Geometric Back-Projection Network for Point Cloud Classification
As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better representations. To achieve this, on the one hand, we enrich the ge...
Uloženo v:
| Vydáno v: | IEEE transactions on multimedia Ročník 24; s. 1943 - 1955 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Piscataway
IEEE
2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 1520-9210, 1941-0077 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better representations. To achieve this, on the one hand, we enrich the geometric information of points in low-level 3D space explicitly. On the other hand, we apply CNN-based structures in high-level feature spaces to learn local geometric context implicitly. Specifically, we leverage an idea of error-correcting feedback structure to capture the local features of point clouds comprehensively. Furthermore, an attention module based on channel affinity assists the feature map to avoid possible redundancy by emphasizing its distinct channels. The performance on both synthetic and real-world point clouds datasets demonstrate the superiority and applicability of our network. Comparing with other state-of-the-art methods, our approach balances accuracy and efficiency. |
|---|---|
| AbstractList | As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better representations. To achieve this, on the one hand, we enrich the geometric information of points in low-level 3D space explicitly. On the other hand, we apply CNN-based structures in high-level feature spaces to learn local geometric context implicitly. Specifically, we leverage an idea of error-correcting feedback structure to capture the local features of point clouds comprehensively. Furthermore, an attention module based on channel affinity assists the feature map to avoid possible redundancy by emphasizing its distinct channels. The performance on both synthetic and real-world point clouds datasets demonstrate the superiority and applicability of our network. Comparing with other state-of-the-art methods, our approach balances accuracy and efficiency. |
| Author | Barnes, Nick Anwar, Saeed Qiu, Shi |
| Author_xml | – sequence: 1 givenname: Shi orcidid: 0000-0001-9958-180X surname: Qiu fullname: Qiu, Shi email: shi.qiu@anu.edu.au organization: Data61, CSIRO (The Commonwealth Scientific and Industrial Research Organisation), and Research School of Engineering, Australian National University, Canberra, ACT, Australia – sequence: 2 givenname: Saeed orcidid: 0000-0002-0692-8411 surname: Anwar fullname: Anwar, Saeed email: saeed.anwar@data61.csiro.au organization: Data61, CSIRO (The Commonwealth Scientific and Industrial Research Organisation), and Research School of Engineering, Australian National University, Canberra, ACT, Australia – sequence: 3 givenname: Nick orcidid: 0000-0002-9343-9535 surname: Barnes fullname: Barnes, Nick email: nick.barnes@anu.edu.au organization: School of Computing, Australian National University, Canberra, ACT, Australia |
