Learning of 3D Graph Convolution Networks for Point Cloud Analysis

Point clouds are among the popular geometry representations in 3D vision. However, unlike 2D images with pixel-wise layouts, such representations containing unordered data points which make the processing and understanding the associated semantic information quite challenging. Although a number of p...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 8; pp. 4212 - 4224
Main Authors:	Lin, Zhi-Hao, Huang, Sheng-Yu, Wang, Yu-Chiang Frank
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.08.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	3D classification 3D segmentation 3D vision Ablation Convolution Data points deformable kernels Feature extraction graph convolution networks Image segmentation Kernel point clouds Representations Scale invariance Shape Task analysis Three dimensional models Three-dimensional displays Two dimensional displays
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Point clouds are among the popular geometry representations in 3D vision. However, unlike 2D images with pixel-wise layouts, such representations containing unordered data points which make the processing and understanding the associated semantic information quite challenging. Although a number of previous works attempt to analyze point clouds and achieve promising performances, their performances would degrade significantly when data variations like shift and scale changes are presented. In this paper, we propose 3D graph convolution networks (3D-GCN) , which uniquely learns 3D kernels with graph max-pooling mechanisms for extracting geometric features from point cloud data across different scales. We show that, with the proposed 3D-GCN, satisfactory shift and scale invariance can be jointly achieved. We show that 3D-GCN can be applied to point cloud classification and segmentation tasks, with ablation studies and visualizations verifying the design of 3D-GCN.
AbstractList	Point clouds are among the popular geometry representations in 3D vision. However, unlike 2D images with pixel-wise layouts, such representations containing unordered data points which make the processing and understanding the associated semantic information quite challenging. Although a number of previous works attempt to analyze point clouds and achieve promising performances, their performances would degrade significantly when data variations like shift and scale changes are presented. In this paper, we propose 3D graph convolution networks (3D-GCN) , which uniquely learns 3D kernels with graph max-pooling mechanisms for extracting geometric features from point cloud data across different scales. We show that, with the proposed 3D-GCN, satisfactory shift and scale invariance can be jointly achieved. We show that 3D-GCN can be applied to point cloud classification and segmentation tasks, with ablation studies and visualizations verifying the design of 3D-GCN. Point clouds are among the popular geometry representations in 3D vision. However, unlike 2D images with pixel-wise layouts, such representations containing unordered data points which make the processing and understanding the associated semantic information quite challenging. Although a number of previous works attempt to analyze point clouds and achieve promising performances, their performances would degrade significantly when data variations like shift and scale changes are presented. In this paper, we propose 3D graph convolution networks (3D-GCN), which uniquely learns 3D kernels with graph max-pooling mechanisms for extracting geometric features from point cloud data across different scales. We show that, with the proposed 3D-GCN, satisfactory shift and scale invariance can be jointly achieved. We show that 3D-GCN can be applied to point cloud classification and segmentation tasks, with ablation studies and visualizations verifying the design of 3D-GCN.Point clouds are among the popular geometry representations in 3D vision. However, unlike 2D images with pixel-wise layouts, such representations containing unordered data points which make the processing and understanding the associated semantic information quite challenging. Although a number of previous works attempt to analyze point clouds and achieve promising performances, their performances would degrade significantly when data variations like shift and scale changes are presented. In this paper, we propose 3D graph convolution networks (3D-GCN), which uniquely learns 3D kernels with graph max-pooling mechanisms for extracting geometric features from point cloud data across different scales. We show that, with the proposed 3D-GCN, satisfactory shift and scale invariance can be jointly achieved. We show that 3D-GCN can be applied to point cloud classification and segmentation tasks, with ablation studies and visualizations verifying the design of 3D-GCN.
