNBK9Z9JhioBrxnpQRWjVQDV1dCD0ptqtvj7ZoznncLL52SQbzO9Gyk_G5jm4EYyjVjHinEfMsR5TWyw0lJFIWuEcKl4fV69zTj8WmGZzTEuOZX1DONZaSCxpofRKuZymKcNgXJjtHFKcy0eMBiNzScisCZlLQuYloaKl_2n_bPy66tOqiiGUYZcbK8kIIwpLKQTiRCBVsLsVCwDw11gzLJgS9BeKhqj3
CODEN	IAECCG
CitedBy_id	crossref_primary_10_3390_electronics12153238 crossref_primary_10_1016_j_neucom_2025_129750 crossref_primary_10_1002_rob_22054
Cites_doi	10.1007/978-3-642-16138-4_9 10.1109/CVPR.2016.278 10.1109/CVPR.2017.632 10.1162/089976602760128018 10.1007/978-3-319-70096-0_39 10.1109/ROBOT.2008.4543710 10.1109/LRA.2019.2895390 10.1109/ROBOT.2005.1570411 10.1109/ICSMC.2009.5345942 10.1109/ACCESS.2019.2916480 10.1109/TIP.2003.812327 10.1016/j.proeng.2012.07.253 10.1109/ICRA.2012.6225357 10.1109/ROBOT.2004.1302529 10.1002/rob.20113 10.1109/ICCV.2019.00715 10.1145/3334480.3382925 10.1109/IROS.2018.8593786 10.1016/j.ipm.2020.102270 10.1007/978-3-319-46487-9_40 10.1109/AERO.2015.7119022 10.1109/ICCV.2019.00654 10.1109/IJCNN48605.2020.9207523 10.1109/ICRA.2016.7487543 10.1109/LRA.2016.2525040 10.1109/IROS.2016.7758088 10.3390/app9153099 10.1109/IROS.2009.5354535 10.1109/IROS.2012.6386042 10.1109/CVPR.2007.383024 10.1080/00423110802450193 10.1109/CVPR.2016.90 10.1016/j.procs.2020.03.209 10.1109/AERO.2007.352693 10.1109/ACCESS.2021.3059620 10.1109/IVS.2018.8500506 10.24963/ijcai.2017/273 10.1023/B:AURO.0000047286.62481.1d 10.1109/ICASSP.2015.7178827 10.1109/TRO.2005.855994
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 ESBDL RIA RIE RYH AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2021.3075582
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CiNii Complete CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts 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 METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	1
ExternalDocumentID	oai_doaj_org_article_c3a842ccd04c4b13a93c9e4fb07a6cc0 10_1109_ACCESS_2021_3075582 9416486
Genre	orig-research
GroupedDBID	0R~ 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS RYH 4.4 AAYXX AGSQL CITATION EJD 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c573t-2e9dba762e6dd1a4fbc75a5d12591780906bd47c130e5944be8c57a8f393c3f23
IEDL.DBID	DOA
ISICitedReferencesCount	6
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000645860200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:50:27 EDT 2025 Sun Nov 30 03:50:42 EST 2025 Tue Nov 18 22:11:50 EST 2025 Sat Nov 29 06:12:12 EST 2025 Thu Jun 26 22:19:19 EDT 2025 Wed Aug 27 02:30:06 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c573t-2e9dba762e6dd1a4fbc75a5d12591780906bd47c130e5944be8c57a8f393c3f23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-2421-9862 0000-0003-4792-6380
OpenAccessLink	https://doaj.org/article/c3a842ccd04c4b13a93c9e4fb07a6cc0
PQID	2519967173
PQPubID	4845423
PageCount	1
ParticipantIDs	ieee_primary_9416486 doaj_primary_oai_doaj_org_article_c3a842ccd04c4b13a93c9e4fb07a6cc0 proquest_journals_2519967173 crossref_primary_10_1109_ACCESS_2021_3075582 nii_cinii_1874242817766052608 crossref_citationtrail_10_1109_ACCESS_2021_3075582
PublicationCentury	2000
PublicationDate	2021-01-01