| BookMark | eNp9kL1PwzAQxS1UJNrCjsQSiTnl7NhxsgEVFKQWOpTZctyL5H7ExXaF-O9xKWJgYHl3w3t3er8B6XWuQ0IuKYwohfpmMZuNGDA6KkByxuGE9GnNaQ4gZS_tgkFeMwpnZBDCCoByAbJPbifothi9Ndm9Nut87t0KTbSuy14wfji_zlrns7mzXczGG7dfJtUh2NYafbCdk9NWbwJe_MwheXt8WIyf8unr5Hl8N81NIWTMm6JCacqGLhlQ0VAmC9pyKSrZIqVaSF1qzWtEqRuJFS8YLusKBTSmTtIWQ3J9vLvz7n2PIaqV2_suvVSs5KmyKGuZXHB0Ge9C8Niqnbdb7T8VBXXgpBIndeCkfjilSPknYmz8rha9tpv_glfHoEXE3z-JOXAQxReowHYd |
| CODEN | ITMUF8 |
| CitedBy_id | crossref_primary_10_1109_TPAMI_2021_3137794 crossref_primary_10_1016_j_jvcir_2024_104353 crossref_primary_10_1109_TMM_2024_3349912 crossref_primary_10_1016_j_knosys_2024_112715 crossref_primary_10_1109_TIP_2024_3486612 crossref_primary_10_3390_s22134878 crossref_primary_10_3390_rs16163045 crossref_primary_10_1016_j_jag_2025_104572 crossref_primary_10_1109_TGRS_2024_3393845 crossref_primary_10_3390_rs16111835 crossref_primary_10_1007_s00371_023_02816_y crossref_primary_10_1371_journal_pone_0314086 crossref_primary_10_1109_TAI_2024_3429050 crossref_primary_10_1016_j_imavis_2024_105396 crossref_primary_10_1109_TMM_2023_3286981 crossref_primary_10_1109_TVCG_2023_3328354 crossref_primary_10_1109_TITS_2022_3198836 crossref_primary_10_1007_s11390_024_3521_x crossref_primary_10_1016_j_patcog_2025_112025 crossref_primary_10_1007_s00371_023_03091_7 crossref_primary_10_1109_TMM_2023_3318327 crossref_primary_10_1145_3679204 crossref_primary_10_3390_app12157384 crossref_primary_10_1109_TMM_2023_3317998 crossref_primary_10_1016_j_neucom_2024_128436 crossref_primary_10_1109_TMM_2023_3312855 crossref_primary_10_1109_TMM_2022_3198318 crossref_primary_10_1109_TIP_2025_3571680 crossref_primary_10_1016_j_neucom_2024_128435 crossref_primary_10_1088_1361_6560_ad953f crossref_primary_10_1016_j_neucom_2025_130201 crossref_primary_10_1109_TMM_2022_3200851 crossref_primary_10_1145_3735560 crossref_primary_10_3390_s25030658 crossref_primary_10_1109_ACCESS_2023_3335607 crossref_primary_10_3390_s23125512 crossref_primary_10_1109_ACCESS_2023_3266340 crossref_primary_10_1007_s11227_025_07766_x crossref_primary_10_3390_s23229042 crossref_primary_10_1109_TMM_2022_3189778 crossref_primary_10_1109_TMM_2024_3521735 crossref_primary_10_1109_TMM_2022_3198011 crossref_primary_10_1109_TMM_2024_3410117 crossref_primary_10_1007_s11760_025_04116_5 crossref_primary_10_1111_exsy_13831 crossref_primary_10_1109_TMM_2024_3374580 crossref_primary_10_1016_j_asoc_2024_111622 crossref_primary_10_1109_ACCESS_2022_3228044 crossref_primary_10_3390_math12233827 crossref_primary_10_3390_robotics12040100 crossref_primary_10_1007_s11227_024_06838_8 crossref_primary_10_3390_s22239488 crossref_primary_10_1109_TGRS_2022_3168555 crossref_primary_10_1109_TMM_2024_3521745 crossref_primary_10_1109_TGRS_2023_3331748 crossref_primary_10_1007_s12652_024_04879_8 crossref_primary_10_1109_ACCESS_2024_3470971 crossref_primary_10_1109_TIM_2023_3320732 crossref_primary_10_3389_frai_2024_1439340 crossref_primary_10_1109_LRA_2022_3224370 