Author	Lin, Zhi-Hao Wang, Yu-Chiang Frank Huang, Sheng-Yu
Author_xml	– sequence: 1 givenname: Zhi-Hao orcidid: 0000-0002-4831-5488 surname: Lin fullname: Lin, Zhi-Hao email: r08942062@ntu.edu.tw organization: Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan – sequence: 2 givenname: Sheng-Yu orcidid: 0000-0002-3149-9620 surname: Huang fullname: Huang, Sheng-Yu email: r08942095@ntu.edu.tw organization: Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan – sequence: 3 givenname: Yu-Chiang Frank orcidid: 0000-0002-2333-157X surname: Wang fullname: Wang, Yu-Chiang Frank email: ycwang@ntu.edu.tw organization: Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33591911$$D View this record in MEDLINE/PubMed
BookMark	eNp9kU1PGzEQhq0KVALlDxSpssSll03Hn2sfQ9pCpNDmAGfLu-stphs72LtU_PtuSODAgdNIo-cZzcx7jA5CDA6hzwSmhID-drOaXS-mFCiZMhC6FOoDmlAiodBU0wM0ASJpoRRVR-g453sAwgWwj-iIMaGJJmSCLpbOpuDDHxxbzL7jy2Q3d3gew2Psht7HgH-5_l9MfzNuY8Kr6EOP510cGjwLtnvKPn9Ch63tsjvd1xN0-_PHzfyqWP6-XMxny6JmgvSF1FVblmUFlawFNExxq1oYG43UjnKpBJfCgW6hJq7mnFlZMWKdahSUvNTsBH3dzd2k-DC43Ju1z7XrOhtcHLKhXIMETqUY0fM36H0c0rjvSElFx9s53VJf9tRQrV1jNsmvbXoyL98ZAbUD6hRzTq41te_t9it9sr4zBMw2CPMchNkGYfZBjCp9o75Mf1c620neOfcqaCYEjOv-B7dzkLc
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_3390_rs14092187 crossref_primary_10_1109_ACCESS_2022_3144449 crossref_primary_10_1109_TII_2024_3514159 crossref_primary_10_1109_TPAMI_2022_3178184 crossref_primary_10_1109_TGRS_2024_3416219 crossref_primary_10_1109_TPAMI_2024_3378708 crossref_primary_10_1109_TPAMI_2023_3298711 crossref_primary_10_1080_10095020_2023_2264337 crossref_primary_10_1016_j_cag_2023_03_008 crossref_primary_10_7717_peerj_cs_1738 crossref_primary_10_1007_s10489_023_04754_7 crossref_primary_10_1016_j_engappai_2024_109224 crossref_primary_10_1109_TPAMI_2024_3387838 crossref_primary_10_1016_j_cag_2022_07_002 crossref_primary_10_1016_j_neucom_2021_10_072 crossref_primary_10_1109_JSEN_2024_3452673 crossref_primary_10_1109_TIP_2025_3571680 crossref_primary_10_1109_TMM_2024_3358695 crossref_primary_10_1109_TPAMI_2025_3532637 crossref_primary_10_3390_rs13163288 crossref_primary_10_1109_TMM_2023_3342697 crossref_primary_10_1109_TPAMI_2024_3400402 crossref_primary_10_1108_ECAM_12_2023_1227
Cites_doi	10.1109/CVPR.2018.00275 10.1109/CVPR.2016.90 10.1145/3450626.3459787 10.1109/CVPR.2017.11 10.1109/CVPR.2019.00910 10.1007/978-3-319-46484-8_38 10.1109/CVPR.2017.576 10.1109/ICIP.2011.6116679 10.1109/ICCV.2019.00169 10.1145/3065386 10.1109/CVPR42600.2020.00187 10.1111/j.1467-8659.2011.01884.x 10.1109/CVPR.2018.00526 10.1109/TNNLS.2020.2978386 10.1109/CVPR.2018.00376 10.1145/3306346.3322959 10.1109/ICCVW.2015.112 10.1145/3197517.3201301 10.1007/978-3-319-24574-4_28 10.1109/ICCV.2017.99 10.1109/CVPR.2015.7298801 10.1109/CVPR.2018.00409 10.1109/ICCV.2015.114 10.1109/CVPR.2016.609 10.18178/wcse.2019.06.016 10.5555/3157382.3157527 10.1109/TPAMI.2020.2983410 10.5555/3295222.3295263 10.1109/CVPR.2015.7298965 10.1145/2980179.2980238 