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– month: 01 year: 2021 text: 2021-01-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE Access
PublicationTitleAbbrev	Access
PublicationYear	2021
Publisher	IEEE Institute of Electrical and Electronics Engineers (IEEE) The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: Institute of Electrical and Electronics Engineers (IEEE) – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref12 ref14 ref53 ref52 ref11 ref10 zürn (ref6) 2019 ref17 ref16 ramachandran (ref55) 2017 ref18 valada (ref13) 2018 wu (ref28) 2018 tschannen (ref26) 2018 ref50 ref46 ref45 ref48 ref42 ref41 ref44 ref43 neverova (ref36) 2014 ref49 ref8 ref7 xie (ref37) 2016; 48 ref9 higgins (ref51) 2017 ref4 ref3 xie (ref19) 2020; 100 ref5 ref40 baur (ref47) 2018 van der maaten (ref57) 2008; 9 kingma (ref56) 2015 ref35 ref34 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 hu (ref23) 2020 ref24 takahashi (ref15) 2018 ref20 ref22 ref21 ref29 paszke (ref54) 2019 xie (ref25) 2016 ishikawa (ref27) 2020
References_xml	– year: 2019 ident: ref6 article-title: Self-supervised visual terrain classification from unsupervised acoustic feature learning publication-title: arXiv 1912 03227 – ident: ref53 doi: 10.1007/978-3-642-16138-4_9 – ident: ref44 doi: 10.1109/CVPR.2016.278 – ident: ref46 doi: 10.1109/CVPR.2017.632 – year: 2017 ident: ref55 article-title: Searching for activation functions publication-title: arXiv 1710 05941 – ident: ref52 doi: 10.1162/089976602760128018 – ident: ref38 doi: 10.1007/978-3-319-70096-0_39 – ident: ref32 doi: 10.1109/ROBOT.2008.4543710 – ident: ref42 doi: 10.1109/LRA.2019.2895390 – ident: ref3 doi: 10.1109/ROBOT.2005.1570411 – year: 2020 ident: ref23 article-title: Ambient sound helps: Audiovisual crowd counting in extreme conditions publication-title: arXiv 2005 07097 – ident: ref33 doi: 10.1109/ICSMC.2009.5345942 – ident: ref17 doi: 10.1109/ACCESS.2019.2916480 – ident: ref34 doi: 10.1109/TIP.2003.812327 – year: 2016 ident: ref25 article-title: Aggregated residual transformations for deep neural networks publication-title: arXiv 1611 05431 – ident: ref16 doi: 10.1016/j.proeng.2012.07.253 – year: 2018 ident: ref26 article-title: Recent advances in autoencoder-based representation learning publication-title: arXiv 1812 05069 – ident: ref11 doi: 10.1109/ICRA.2012.6225357 – ident: ref4 doi: 10.1109/ROBOT.2004.1302529 – ident: ref12 doi: 10.1002/rob.20113 – start-page: 9399 year: 2020 ident: ref27 article-title: Single-modal incremental terrain clustering from self-supervised audio-visual feature learning publication-title: Proc Int Conf Pattern Recognit (ICPR) – year: 2015 ident: ref56 article-title: Adam: A method for stochastic optimization publication-title: Proc 3rd Int Conf Learn Represent (ICLR) – ident: ref20 doi: 10.1109/ICCV.2019.00715 – ident: ref7 doi: 10.1145/3334480.3382925 – ident: ref21 doi: 10.1109/IROS.2018.8593786 – year: 2014 ident: ref36 article-title: ModDrop: Adaptive multi-modal gesture recognition publication-title: arXiv 1501 00102 – ident: ref50 doi: 10.1016/j.ipm.2020.102270 – ident: ref45 doi: 10.1007/978-3-319-46487-9_40 – start-page: 5580 year: 2018 ident: ref28 article-title: Multimodal generative models for scalable weakly-supervised learning publication-title: Proc Int Conf Neural Inf Process – ident: ref29 doi: 10.1109/AERO.2015.7119022 – volume: 100 start-page: 1369 year: 2020 ident: ref19 article-title: The best of both modes: Separately leveraging RGB and depth for unseen object instance segmentation publication-title: Proc Conf Robot Learn – ident: ref40 doi: 10.1109/ICCV.2019.00654 – ident: ref41 doi: 10.1109/IJCNN48605.2020.9207523 – ident: ref10 doi: 10.1109/ICRA.2016.7487543 – ident: ref5 doi: 10.1109/LRA.2016.2525040 – ident: ref14 doi: 10.1109/IROS.2016.7758088 – ident: ref8 doi: 10.3390/app9153099 – ident: ref30 doi: 10.1109/IROS.2009.5354535 – year: 2018 ident: ref47 article-title: Deep autoencoding models for unsupervised anomaly segmentation in brain MR images publication-title: arXiv 1804 04488 – ident: ref35 doi: 10.1109/IROS.2012.6386042 – start-page: 21 year: 2018 ident: ref13 publication-title: Deep Feature Learning for Acoustics-Based Terrain Classification – ident: ref1 doi: 10.1109/CVPR.2007.383024 – ident: ref18 doi: 10.1080/00423110802450193 – ident: ref24 doi: 10.1109/CVPR.2016.90 – volume: 48 start-page: 478 year: 2016 ident: ref37 article-title: Unsupervised deep embedding for clustering analysis publication-title: Proc 33rd Int Conf Int Conf Mach Learn (ICML) – ident: ref49 doi: 10.1016/j.procs.2020.03.209 – ident: ref43 doi: 10.1109/AERO.2007.352693 – ident: ref22 doi: 10.1109/ACCESS.2021.3059620 – year: 2017 ident: ref51 article-title: Beta-VAE: Learning basic visual concepts with a constrained variational framework publication-title: Proc 5th Int Conf Learn Represent (ICLR) – ident: ref9 doi: 10.1109/IVS.2018.8500506 – ident: ref39 doi: 10.24963/ijcai.2017/273 – start-page: 8024 year: 2019 ident: ref54 article-title: PyTorch: An imperative style, high-performance deep learning library publication-title: Proc Adv Neural Inf Process Syst – volume: 9 start-page: 2579 year: 2008 ident: ref57 article-title: Visualizing data using T-SNE publication-title: J Mach Learn Res – ident: ref2 doi: 10.1023/B:AURO.0000047286.62481.1d – year: 2018 ident: ref15 article-title: Deep visuo-tactile learning: Estimation of material properties from images publication-title: arXiv 1803 03435 – ident: ref48 doi: 10.1109/ICASSP.2015.7178827 – ident: ref31 doi: 10.1109/TRO.2005.855994
SSID	ssj0000816957
Score	2.233185
Snippet	The key to an accurate understanding of terrain is to extract the informative features from the multi-modal data obtained from different devices. Sensors, such...
SourceID	doaj proquest crossref nii ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Ablation Algorithms Audio data Cameras Clustering Data mining Electrical engineering. Electronics. Nuclear engineering Electronic devices Feature extraction Machine learning Microphones Modal data Multi-modal learning Probabilistic models Robotics Robots Self-supervised Sensors Terrain Terrain type clustering Testing TK1-9971 Training Visualization