crossref_primary_10_3390_electronics13224355 crossref_primary_10_1109_TPAMI_2024_3400402 crossref_primary_10_1016_j_patcog_2025_111351 crossref_primary_10_1109_TMM_2023_3248150 crossref_primary_10_1007_s11831_024_10108_4 crossref_primary_10_1109_TMM_2023_3236212 crossref_primary_10_1109_LRA_2022_3223558 crossref_primary_10_1109_LRA_2023_3301278 crossref_primary_10_1109_TMM_2023_3277281 crossref_primary_10_1007_s11042_024_18658_2 crossref_primary_10_1109_TPAMI_2023_3298711 crossref_primary_10_1016_j_cag_2025_104238 crossref_primary_10_1109_TGRS_2023_3337088 crossref_primary_10_1109_TMM_2024_3443613 crossref_primary_10_1007_s10489_023_04498_4 crossref_primary_10_1016_j_compeleceng_2022_108463 crossref_primary_10_1016_j_neucom_2021_10_098 crossref_primary_10_1109_TMM_2022_3154927 crossref_primary_10_1016_j_displa_2023_102610 crossref_primary_10_1016_j_engappai_2025_111474 crossref_primary_10_1109_ACCESS_2023_3322433 crossref_primary_10_1109_TNNLS_2024_3409891 crossref_primary_10_1109_JAS_2023_123432 crossref_primary_10_1109_LRA_2022_3147907 crossref_primary_10_1109_TMM_2022_3216951 crossref_primary_10_1016_j_knosys_2022_108887 crossref_primary_10_1016_j_compag_2025_110857 crossref_primary_10_1088_1361_6501_ad1fce crossref_primary_10_1016_j_autcon_2025_106387 crossref_primary_10_1016_j_patcog_2024_110624 crossref_primary_10_1109_TIM_2024_3451587 crossref_primary_10_1371_journal_pone_0329146 crossref_primary_10_7717_peerj_cs_1738 crossref_primary_10_1016_j_cag_2025_104221 crossref_primary_10_1109_TMM_2023_3275366 crossref_primary_10_1109_TMM_2024_3412330 crossref_primary_10_1007_s00530_023_01100_2 crossref_primary_10_1016_j_neucom_2024_127940 crossref_primary_10_1109_TCDS_2024_3403900 crossref_primary_10_1155_2022_5417440 crossref_primary_10_1016_j_cag_2025_104222 crossref_primary_10_1109_JSEN_2024_3436834 crossref_primary_10_1109_TMM_2025_3535341 crossref_primary_10_1016_j_patrec_2025_04_037 crossref_primary_10_1108_DTA_06_2022_0243 crossref_primary_10_1109_TCSVT_2025_3553537 crossref_primary_10_1109_ACCESS_2024_3442928 crossref_primary_10_1007_s11263_024_02248_8 crossref_primary_10_3390_machines10070517 crossref_primary_10_1109_ACCESS_2025_3525739 crossref_primary_10_1109_TMM_2023_3314973 crossref_primary_10_1016_j_jvcir_2023_103769 crossref_primary_10_1109_TIM_2025_3551981 crossref_primary_10_1016_j_patrec_2024_05_016 crossref_primary_10_1016_j_engappai_2024_109224 crossref_primary_10_1109_TIP_2023_3333191 crossref_primary_10_1109_TMM_2023_3304892 crossref_primary_10_1109_TMM_2024_3358695 crossref_primary_10_1016_j_engappai_2025_111417 crossref_primary_10_1109_TMM_2023_3304896 crossref_primary_10_1109_TPAMI_2023_3238516 crossref_primary_10_1109_ACCESS_2023_3323428 crossref_primary_10_1007_s00371_025_04171_6 crossref_primary_10_1109_TGRS_2023_3336053 crossref_primary_10_1109_TMM_2023_3321535 crossref_primary_10_1007_s00371_024_03380_9 crossref_primary_10_1109_TCSVT_2023_3263952 crossref_primary_10_3233_JIFS_231997 crossref_primary_10_1109_TVCG_2025_3591189 crossref_primary_10_3390_s24237861 crossref_primary_10_1016_j_imavis_2023_104890 crossref_primary_10_1016_j_eswa_2023_122438 crossref_primary_10_1016_j_asoc_2025_112801 crossref_primary_10_1016_j_ins_2025_122474 crossref_primary_10_1016_j_neucom_2024_128413 crossref_primary_10_1016_j_cagd_2024_102311 |
| Cites_doi | 10.1109/ICCV.2019.00167 10.1111/j.1467-8659.2007.01016.x 10.1145/777792.777840 10.1145/3326362 10.1109/ICCV.2017.99 10.1145/2980179.2980238 10.1109/CVPR.2019.01272 10.1109/TPAMI.2016.2644615 10.1109/CVPR.2018.00979 10.1109/CVPR.2019.00326 10.1109/CVPR.2015.7298655 10.1109/JRA.1987.1087115 10.1109/CVPR.2018.00484 10.1109/TMM.2019.2963592 10.1109/CVPR42600.2020.01297 10.1109/ICCV.2019.00937 10.1109/ICCV.2019.00730 10.1109/TPAMI.2020.3005434 10.1007/978-3-030-01240-3_17 10.1109/CVPR.2018.00179 10.1109/LRA.2018.2850061 10.1109/CVPRW.2019.00256 10.1109/CVPR.2015.7298965 10.1109/CVPR.2018.00029 10.1109/IROS.2015.7353481 10.1145/3197517.3201301 10.1109/CVPR.2019.01054 10.1109/CVPR42600.2020.00563 10.1109/ROBOT.2009.5152473 10.1109/ICCV.2019.00325 10.1145/3343031.3350960 10.1109/ICCV.2019.00069 10.1109/CVPR.2009.5206848 10.1145/3240508.3240621 10.1109/CVPR42600.2020.01112 10.1109/TMM.2020.2976627 10.1109/CVPR.2018.00243 10.1117/1.1631921 10.1109/ICCV.2015.114 10.1109/CVPR.2018.00745 10.1109/ICCV.2019.00534 10.1109/TMM.2018.2859591 10.1109/ICRA40945.2020.9197503 10.1109/CVPR.2017.11 10.1109/CVPR.2018.00439 10.1109/TMM.2013.2286580 10.1109/CVPR.2019.00910 10.1109/CVPRW.2019.00169 10.1109/CVPR.2015.7298801 10.1016/j.patcog.2020.107446 10.1609/aaai.v33i01.33018778 10.1016/j.neucom.2021.01.095 10.1109/ICCV.2019.00812 10.1109/ICRA.2018.8461095 10.1145/1057432.1057435 10.1109/TMM.2016.2612761 10.1109/ICCV.2019.00651 10.1007/s11263-015-0816-y 10.1109/WACV45572.2020.9093430 10.1007/s11069-010-9634-2 10.1109/CVPR42600.2020.00641 10.1145/3072959.3073608 10.1109/TVCG.2010.261 10.1007/978-3-030-01237-3_6 10.1038/nature01254 10.1109/CVPR.2018.00813 10.1007/978-3-030-01234-2_1 10.1109/CVPR.2016.512 |
| 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 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TMM.2021.3074240 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore : IEEE Electronic Library (IEL) [unlimited simultaenous users] 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 |
| DatabaseTitle | 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 |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1941-0077 |
| EndPage | 1955 |
| ExternalDocumentID | 10_1109_TMM_2021_3074240 9410405 |
| Genre | orig-research |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK 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 IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TN5 VH1 ZY4 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c357t-b38e7c6b1d2015b12731f47587fe11a57a6aa49ee7ab7e8432ed98e50bc950bf3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 189 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000778959200013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1520-9210 |
| IngestDate | Mon Jun 30 06:57:08 EDT 2025 Tue Nov 18 22:28:52 EST 2025 Sat Nov 29 03:10:07 EST 2025 Wed Aug 27 02:40:51 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c357t-b38e7c6b1d2015b12731f47587fe11a57a6aa49ee7ab7e8432ed98e50bc950bf3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-0692-8411 0000-0002-9343-9535 0000-0001-9958-180X |
| PQID | 2647425697 |
| PQPubID | 75737 |
| PageCount | 13 |
| ParticipantIDs | crossref_primary_10_1109_TMM_2021_3074240 ieee_primary_9410405 proquest_journals_2647425697 crossref_citationtrail_10_1109_TMM_2021_3074240 |
| PublicationCentury | 2000 |
| PublicationDate | 20220000 2022-00-00 20220101 |
| PublicationDateYYYYMMDD | 2022-01-01 |
| PublicationDate_xml | – year: 2022 text: 20220000 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE transactions on multimedia |
| PublicationTitleAbbrev | TMM |
| 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 ref57 ref12 ref56 ref15 ref59 ref14 ref53 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 Krtgen (ref45) 2003; 3 ref51 ref50 ref46 Vaswani (ref34) 2017 ref42 ref41 ref44 HKUST-VGD (ref72) 2020 ref43 ref49 ref8 Qi (ref47) 2017 ref7 ref9 ref4 ref3 ref6 ref5 Loshchilov (ref63) 2016 ref40 ref35 ref79 ref78 ref37 ref36 ref31 ref75 ref30 ref74 ref33 ref77 ref32 ref2 ref1 ref39 Li (ref48) 2018; 31 ref38 Qi (ref22) 2017 Velikovi (ref61) 2017 ref71 ref70 Kang (ref58) 2019; 16 ref73 ref24 ref68 ref23 ref67 ref26 ref25 ref69 ref20 ref64 ref66 ref21 ref65 ref28 ref27 ref29 Vosselman (ref18) 2001; 34 ref60 ref62 Chang (ref76) 2015 |
| References_xml | – ident: ref12 doi: 10.1109/ICCV.2019.00167 – ident: ref15 doi: 10.1111/j.1467-8659.2007.01016.x – ident: ref43 doi: 10.1145/777792.777840 – ident: ref49 doi: 10.1145/3326362 – ident: ref65 doi: 10.1109/ICCV.2017.99 – ident: ref75 doi: 10.1145/2980179.2980238 – ident: ref56 doi: 10.1109/CVPR.2019.01272 – year: 2020 ident: ref72 article-title: 3D Scene understanding benchmark – ident: ref62 doi: 10.1109/TPAMI.2016.2644615 – ident: ref26 doi: 10.1109/CVPR.2018.00979 – ident: ref37 doi: 10.1109/CVPR.2019.00326 – ident: ref77 doi: 10.1109/CVPR.2015.7298655 – start-page: 5998 volume-title: NeurIPS year: 2017 ident: ref34 article-title: Attention is all you need – year: 2015 ident: ref76 article-title: ShapeNet: An information-rich 3D model repository – ident: ref28 doi: 10.1109/JRA.1987.1087115 – ident: ref40 doi: 10.1109/CVPR.2018.00484 – year: 2016 ident: ref63 article-title: SGDR: Stochastic gradient descent with warm restarts – ident: ref5 doi: 10.1109/TMM.2019.2963592 – ident: ref14 doi: 10.1109/CVPR42600.2020.01297 – ident: ref78 doi: 10.1109/ICCV.2019.00937 – ident: ref33 doi: 10.1109/ICCV.2019.00730 – ident: ref19 doi: 10.1109/TPAMI.2020.3005434 – ident: ref73 doi: 10.1007/978-3-030-01240-3_17 – ident: ref31 doi: 10.1109/CVPR.2018.00179 – ident: ref70 doi: 10.1109/LRA.2018.2850061 – ident: ref32 doi: 10.1109/CVPRW.2019.00256 – start-page: 652 volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. year: 2017 ident: ref22 article-title: PointNet: Deep learning on point sets for 3D classification and segmentation – ident: ref79 doi: 10.1109/CVPR.2015.7298965 – ident: ref9 doi: 10.1109/CVPR.2018.00029 – ident: ref21 doi: 10.1109/IROS.2015.7353481 – ident: ref66 doi: 10.1145/3197517.3201301 – ident: ref59 doi: 10.1109/CVPR.2019.01054 – year: 2017 ident: ref61 article-title: Graph attention networks – ident: ref46 doi: 10.1109/CVPR42600.2020.00563 – ident: ref17 doi: 10.1109/ROBOT.2009.5152473 – ident: ref39 doi: 10.1109/ICCV.2019.00325 – ident: ref42 doi: 10.1145/3343031.3350960 – ident: ref74 doi: 10.1109/ICCV.2019.00069 – ident: ref8 doi: 10.1109/CVPR.2009.5206848 – volume: 31 start-page: 820 year: 2018 ident: ref48 article-title: PoinTCNN: Convolution on X-transformed points publication-title: NeurIPS – ident: ref69 doi: 10.1145/3240508.3240621 – ident: ref27 doi: 10.1109/CVPR42600.2020.01112 – volume: 34 start-page: 37 issue: 3/W4 year: 2001 ident: ref18 article-title: 3D building model reconstruction from point clouds and ground plans, publication-title: Int. Archives Photogrammetry Remote Sensing Spatial Inform. Sciences – ident: ref4 doi: 10.1109/TMM.2020.2976627 – start-page: 5099 volume-title: NeurIPS year: 2017 ident: ref47 article-title: PointNet++: Deep hierarchical feature learning on point sets in a metric space – ident: ref53 doi: 10.1109/CVPR.2018.00243 – ident: ref6 doi: 10.1117/1.1631921 – ident: ref20 doi: 10.1109/ICCV.2015.114 – ident: ref36 doi: 10.1109/CVPR.2018.00745 – ident: ref67 doi: 10.1109/ICCV.2019.00534 – ident: ref3 doi: 10.1109/TMM.2018.2859591 – ident: ref50 doi: 10.1109/ICRA40945.2020.9197503 – ident: ref64 doi: 10.1109/CVPR.2017.11 – ident: ref10 doi: 10.1109/CVPR.2018.00439 – ident: ref1 doi: 10.1109/TMM.2013.2286580 – ident: ref23 doi: 10.1109/CVPR.2019.00910 – ident: ref54 doi: 10.1109/CVPRW.2019.00169 – ident: ref71 doi: 10.1109/CVPR.2015.7298801 – ident: ref41 doi: 10.1016/j.patcog.2020.107446 – ident: ref57 doi: 10.1609/aaai.v33i01.33018778 – ident: ref60 doi: 10.1016/j.neucom.2021.01.095 – ident: ref38 doi: 10.1109/ICCV.2019.00812 – volume: 3 start-page: 5 volume-title: Proc. 7th Central Eur. Seminar Comput. Graphics year: 2003 ident: ref45 article-title: 3D Shape matching with 3D shape contexts – ident: ref11 doi: 10.1109/ICRA.2018.8461095 – ident: ref16 doi: 10.1145/1057432.1057435 – volume: 16 start-page: 35 issue: 2 year: 2019 ident: ref58 article-title: PyramNet: Point cloud pyramid attention network and graph embedding module for classification and segmentation publication-title: Aust. J. Intell. Inf. Process. Syst. – ident: ref2 doi: 10.1109/TMM.2016.2612761 – ident: ref68 doi: 10.1109/ICCV.2019.00651 – ident: ref51 doi: 10.1007/s11263-015-0816-y – ident: ref55 doi: 10.1109/WACV45572.2020.9093430 – ident: ref7 doi: 10.1007/s11069-010-9634-2 – ident: ref13 doi: 10.1109/CVPR42600.2020.00641 – ident: ref24 doi: 10.1145/3072959.3073608 – ident: ref44 doi: 10.1109/TVCG.2010.261 – ident: ref25 doi: 10.1007/978-3-030-01237-3_6 – ident: ref29 doi: 10.1038/nature01254 – ident: ref35 doi: 10.1109/CVPR.2018.00813 – ident: ref52 doi: 10.1007/978-3-030-01234-2_1 – ident: ref30 doi: 10.1109/CVPR.2016.512 |
| SSID | ssj0014507 |
| Score | 2.689075 |
| Snippet | As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1943 |
| SubjectTerms | 3D Deep Learning Attention Mechanism Classification Error correction Error-correcting Feedback Feature extraction Feature maps Geometric Features Geometry Microbalances Point Cloud Classification Redundancy Shape Task analysis Three-dimensional displays Visualization |
| Title | Geometric Back-Projection Network for Point Cloud Classification |
| URI | https://ieeexplore.ieee.org/document/9410405 https://www.proquest.com/docview/2647425697 |
| Volume | 24 |
| WOSCitedRecordID | wos000778959200013&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 customDbUrl: eissn: 1941-0077 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014507 issn: 1520-9210 databaseCode: RIE dateStart: 19990101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6VigEGCi2IQkEeWJBImzQPxxtQURho1aGgbpHtOBKiJKhN-f2cnYcqgZBYogy-JLrPl3v57gCumM_jRHIbBUkklm5AZ4VeaFscbQ9UH1LYJoP_-kyn03CxYLMG3NS1MEopc_hM9fWtyeXHmdzoUNmAeeg86IalO5QGRa1WnTHwfFMajeoI34t-TJWStNlgPpmgIzh0-q52BHWYY0sFmZkqP37ERruMW__7rkM4KK1IclfAfgQNlbahVU1oIKXAtmF_q91gB24fVfahJ2hJcs_luzUrojCIDJkWp8EJmrBklr2lORkts01MzMxMfZrIAHgML-OH-ejJKicoWNL1aW4JN1RUBsKJUc_7wkFbxUk8dBFoohyH-5QHnHtMKcoFVaHnDlXMQuXbQjK8JO4JNNMsVadAvEQxNFY4PpEhRSwCP0YJljoNJ5ww6cKgYmoky_biesrFMjJuhs0ihCHSMEQlDF24rik-i9Yaf6ztaLbX60qOd6FX4RaVsreO0MRDGj9g9Ox3qnPYG-oiBhNI6UEzX23UBezKr_xtvbo02-obFjzIkQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT8IwEL8QNVEfREEjitoHX0wcbKxl65tKRIxAeEDD29J2XUJEZvjw7_faDUKiMfFl2UNvW-7X23317gCuORNxooSLgiQTxzSgc0Iauo5A2wPVh5KuzeC_dYN-PxyN-KAAt-taGK21PXyma-bW5vLjVC1NqKzOKToPpmHpNqO04WbVWuucAWW2OBoVEr4ZPZlVUtLl9WGvh65gw6v5xhU0gY4NJWSnqvz4FVv90i7-78sO4SC3I8l9BvwRFPS0BMXVjAaSi2wJ9jcaDpbh7kmnH2aGliIPQr07gywOg9iQfnYenKARSwbpeLogrUm6jImdmmnOE1kIj-G1_ThsdZx8hoKjfBYsHOmHOlBN6cWo6Zn00FrxEopOQpBozxMsEE0hKNc6EDLQIfUbOuahZq5UHC-JfwJb03SqT4HQRHM0VwQ-kSNFLJssRhlWJhEnvTCpQH3F1EjlDcbNnItJZB0Nl0cIQ2RgiHIYKnCzpvjMmmv8sbZs2L5el3O8AtUVblEuffMIjTykYU0enP1OdQW7nWGvG3Wf-y_nsNcwJQ02rFKFrcVsqS9gR30txvPZpd1i37DDy9g |
| 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=Geometric+Back-Projection+Network+for+Point+Cloud+Classification&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Qiu%2C+Shi&rft.au=Anwar%2C+Saeed&rft.au=Barnes%2C+Nick&rft.date=2022&rft.pub=IEEE&rft.issn=1520-9210&rft.volume=24&rft.spage=1943&rft.epage=1955&rft_id=info:doi/10.1109%2FTMM.2021.3074240&rft.externalDocID=9410405 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-9210&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-9210&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-9210&client=summon |