10.1109/ICCV.2019.00859 10.1109/TPAMI.2007.41 10.1109/TPAMI.2014.2316828 10.1109/CVPR.2016.170 10.1109/CVPR42600.2020.01112 10.1109/CVPR.2018.00979 10.1109/IROS.2008.4650967 10.1109/CVPR.2017.701 10.1109/CVPR.2018.00102 10.1145/3326362 10.1109/IROS.2015.7353481 10.1109/TPAMI.2016.2644615 10.1109/CVPR.2018.00278 10.1109/CVPR.2018.00109 10.1109/CVPR.2018.00478 10.1109/ICCV.2019.00651 10.1109/ROBOT.2009.5152473 10.1109/CVPR.2019.00985 10.1007/978-3-030-01234-2_7
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2021.3059758
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef PubMed 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	CrossRef PubMed 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	PubMed MEDLINE - Academic Technology Research Database
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	4224
ExternalDocumentID	33591911 10_1109_TPAMI_2021_3059758 9355025
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: Ministry of Science and Technology of Taiwan grantid: MOST 109-2634-F-002-037
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR 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 RIE RNS RXW TAE TN5 UHB ~02 5VS 9M8 AAYXX ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH CITATION FA8 H~9 IBMZZ ICLAB IFJZH RNI RZB VH1 NPM RIC Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c351t-69bf777b0b6c50d384a8f077bd69e24685465e09f0c1ec443a6b31ae8d8074793
IEDL.DBID	RIE
ISICitedReferencesCount	58
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000820521600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Sat Sep 27 21:41:05 EDT 2025 Sun Jun 29 15:54:18 EDT 2025 Wed Feb 19 02:28:10 EST 2025 Sat Nov 29 05:16:00 EST 2025 Tue Nov 18 22:53:29 EST 2025 Wed Aug 27 02:23:53 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c351t-69bf777b0b6c50d384a8f077bd69e24685465e09f0c1ec443a6b31ae8d8074793
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-2333-157X 0000-0002-3149-9620 0000-0002-4831-5488
PMID	33591911
PQID	2682919425
PQPubID	85458
PageCount	13
ParticipantIDs	proquest_journals_2682919425 crossref_primary_10_1109_TPAMI_2021_3059758 crossref_citationtrail_10_1109_TPAMI_2021_3059758 ieee_primary_9355025 pubmed_primary_33591911 proquest_miscellaneous_2490604265
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	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	2022
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	ref13 ref12 ref56 ref15 ref14 ref53 ref52 ref55 ref10 ref54 ref17 ref16 ref18 ref51 ref50 ref45 Qi (ref9) ref48 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref4 ref3 ref6 ref5 Belongie (ref27) ref35 ref34 ref37 ref36 ref31 Roynard (ref19) 2018 ref30 ref33 ref32 ref2 ref1 ref38 Boscaini (ref11) Li (ref46) ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref29 Veličković (ref40) 2018 Hamilton (ref39)
References_xml	– year: 2018 ident: ref40 article-title: Graph attention networks publication-title: Proc. Int. Conf. Learn. Representations – ident: ref42 doi: 10.1109/CVPR.2018.00275 – ident: ref7 doi: 10.1109/CVPR.2016.90 – ident: ref21 doi: 10.1145/3450626.3459787 – ident: ref10 doi: 10.1109/CVPR.2017.11 – ident: ref13 doi: 10.1109/CVPR.2019.00910 – ident: ref3 doi: 10.1007/978-3-319-46484-8_38 – ident: ref6 doi: 10.1109/CVPR.2017.576 – year: 2018 ident: ref19 article-title: Classification of point cloud scenes with multiscale voxel deep network – ident: ref31 doi: 10.1109/ICIP.2011.6116679 – start-page: 1025 volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst. ident: ref39 article-title: Inductive representation learning on large graphs – ident: ref48 doi: 10.1109/ICCV.2019.00169 – ident: ref8 doi: 10.1145/3065386 – ident: ref16 doi: 10.1109/CVPR42600.2020.00187 – ident: ref33 doi: 10.1111/j.1467-8659.2011.01884.x – ident: ref23 doi: 10.1109/CVPR.2018.00526 – ident: ref41 doi: 10.1109/TNNLS.2020.2978386 – ident: ref2 doi: 10.1109/CVPR.2018.00376 – ident: ref43 doi: 10.1145/3306346.3322959 – ident: ref5 doi: 10.1109/ICCVW.2015.112 – ident: ref26 doi: 10.1145/3197517.3201301 – ident: ref52 doi: 10.1007/978-3-319-24574-4_28 – ident: ref35 doi: 10.1109/ICCV.2017.99 – ident: ref4 doi: 10.1109/CVPR.2015.7298801 – ident: ref25 doi: 10.1109/CVPR.2018.00409 – ident: ref22 doi: 10.1109/ICCV.2015.114 – ident: ref24 doi: 10.1109/CVPR.2016.609 – ident: ref37 doi: 10.18178/wcse.2019.06.016 – ident: ref38 doi: 10.5555/3157382.3157527 – ident: ref47 doi: 10.1109/TPAMI.2020.2983410 – start-page: 798 volume-title: Proc. 13th Int. Conf. Neural Inf. Process. Syst. ident: ref27 article-title: Shape context: A new descriptor for shape matching and object recognition – ident: ref44 doi: 10.5555/3295222.3295263 – ident: ref51 doi: 10.1109/CVPR.2015.7298965 – start-page: 828 volume-title: Proc. 32nd Int. Conf. Neural Inf. Process. Syst. ident: ref46 article-title: PointCNN: Convolution on X-transformed points – ident: ref55 doi: 10.1145/2980179.2980238 – ident: ref17 doi: 10.1109/ICCV.2019.00859 – ident: ref28 doi: 10.1109/TPAMI.2007.41 – ident: ref32 doi: 10.1109/TPAMI.2014.2316828 – ident: ref56 doi: 10.1109/CVPR.2016.170 – ident: ref50 doi: 10.1109/CVPR42600.2020.01112 – ident: ref54 doi: 10.1109/CVPR.2018.00979 – ident: ref30 doi: 10.1109/IROS.2008.4650967 – ident: ref20 doi: 10.1109/CVPR.2017.701 – ident: ref1 doi: 10.1109/CVPR.2018.00102 – ident: ref15 doi: 10.1145/3326362 – ident: ref18 doi: 10.1109/IROS.2015.7353481 – start-page: 3197 volume-title: Proc. 30th Int. Conf. Neural Inf. Process. Syst. ident: ref11 article-title: Learning shape correspondence with anisotropic convolutional neural networks – ident: ref53 doi: 10.1109/TPAMI.2016.2644615 – ident: ref34 doi: 10.1109/CVPR.2018.00278 – ident: ref45 doi: 10.1109/CVPR.2018.00109 – ident: ref12 doi: 10.1109/CVPR.2018.00478 – ident: ref14 doi: 10.1109/ICCV.2019.00651 – ident: ref29 doi: 10.1109/ROBOT.2009.5152473 – ident: ref49 doi: 10.1109/CVPR.2019.00985 – start-page: 77 volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. ident: ref9 article-title: PointNet: Deep learning on point sets for 3D classification and segmentation – ident: ref36 doi: 10.1007/978-3-030-01234-2_7
SSID	ssj0014503
Score	2.607508
Snippet	Point clouds are among the popular geometry representations in 3D vision. However, unlike 2D images with pixel-wise layouts, such representations containing...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	4212
SubjectTerms	3D classification 3D segmentation 3D vision Ablation Convolution Data points deformable kernels Feature extraction graph convolution networks Image segmentation Kernel point clouds Representations Scale invariance Shape Task analysis Three dimensional models Three-dimensional displays Two dimensional displays
Title	Learning of 3D Graph Convolution Networks for Point Cloud Analysis
URI	https://ieeexplore.ieee.org/document/9355025 https://www.ncbi.nlm.nih.gov/pubmed/33591911 https://www.proquest.com/docview/2682919425 https://www.proquest.com/docview/2490604265
Volume	44
WOSCitedRecordID	wos000820521600002&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 Xplore customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS-QwEB9UjkMfzju_btWTCL5pNW3SNHnU9dQDXfZBZd9KmqYiSHu4u_79N0nTonAKvpVm-sF8kJkk8_sBHCimUqN4gc6bMCxQijSSyuioYllmNS8L6ene7q-z0UhOJmq8AEd9L4y11h8-s8fu0u_ll42Zu6WyE4cFjnP0IixmWdb2avU7Bjz1LMiYwWCEYxnRNchQdXI7Pr35g6VgEh-jdyvMkJfhK2OpwlolfjMfeYKV93NNP-dcrH7ub7_Dt5BbktPWGX7Agq3XYLXjbSAhjNdg5RUI4TqcBYjVB9JUhJ2TSwdhTYZN_RK8kozao-JTggkuGTeP9YwMn5p5STpEkw24u_h9O7yKArNCZFgazyKhigpVWNBCmJSWTHItK4o3SqFswoV0FOmWqoqa2BrOmRYFi7WVpcPOwZDehKW6qe1PIFQaZhLGlckqLopMx1jBKKqZoFqqygwg7vSbmwA77tgvnnJfflCVe_Pkzjx5MM8ADvtn_ragGx9Krzvl95JB7wPY7cyYh7ic5omQCZqdu-H9fhgjym2T6No2c5ThyiEKJQJltlrz9-_uvGb7_9_cgeXEtUf4A4K7sDR7nttf8MW8zB6nz3vothO55932H6ja4xc
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB5RqFp6gBb62Ja2rtRbCTi249hHukBBXVZ7WCpukeM4CAklFbvL7-_YcaJWopV6i-LJQ54Zecbj-T6Az5rrzGpRovEyjglKmSVKW5PUPM-dEVWpAt3bj0k-naqrKz1bg_2hF8Y5Fw6fuQN_GWr5VWtXfqvs0GOB4xr9CDYyIVjadWsNNQORBR5kjGHQxzGR6FtkqD6cz44uzjEZZOkB2rfGGHkTnnCeacxW0j9WpECx8vdoM6w6p9v_97_PYStGl-SoM4cXsOaaHdjumRtIdOQdePYbDOEufI0gq9ekrQk_Jt88iDUZt819tEsy7Q6LLwiGuGTW3jRLMr5tVxXpMU1ewuXpyXx8lkRuhcTyLF0mUpd1nuclLaXNaMWVMKqmeKOS2jEhlSdJd1TX1KbOCsGNLHlqnKo8eg469StYb9rGvQFCleWWcaFtXgtZ5ibFHEZTwyU1Std2BGk_v4WNwOOe_-K2CAkI1UVQT-HVU0T1jODL8MzPDnbjn9K7fvIHyTjvI9jr1VhEz1wUTCqGahd--NMwjD7lCyWmce0KZYT2mEJMoszrTv3Du3urefvwNz_C07P5xaSYnE-_v4NN5pslwnHBPVhf3q3ce3hs75c3i7sPwXh_AUhx5XY
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=Learning+of+3D+Graph+Convolution+Networks+for+Point+Cloud+Analysis&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Lin%2C+Zhi-Hao&rft.au=Huang%2C+Sheng+Yu&rft.au=Wang%2C+Yu-Chiang+Frank&rft.date=2022-08-01&rft.eissn=1939-3539&rft.volume=PP&rft_id=info:doi/10.1109%2FTPAMI.2021.3059758&rft_id=info%3Apmid%2F33591911&rft.externalDocID=33591911
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