SummonAdditionalLinks	– databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6S0EN76CstcZsUH3qMEtmW9ThuloYcQihsGnIztjQuhu1u2F3393fGVkxLSqEXI4wkNJ7R6NNY-gbgs7NeBq9z0ZTKCAa8oi5MITLUTeszK8OQDuju2tzc2Pt793UPTqe7MIg4HD7DMy4O__LD2vccKjt3hB6U1fuwb4we72pN8RROIOFKE4mFMunOZ_M5yUBbwDw7I0suS5v_sfgMHP0xqQqtLKuue-KPh0Xm8tX_De81vIxgMp2N2n8De7h6Cy9-oxg8hGaBy1Ys-gf2CVsM6awP3VrcddueWjIA7DeYRpbV7ylB2HRBhSWKH-tANch_jBFEKt_ihhNKpLx3TefLnjkWqO47-Hb55XZ-JWJeBeFLU-xEji40NXlB1CFktWobb8q6DIR1aPNmpZO6Ccp4Wt6wdEo1aKlhbdvCFb5o8-I9HKzWKzyClAAaEgIy2KJRmOe1RtW01FZj6QmKJZA_fvDKR9Jxzn2xrIbNh3TVqKWKtVRFLSVwOjV6GDk3_l39gjU5VWXC7OEFKaeK86_yRW1V7n2QyqsmK2oSxSGJLk2tvZcJHLJCp06iLhM4IbugofOT0xcSorEZWZ9mnhxpEzh-tJgqTv5txZeBnebjDR_-3utHeM4CjJGcYzjYbXo8gWf-567bbj4Ndv0LdjvzIQ priority: 102 providerName: IEEE
Title	Self-Supervised Audio-Visual Feature Learning for Single-modal Incremental Terrain Type Clustering
URI	https://ieeexplore.ieee.org/document/9416486 https://cir.nii.ac.jp/crid/1874242817766052608 https://www.proquest.com/docview/2519967173 https://doaj.org/article/c3a842ccd04c4b13a93c9e4fb07a6cc0
Volume	9
WOSCitedRecordID	wos000645860200001&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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NaxQxFA9SPOhB1CqOtmUOHo3NzOTzuC4tHmwRtpbeQj7eyMCyW3Z3PPq3-5JJlxVBL15CGN4bkpeX5PdC8nuEvDc6sBhkS73giibAS12nOtqA9H1oNIs5HdDtF3V9re_uzNeDVF_pTthEDzwZ7jx0TvM2hMh44L7pnOmCAd57ppwMIUfrTJmDYCqvwbqRRqhCM9Qwcz6bz7FHGBC2zUf0ayF0-9tWlBn7S4oV3GdWw_DH6py3nMvn5FnBivVsauML8ghWL8nTAwbBY-IXsOzpYrxPU34LsZ6NcVjT22E7ombCd-MG6kKi-r1GhFovsLIEerWOKIHLw3RAiPUb2KR8EXUKTev5ckwUCij7iny7vLiZf6YlbQINQnU72oKJ3uEiBzLGxqGpghJORIQyGJtpZpj0kauAuxcIw7kHjYpO9x2atuvb7jU5Wq1X8IbUiL8AAY6CHhSHtnUSuO9RV4IIiLQq0j5Y0IbCKZ5SWyxtji2YsZPZbTK7LWavyIe90v1EqfF38U9paPaiiQ87f0AvscVL7L-8pCLHaWD3PzGIQ7mWFTnFgcampzJlJ0TAohulpEw0OExX5OTBBWyZ21ub3voamW4vvP0fTXtHnqTuTsc6J-RotxnhlDwOP3bDdnOW3RrLq58XZ_lx4i-GDPkd
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwELfGQAIe-BqIwAZ54HHeHMefj6ViGqJUSC3T3qzEvqBIpZ3ahr-fc-JFIBASL5EVnS1fzj7_fLF_R8g7azwLXnFaS6FpBLy0KnVJC1B14wvDQp8O6Gqm53NzfW2_HJDT8S4MAPSHz-AsFvt_-WHjuxgqO7eIHoRRd8hdKQRnw22tMaISU0hYqRO1UMHs-WQ6RS1wE8iLMxzLUhr-2_LTs_SntCq4tqzb9g-P3C8zF4__r4NPyKMEJ_PJYP-n5ADWz8jDX0gGj0i9gFVDF91N9Ao7CPmkC-2GXrW7DmtGCNhtIU88q99yBLH5AgsroN83ASXQgwwxRCwvYRtTSuRx95pPV11kWUDZ5-TrxYfl9JKmzArUS13uKQcb6gr9IKgQiko0tdeykgHRDm7fDLNM1UFojwscSCtEDQYrVqYpbenLhpcvyOF6s4aXJEeIBoiBNDSgBXBeKRB1g3UVSI9gLCP89oM7n2jHY_aLleu3H8y6wUouWsklK2XkdKx0M7Bu_Fv8fbTkKBops_sXaByXZqDzZWUE9z4w4UVdlBWqYgFVZ7pS3rOMHEWDjo0kW2bkBMcFdj0-YwJDxDSm0FqpyJTDTEaOb0eMS9N_5-J1YKviAYdXf2_1Lbl_ufw8c7OP80-vyYOozBDXOSaH-20HJ-Se_7Fvd9s3_Rj_CT7u9mg
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=Self-Supervised+Audio-Visual+Feature+Learning+for+Single-Modal+Incremental+Terrain+Type+Clustering&rft.jtitle=IEEE+access&rft.au=Ishikawa%2C+Reina&rft.au=Hachiuma%2C+Ryo&rft.au=Saito%2C+Hideo&rft.date=2021-01-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2169-3536&rft.volume=9&rft.spage=64346&rft_id=info:doi/10.1109%2FACCESS.2021.3075582&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon