Fuzzy Integral-Based CNN Classifier Fusion for 3D Skeleton Action Recognition
Action recognition based on skeleton key joints has gained popularity due to its cost effectiveness and low complexity. Existing Convolutional Neural Network (CNN) based models mostly fail to capture various aspects of the skeleton sequence. To this end, four feature representations, which capture c...
Saved in:
| Published in | IEEE transactions on circuits and systems for video technology Vol. 31; no. 6; pp. 2206 - 2216 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.06.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Action recognition based on skeleton key joints has gained popularity due to its cost effectiveness and low complexity. Existing Convolutional Neural Network (CNN) based models mostly fail to capture various aspects of the skeleton sequence. To this end, four feature representations, which capture complementary characteristics of the sequence of key joints, are extracted with novel contribution of features estimated from angular information, and kinematics of the human actions. Single channel grayscale images are used to encode these features for classification using four CNNs, with the complementary nature verified through Kullback-Leibler (KL) and Jensen-Shannon (JS) divergences. As opposed to straightforward classifier combination generally used in existing literature, fuzzy fusion through the Choquet integral leverages the degree of uncertainty of decision scores obtained from four CNNs. Experimental results support the efficacy of fuzzy combination of CNNs to adaptively generate final decision score based upon confidence of each information source. Impressive results on the challenging UTD-MHAD, HDM05, G3D, and NTU RGB+D 60 and 120 datasets demonstrate the effectiveness of the proposed method. The source code for our method is available at https://github.com/theavicaster/fuzzy-integral-cnn-fusion-3d-har |
|---|---|
| AbstractList | Action recognition based on skeleton key joints has gained popularity due to its cost effectiveness and low complexity. Existing Convolutional Neural Network (CNN) based models mostly fail to capture various aspects of the skeleton sequence. To this end, four feature representations, which capture complementary characteristics of the sequence of key joints, are extracted with novel contribution of features estimated from angular information, and kinematics of the human actions. Single channel grayscale images are used to encode these features for classification using four CNNs, with the complementary nature verified through Kullback-Leibler (KL) and Jensen-Shannon (JS) divergences. As opposed to straightforward classifier combination generally used in existing literature, fuzzy fusion through the Choquet integral leverages the degree of uncertainty of decision scores obtained from four CNNs. Experimental results support the efficacy of fuzzy combination of CNNs to adaptively generate final decision score based upon confidence of each information source. Impressive results on the challenging UTD-MHAD, HDM05, G3D, and NTU RGB+D 60 and 120 datasets demonstrate the effectiveness of the proposed method. The source code for our method is available at https://github.com/theavicaster/fuzzy-integral-cnn-fusion-3d-har |
| Author | Singh, Pawan Kumar Banerjee, Avinandan Sarkar, Ram |
| Author_xml | – sequence: 1 givenname: Avinandan orcidid: 0000-0003-3536-9847 surname: Banerjee fullname: Banerjee, Avinandan email: avinandanbanerjee99@gmail.com organization: Department of Information Technology, Jadavpur University, Kolkata, India – sequence: 2 givenname: Pawan Kumar orcidid: 0000-0002-9598-7981 surname: Singh fullname: Singh, Pawan Kumar email: pawankrsingh@ieee.org organization: Department of Information Technology, Jadavpur University, Kolkata, India – sequence: 3 givenname: Ram orcidid: 0000-0001-8813-4086 surname: Sarkar fullname: Sarkar, Ram email: rsarkar@ieee.org organization: Department of Computer Science and Engineering, Jadavpur University, Kolkata, India |
| BookMark | eNp9kD9PwzAQxS1UJNrCF4AlEnOK_9SxPZZAoVIpEi2sluOeq5SQFDsZ2k9PQhEDA9O9O73f3ekNUK-sSkDokuARIVjdrNLl22pEMcUjhomiip2gPuFcxpRi3ms15iSWlPAzNAhhizEZy7Hoo6dpczjso1lZw8abIr41AdZRulhEaWFCyF0OPpo2Ia_KyFU-YnfR8h0KqNt-Yutu_AK22pR5p8_RqTNFgIufOkSv0_tV-hjPnx9m6WQeW6p4HVNHheCcqkxZJgwGm7GMuWycYcMSjsmaySyhCQBNzFpJbBKhLFDpsBDUSTZE18e9O199NhBqva0aX7YnNeUskYkkqnPJo8v6KgQPTtu8Nt2ftTd5oQnWXXj6Ozzdhad_wmtR-gfd-fzD-P3_0NURygHgF1BECCIw-wLSdnu7 |
| CODEN | ITCTEM |
| CitedBy_id | crossref_primary_10_1109_TCDS_2022_3204905 crossref_primary_10_1109_TPAMI_2022_3183112 crossref_primary_10_3390_electronics13234733 crossref_primary_10_1007_s40747_025_01807_x crossref_primary_10_1007_s11042_023_17529_6 crossref_primary_10_1007_s00530_024_01604_5 crossref_primary_10_1007_s10994_022_06141_8 crossref_primary_10_1016_j_cmpb_2022_106776 crossref_primary_10_1109_TCSVT_2022_3142771 crossref_primary_10_1109_THMS_2024_3467334 crossref_primary_10_3390_diagnostics12051173 crossref_primary_10_1016_j_bspc_2023_104873 crossref_primary_10_3389_fnbot_2024_1439188 crossref_primary_10_1016_j_eswa_2021_116287 crossref_primary_10_1109_TCE_2024_3420936 crossref_primary_10_3389_fnbot_2025_1482281 crossref_primary_10_1109_TFUZZ_2022_3206504 crossref_primary_10_1016_j_neucom_2022_07_046 crossref_primary_10_1109_TCSVT_2022_3193574 crossref_primary_10_1109_TCSVT_2022_3156588 crossref_primary_10_1016_j_measurement_2024_115682 crossref_primary_10_1109_TAI_2023_3318575 crossref_primary_10_1007_s11042_024_20475_6 crossref_primary_10_1109_TCSVT_2023_3284493 crossref_primary_10_1007_s00521_023_08814_4 crossref_primary_10_1109_TCSVT_2023_3240472 crossref_primary_10_1007_s00034_024_02815_x crossref_primary_10_1007_s11042_021_10753_y crossref_primary_10_3390_app12010004 crossref_primary_10_1109_TFUZZ_2024_3434589 crossref_primary_10_1007_s11760_023_02923_2 crossref_primary_10_1038_s41598_022_27192_w crossref_primary_10_1016_j_cviu_2024_104076 crossref_primary_10_1016_j_engappai_2022_105702 crossref_primary_10_1007_s11831_021_09681_9 crossref_primary_10_3390_electronics12214466 crossref_primary_10_1109_TCSVT_2021_3100128 crossref_primary_10_1109_TCSVT_2023_3259430 crossref_primary_10_1007_s11042_021_11319_8 crossref_primary_10_1007_s40815_022_01307_x crossref_primary_10_1007_s10489_022_04302_9 crossref_primary_10_1016_j_neucom_2025_129820 crossref_primary_10_1007_s40192_021_00210_x crossref_primary_10_1155_2022_9416467 crossref_primary_10_1109_TCSVT_2022_3217763 crossref_primary_10_1109_TCSVT_2022_3219864 crossref_primary_10_3390_s23020734 crossref_primary_10_1109_TCSVT_2022_3178430 crossref_primary_10_3390_electronics12010117 crossref_primary_10_1016_j_asoc_2025_112797 crossref_primary_10_1109_TFUZZ_2024_3387429 crossref_primary_10_1109_ACCESS_2024_3389499 crossref_primary_10_3390_app12189229 crossref_primary_10_1109_JSEN_2021_3079366 crossref_primary_10_1016_j_asoc_2023_110732 crossref_primary_10_1007_s00521_022_07514_9 crossref_primary_10_1109_TCSVT_2024_3386553 crossref_primary_10_1109_TFUZZ_2022_3152106 crossref_primary_10_1016_j_jmsy_2022_11_009 crossref_primary_10_1109_TCSVT_2022_3222226 crossref_primary_10_1038_s41598_022_18463_7 crossref_primary_10_1016_j_jvcir_2023_103953 crossref_primary_10_1109_JBHI_2024_3411658 crossref_primary_10_1007_s11042_022_11942_z crossref_primary_10_1016_j_eswa_2024_124917 crossref_primary_10_3390_s22020671 crossref_primary_10_1007_s13042_023_01948_w crossref_primary_10_1145_3633785 crossref_primary_10_1145_3715917 crossref_primary_10_1109_TAI_2023_3323272 crossref_primary_10_1109_TCDS_2022_3171550 crossref_primary_10_1109_TCSVT_2022_3194350 crossref_primary_10_4103_bbrj_bbrj_56_24 crossref_primary_10_1007_s00371_022_02461_x crossref_primary_10_1155_2022_4667640 crossref_primary_10_1016_j_eswa_2023_122314 crossref_primary_10_1109_TCSVT_2023_3250646 crossref_primary_10_1007_s10489_022_03968_5 crossref_primary_10_1109_TIM_2023_3314815 crossref_primary_10_1109_TSMC_2023_3250120 |
| Cites_doi | 10.1109/TCSVT.2018.2864148 10.1109/CVPR.2017.502 10.1109/CVPR.2016.484 10.1016/j.ins.2019.10.047 10.1109/TIE.2018.2881943 10.1109/ICIP.2015.7350781 10.1109/TPAMI.2019.2916873 10.1016/0165-0114(89)90194-2 10.1167/6.8.6 10.1016/j.patrec.2004.09.024 10.1109/TFUZZ.2016.2598362 10.1109/TCSVT.2020.3015051 10.1109/ICHI.2016.100 10.1109/CVPR.2017.137 10.1109/SIBGRAPI.2019.00011 10.1109/TCSVT.2018.2879913 10.1109/LSP.2017.2678539 10.1109/CVPRW.2012.6239175 10.1109/ACPR.2015.7486569 10.1109/CRV.2019.00015 10.1109/21.57289 10.1109/ICPR.2014.340 10.1109/TCSVT.2019.2914137 10.1109/ACCESS.2017.2778011 10.1109/CVPR.2019.00792 10.1109/TII.2019.2910876 10.1201/9781351003827-5 10.1007/s00530-020-00677-2 10.1016/B978-1-4832-1450-4.50027-4 10.1109/TIP.2018.2812099 10.1109/ICASSP40776.2020.9054392 10.1016/j.cviu.2014.12.005 10.1016/j.ymssp.2008.07.012 10.1109/CVPR42600.2020.00026 10.1145/2964284.2967191 10.1109/CVPR.2018.00127 10.1109/CVPR.2017.391 10.24963/ijcai.2018/109 |
| 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 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TCSVT.2020.3019293 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) 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 Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2205 |
| EndPage | 2216 |
| ExternalDocumentID | 10_1109_TCSVT_2020_3019293 9177170 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: PURSE-II and UPE-II, Jadavpur University projects funderid: 10.13039/100009589 – fundername: DST, Govt. of India grantid: EMR/2016/007213 |
| 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 ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION RIG 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c295t-2f2775529b9c37a0ecb3b3fb4b0a36501d38b626ee26ad980a679ce28f0772f83 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Mon Jun 30 04:13:24 EDT 2025 Tue Jul 01 00:41:14 EDT 2025 Thu Apr 24 23:08:23 EDT 2025 Wed Aug 27 02:29:53 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| 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-c295t-2f2775529b9c37a0ecb3b3fb4b0a36501d38b626ee26ad980a679ce28f0772f83 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-3536-9847 0000-0002-9598-7981 0000-0001-8813-4086 |
| PQID | 2536868198 |
| PQPubID | 85433 |
| PageCount | 11 |
| ParticipantIDs | crossref_citationtrail_10_1109_TCSVT_2020_3019293 ieee_primary_9177170 crossref_primary_10_1109_TCSVT_2020_3019293 proquest_journals_2536868198 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021-06-01 |
| PublicationDateYYYYMMDD | 2021-06-01 |
| PublicationDate_xml | – month: 06 year: 2021 text: 2021-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on circuits and systems for video technology |
| PublicationTitleAbbrev | TCSVT |
| 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 | ref13 ref15 memmesheimer (ref39) 2020 ref14 ref10 ref17 ref16 ref18 huang (ref42) 2018 müller (ref33) 2007 zhu (ref37) 2018 choi (ref3) 2007 ref46 ref45 ref48 ref47 ref41 ref44 ref43 ref49 ref8 ref7 ref4 ref6 ref5 li (ref24) 2018 li (ref19) 2017 ref35 ref34 ref36 ref31 ref30 ref32 ref2 ref1 shahroudy (ref9) 2016 ref38 huang (ref40) 2017 thakkar (ref23) 2018 ref25 ref20 ref22 sugeno (ref26) 1993 ref21 ref28 ref27 ref29 song (ref11) 2017 jiang (ref12) 2020; 30 |
| References_xml | – ident: ref18 doi: 10.1109/TCSVT.2018.2864148 – ident: ref7 doi: 10.1109/CVPR.2017.502 – ident: ref45 doi: 10.1109/CVPR.2016.484 – year: 2007 ident: ref33 article-title: Documentation mocap database HDM05 – ident: ref21 doi: 10.1016/j.ins.2019.10.047 – ident: ref8 doi: 10.1109/TIE.2018.2881943 – ident: ref32 doi: 10.1109/ICIP.2015.7350781 – ident: ref34 doi: 10.1109/TPAMI.2019.2916873 – start-page: 585 year: 2017 ident: ref19 article-title: Skeleton-based action recognition using LSTM and CNN publication-title: Proc IEEE Int Conf Multimedia Expo Workshops (ICMEW) – ident: ref28 doi: 10.1016/0165-0114(89)90194-2 – ident: ref4 doi: 10.1167/6.8.6 – ident: ref30 doi: 10.1016/j.patrec.2004.09.024 – ident: ref31 doi: 10.1109/TFUZZ.2016.2598362 – ident: ref25 doi: 10.1109/TCSVT.2020.3015051 – ident: ref1 doi: 10.1109/ICHI.2016.100 – ident: ref41 doi: 10.1109/CVPR.2017.137 – start-page: 8561 year: 2018 ident: ref24 article-title: Spatio-temporal graph routing for skeleton-based action recognition publication-title: Proc 32nd AAAI Conf Artif Intell – ident: ref47 doi: 10.1109/SIBGRAPI.2019.00011 – ident: ref16 doi: 10.1109/TCSVT.2018.2879913 – ident: ref15 doi: 10.1109/LSP.2017.2678539 – ident: ref2 doi: 10.1109/CVPRW.2012.6239175 – ident: ref13 doi: 10.1109/ACPR.2015.7486569 – ident: ref38 doi: 10.1109/CRV.2019.00015 – ident: ref27 doi: 10.1109/21.57289 – ident: ref43 doi: 10.1109/ICPR.2014.340 – start-page: 1010 year: 2016 ident: ref9 article-title: NTU RGB+D: A large scale dataset for 3D human activity analysis publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) – start-page: 4263 year: 2017 ident: ref11 article-title: An end-to-end spatio-temporal attention model for human action recognition from skeleton data publication-title: Proc 31st AAAI Conf Artif Intell – volume: 30 start-page: 2129 year: 2020 ident: ref12 article-title: Action recognition scheme based on skeleton representation with DS-LSTM network publication-title: IEEE Trans Circuits Syst Video Technol doi: 10.1109/TCSVT.2019.2914137 – ident: ref6 doi: 10.1109/ACCESS.2017.2778011 – ident: ref35 doi: 10.1109/CVPR.2019.00792 – year: 2018 ident: ref37 article-title: Action machine: Rethinking action recognition in trimmed videos publication-title: arXiv 1812 05770 – ident: ref20 doi: 10.1109/TII.2019.2910876 – ident: ref5 doi: 10.1201/9781351003827-5 – ident: ref49 doi: 10.1007/s00530-020-00677-2 – start-page: 251 year: 1993 ident: ref26 article-title: Fuzzy measures and fuzzy integrals-A survey publication-title: Readings in Fuzzy Sets for Intelligent Systems doi: 10.1016/B978-1-4832-1450-4.50027-4 – start-page: 1 year: 2017 ident: ref40 article-title: A Riemannian network for SPD matrix learning publication-title: Proc AAAI Conf Artif Intell – ident: ref46 doi: 10.1109/TIP.2018.2812099 – ident: ref22 doi: 10.1109/ICASSP40776.2020.9054392 – year: 2020 ident: ref39 article-title: Gimme signals: Discriminative signal encoding for multimodal activity recognition publication-title: arXiv 2003 06156 – ident: ref44 doi: 10.1016/j.cviu.2014.12.005 – ident: ref29 doi: 10.1016/j.ymssp.2008.07.012 – start-page: 112 year: 2007 ident: ref3 article-title: A view-based real-time human action recognition system as an interface for human computer interaction publication-title: Proc Int Conf Virtual Syst MultiMedia – ident: ref48 doi: 10.1109/CVPR42600.2020.00026 – ident: ref14 doi: 10.1145/2964284.2967191 – ident: ref36 doi: 10.1109/CVPR.2018.00127 – start-page: 270 year: 2018 ident: ref23 article-title: Part-based graph convolutional network for action recognition publication-title: Proc Brit Mach Vis Conf (BMVC) – start-page: 1 year: 2018 ident: ref42 article-title: Building deep networks on grassmann manifolds publication-title: Proc 32nd AAAI Conf Artif Intell – ident: ref10 doi: 10.1109/CVPR.2017.391 – ident: ref17 doi: 10.24963/ijcai.2018/109 |
| SSID | ssj0014847 |
| Score | 2.6028624 |
| Snippet | Action recognition based on skeleton key joints has gained popularity due to its cost effectiveness and low complexity. Existing Convolutional Neural Network... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2206 |
| SubjectTerms | 3D skeleton Action recognition Artificial neural networks Choquet integral Classifiers convolutional neural network Cost effectiveness Data mining Feature extraction fuzzy fusion Image classification Image coding Integrals Joints (anatomy) Kinematics Recognition Skeleton Source code Three-dimensional displays Two dimensional displays |
| Title | Fuzzy Integral-Based CNN Classifier Fusion for 3D Skeleton Action Recognition |
| URI | https://ieeexplore.ieee.org/document/9177170 https://www.proquest.com/docview/2536868198 |
| Volume | 31 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV05T8MwFLaACQZuRKEgD2yQktg57BEKVUFqByiILYovCbVKESQD_fU8O4e4hNgy2JL1nuP3fe9E6CSMMmJ4YDyZ2TCjUsLjSgeeMtLnTIvEaOvQH43j4UN4-xQ9LaGzthZGa-2Sz3TPfrpYvprL0rrKzoFaAPsAgr4MxK2q1WojBiFzw8QALgQeAzvWFMj4_HzSv3-cABUkwFAtouH0ixFyU1V-PMXOvgw20Kg5WZVWMu2VhejJxbemjf89-iZar4EmvqhuxhZa0vk2WvvUfnAHjQblYvGOb6qOETPvEiyawv3xGLtRmc8GTCYelNafhgHbYnqF76dgpgAu4gtXD4Hvmvyjeb6LHgbXk_7Qq8creJLwqPCIIUkSRYQLLmmS-VoKKqgRofAzCsAtUJQJ4DtakzhTnPlZnHCpCTM-QHLD6B5ayee53kc4UgmJGTwGKkxCZTGfCo0OidAiE0aaDgoaeaey7j1uR2DMUsdBfJ46HaVWR2mtow46bfe8VJ03_ly9Y4Xerqzl3UHdRq1p_XO-pSSiMYsBCrGD33cdolViU1ecs6WLVorXUh8B9ijEsbt0H3FX1PI |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwzV1LbxMxEB6VcgAOFCiIQAEf4IQ23bX3YR96aFOihDY50BT1tqztsYRaJYhmhZrfwl_hv3Xs3Y14iVslbnuwLa3n08w343kAvE6zijuVuMhU_pnRWh0pi0lknYmVRF049AH9yTQfnabvz7KzDfi-roVBxJB8hn3_Gd7y7cLUPlS2S64FeR9xm0J5hFffyEG73BsfkjTfcD58NxuMonaGQGS4ypYRd7wosowrrYwoqhiNFlo4neq4EsROEiukJlKPyPPKKhlXeaEMculi4p1OCjr3FtwmnpHxpjps_UaRyjC-jAhKEkmynF1JTqx2Z4OTjzNyPjn5xJ5DKfGL2QtzXP5Q_sGiDbfgR3cXTSLLeb9e6r5Z_dYm8n-9rAdwv6XSbL_B_kPYwPkjuPdTg8VtmAzr1eqKjZueGBfRAdlsywbTKQvDQD87IgVsWPuIISP2zsQhOzknQ0yEmO2Hig_2ocuwWswfw-mN_M8T2Jwv5vgUWGYLnktSdzYtUutZrU0dplyjrrQzrgdJJ9_StN3V_ZCPizJ4WbEqAyZKj4myxUQP3q73fGl6i_xz9bYX8nplK98e7HQwKlv1c1nyTOQyJ7Inn_191yu4M5pNjsvj8fToOdzlPlEnhJZ2YHP5tcYXxLSW-mUAPINPNw2aawXaMbc |
| 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=Fuzzy+Integral-Based+CNN+Classifier+Fusion+for+3D+Skeleton+Action+Recognition&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Banerjee%2C+Avinandan&rft.au=Singh%2C+Pawan+Kumar&rft.au=Sarkar%2C+Ram&rft.date=2021-06-01&rft.pub=IEEE&rft.issn=1051-8215&rft.volume=31&rft.issue=6&rft.spage=2206&rft.epage=2216&rft_id=info:doi/10.1109%2FTCSVT.2020.3019293&rft.externalDocID=9177170 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon |