Skeleton-Based Online Action Prediction Using Scale Selection Network
Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a...
Saved in:
| Published in | IEEE transactions on pattern analysis and machine intelligence Vol. 42; no. 6; pp. 1453 - 1467 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.06.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis. Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step. An activation sharing scheme is also proposed to handle the overlapping computations among the adjacent time steps, which enables our framework to run more efficiently. Moreover, to enhance the performance of our framework for action prediction with the skeletal input data, a hierarchy of dilated tree convolutions are also designed to learn the multi-level structured semantic representations over the skeleton joints at each frame. Our proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of our method for skeleton-based online action prediction. |
|---|---|
| AbstractList | Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis. Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step. An activation sharing scheme is also proposed to handle the overlapping computations among the adjacent time steps, which enables our framework to run more efficiently. Moreover, to enhance the performance of our framework for action prediction with the skeletal input data, a hierarchy of dilated tree convolutions are also designed to learn the multi-level structured semantic representations over the skeleton joints at each frame. Our proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of our method for skeleton-based online action prediction. Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis. Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step. An activation sharing scheme is also proposed to handle the overlapping computations among the adjacent time steps, which enables our framework to run more efficiently. Moreover, to enhance the performance of our framework for action prediction with the skeletal input data, a hierarchy of dilated tree convolutions are also designed to learn the multi-level structured semantic representations over the skeleton joints at each frame. Our proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of our method for skeleton-based online action prediction.Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis. Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step. An activation sharing scheme is also proposed to handle the overlapping computations among the adjacent time steps, which enables our framework to run more efficiently. Moreover, to enhance the performance of our framework for action prediction with the skeletal input data, a hierarchy of dilated tree convolutions are also designed to learn the multi-level structured semantic representations over the skeleton joints at each frame. Our proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of our method for skeleton-based online action prediction. |
| Author | Duan, Ling-Yu Shahroudy, Amir Kot, Alex C. Wang, Gang Liu, Jun |
| Author_xml | – sequence: 1 givenname: Jun orcidid: 0000-0002-4365-4165 surname: Liu fullname: Liu, Jun email: jliu029@ntu.edu.sg organization: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore – sequence: 2 givenname: Amir orcidid: 0000-0002-1045-6437 surname: Shahroudy fullname: Shahroudy, Amir email: amirsh@chalmers.se organization: Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden – sequence: 3 givenname: Gang orcidid: 0000-0002-1816-1457 surname: Wang fullname: Wang, Gang email: wanggang@ntu.edu.sg organization: Alibaba Group, Hangzhou, China – sequence: 4 givenname: Ling-Yu orcidid: 0000-0002-4491-2023 surname: Duan fullname: Duan, Ling-Yu email: lingyu@pku.edu.cn organization: National Engineering Laboratory for Video Technology, Peking University, Beijing, China – sequence: 5 givenname: Alex C. orcidid: 0000-0001-6262-8125 surname: Kot fullname: Kot, Alex C. email: eackot@ntu.edu.sg organization: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30762531$$D View this record in MEDLINE/PubMed https://research.chalmers.se/publication/517262$$DView record from Swedish Publication Index |
| BookMark | eNp9kUFv1DAQhS1URLcLfwAkFIkLlyz22HHs41IVqFRopW3PluOMqdtsstiJKv49XrLsoQdOtqzvPc-8d0ZO-qFHQt4yumKM6k-3N-vvlyugTK9AaaUr8YIsgElaatBwQhaUSSiVAnVKzlJ6oJSJivJX5JTTWkLF2YJcbB6xw3Hoy882YVtc913osVi7MQx9cROxDfP1LoX-Z7FxtsNikyXz6w8cn4b4-Jq89LZL-OZwLsndl4vb82_l1fXXy_P1VekE1GPJBaDiChu0HDyDxlLmwTfeNcxZ5NQj1hyQUam8U7zSSnHeVqKRVrdS8yXZzL7pCXdTY3YxbG38bQYbTMSENrp74-5tt8WYTEJT1w26RoPhVAsjci5G27oy3AvPW8k5yCq7fpxdd3H4NWEazTYkh11nexymZABAM1ZzKjP64Rn6MEyxzzsbEDlfClU2XZL3B2pqttgex_wXewZgBlwcUorojwijZt-t-dut2XdrDt1mkXomcmG0-xrGaEP3f-m7WRoQ8fiXknlkIfkfGTmvbg |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2022_3201227 crossref_primary_10_1007_s11042_022_11919_y crossref_primary_10_1109_ACCESS_2020_3014445 crossref_primary_10_1109_TPAMI_2022_3183112 crossref_primary_10_3390_biomimetics9030123 crossref_primary_10_1016_j_neucom_2022_03_069 crossref_primary_10_3390_ai5030083 crossref_primary_10_1049_csy2_70005 crossref_primary_10_3390_s23146279 crossref_primary_10_1109_TCSVT_2021_3101847 crossref_primary_10_1109_TCSVT_2024_3429182 crossref_primary_10_1016_j_neucom_2020_12_020 crossref_primary_10_3390_app14146335 crossref_primary_10_1016_j_patcog_2024_110733 crossref_primary_10_1109_TCSVT_2021_3124562 crossref_primary_10_26599_TST_2021_9010068 crossref_primary_10_1109_JSEN_2024_3388154 crossref_primary_10_1016_j_neucom_2020_10_096 crossref_primary_10_1016_j_jvcir_2022_103531 crossref_primary_10_1109_TMM_2019_2953814 crossref_primary_10_3390_data5040104 crossref_primary_10_1109_TPAMI_2022_3157033 crossref_primary_10_1016_j_engappai_2023_106855 crossref_primary_10_1016_j_eswa_2023_123061 crossref_primary_10_1016_j_jvcir_2025_104389 crossref_primary_10_1109_TPAMI_2022_3161735 crossref_primary_10_1109_TCSVT_2020_3015051 crossref_primary_10_1109_TCDS_2021_3103960 crossref_primary_10_1109_TIP_2021_3104182 crossref_primary_10_1109_ACCESS_2021_3102671 crossref_primary_10_1145_3639470 crossref_primary_10_1109_TCSVT_2020_3021409 crossref_primary_10_1109_ACCESS_2020_3012557 crossref_primary_10_3390_s20174871 crossref_primary_10_34133_cbsystems_0100 crossref_primary_10_1016_j_neunet_2024_107114 crossref_primary_10_34133_cbsystems_0102 crossref_primary_10_1109_TPAMI_2022_3170511 crossref_primary_10_1109_JIOT_2020_3042986 crossref_primary_10_1017_S0263574722000169 crossref_primary_10_1080_13682199_2023_2190927 crossref_primary_10_1109_TMM_2021_3050642 crossref_primary_10_1109_TPAMI_2019_2916873 crossref_primary_10_1007_s10489_021_02764_x crossref_primary_10_1049_ipr2_12472 crossref_primary_10_1007_s12204_023_2619_6 crossref_primary_10_1007_s11263_020_01354_7 crossref_primary_10_1109_TIP_2021_3129117 crossref_primary_10_1109_TMM_2022_3198011 crossref_primary_10_1016_j_neucom_2020_03_126 crossref_primary_10_1007_s44196_023_00292_9 crossref_primary_10_1109_TPAMI_2022_3177813 crossref_primary_10_1109_TMM_2021_3119177 crossref_primary_10_1109_TIP_2020_2987425 crossref_primary_10_3390_app10030966 crossref_primary_10_1049_ipr2_12469 crossref_primary_10_1109_ACCESS_2019_2945632 crossref_primary_10_1109_TPAMI_2020_3034233 crossref_primary_10_1016_j_patcog_2023_109595 crossref_primary_10_1109_TMM_2021_3139768 crossref_primary_10_3233_ICA_210652 crossref_primary_10_1007_s40747_022_00914_3 crossref_primary_10_1109_TMM_2021_3137745 crossref_primary_10_1109_TPAMI_2021_3059923 crossref_primary_10_1016_j_engappai_2023_107488 crossref_primary_10_1109_ACCESS_2019_2956538 crossref_primary_10_1109_TASE_2020_3045880 crossref_primary_10_1109_TMM_2020_2978637 crossref_primary_10_1109_ACCESS_2023_3309420 crossref_primary_10_1109_TIP_2022_3193290 crossref_primary_10_1109_TIP_2023_3279991 crossref_primary_10_1016_j_patcog_2022_108645 crossref_primary_10_1007_s00138_023_01386_2 crossref_primary_10_1016_j_neucom_2020_07_135 crossref_primary_10_1109_TIP_2019_2937757 crossref_primary_10_1109_LSP_2021_3049691 crossref_primary_10_1117_1_JEI_28_4_043018 crossref_primary_10_3390_app10041482 |
| Cites_doi | 10.1109/ICCV.2017.317 10.1109/CVPR.2017.106 10.1007/978-3-319-46487-9_50 10.1109/LSP.2017.2690339 10.1109/CVPR.2016.90 10.1109/TPAMI.2017.2771306 10.1007/978-3-319-46478-7_23 10.1016/j.patcog.2016.05.019 10.1007/978-3-319-46448-0_17 10.1109/ICCV.2013.342 10.5244/C.25.65 10.1109/CVPR.2016.119 10.1007/s11263-013-0683-3 10.1109/ICCV.2017.610 10.1109/CVPR.2017.390 10.1109/CVPR.2016.115 10.1109/ICIP.2017.8296967 10.1109/WACV.2015.138 10.1109/WACV.2014.6836044 10.1109/CVPR.2013.343 10.1109/TPAMI.2017.2712608 10.1109/TPAMI.2016.2640292 10.24963/ijcai.2017/342 10.1016/j.cviu.2017.01.011 10.1109/ICPR.2014.772 10.1109/ACPR.2015.7486569 10.1109/ICCV.2017.621 10.1109/TMM.2017.2778559 10.1145/2964284.2967191 10.1016/j.jvcir.2013.03.001 10.1109/WACV.2017.24 10.1007/978-3-319-10602-1_39 10.1109/CVPR.2017.391 10.1109/TPAMI.2015.2505295 10.5244/C.31.52 10.1109/WACV.2017.25 10.1109/ICCV.2017.233 10.1109/CVPRW.2012.6239234 10.1109/CVPR.2017.155 10.1109/ICCV.2013.389 10.1109/TPAMI.2013.198 10.1007/978-3-642-33718-5_21 10.1109/CVPR.2018.00871 10.1016/j.patrec.2014.04.011 10.1109/TCYB.2013.2265378 10.1007/978-3-319-46478-7_13 10.1109/CVPRW.2012.6239175 10.5244/C.31.92 10.1109/CVPR.2017.486 10.1109/CVPRW.2017.207 10.1109/CVPR.2014.82 10.1109/TPAMI.2008.260 10.1109/CVPRW.2012.6239233 10.1109/ICCV.2015.365 10.1109/TIP.2017.2785279 10.1109/ICCV.2011.6126349 10.1109/ICCV.2015.460 10.1109/CVPR.2006.200 10.1007/978-3-319-48881-3_28 10.1109/CVPR.2017.137 10.3758/BF03212378 10.1016/B978-0-12-813445-0.00005-8 10.1109/ICCV.2015.169 10.1016/j.patcog.2015.11.019 10.1109/WACV.2017.29 10.1109/CVPR.2016.293 10.1109/TPAMI.2013.2297321 10.1145/2522848.2532595 10.1109/CVPR.2017.678 10.1109/ICCV.2017.392 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 ADTPV AOWAS F1S |
| DOI | 10.1109/TPAMI.2019.2898954 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present 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 SwePub SwePub Articles SWEPUB Chalmers tekniska högskola |
| 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 Technology Research Database MEDLINE - Academic |
| 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/IET Electronic Library url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 1467 |
| ExternalDocumentID | oai_research_chalmers_se_77becb92_3094_4929_9a75_3f4f3d633265 30762531 10_1109_TPAMI_2019_2898954 8640046 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: National Research Foundation Singapore funderid: 10.13039/501100001381 – fundername: Infocomm Media Development Authority, Singapore – fundername: National Natural Science Foundation of China grantid: 61661146005; U1611461 funderid: 10.13039/501100001809 – fundername: National Basic Research Program of China (973 Program) grantid: 2015CB351806 funderid: 10.13039/501100012166 |
| 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 AAYXX CITATION 5VS 9M8 ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM RIG RNI RZB VH1 XJT 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 ADTPV AOWAS F1S |
| ID | FETCH-LOGICAL-c427t-342e838ebea32f12ba01f2fbfcb1cae30fee732e1068fc83598833d54b6a9d693 |
| IEDL.DBID | RIE |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Thu Aug 21 06:35:21 EDT 2025 Fri Jul 11 16:36:05 EDT 2025 Mon Jun 30 07:04:41 EDT 2025 Mon Jul 21 05:57:16 EDT 2025 Tue Jul 01 03:18:24 EDT 2025 Thu Apr 24 23:01:46 EDT 2025 Wed Aug 27 02:39:21 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-c427t-342e838ebea32f12ba01f2fbfcb1cae30fee732e1068fc83598833d54b6a9d693 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-4365-4165 0000-0002-1816-1457 0000-0002-1045-6437 0000-0001-6262-8125 0000-0002-4491-2023 |
| PMID | 30762531 |
| PQID | 2400102563 |
| PQPubID | 85458 |
| PageCount | 15 |
| ParticipantIDs | crossref_primary_10_1109_TPAMI_2019_2898954 ieee_primary_8640046 proquest_miscellaneous_2229117306 swepub_primary_oai_research_chalmers_se_77becb92_3094_4929_9a75_3f4f3d633265 pubmed_primary_30762531 crossref_citationtrail_10_1109_TPAMI_2019_2898954 proquest_journals_2400102563 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2020-06-01 |
| PublicationDateYYYYMMDD | 2020-06-01 |
| PublicationDate_xml | – month: 06 year: 2020 text: 2020-06-01 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 | 2020 |
| 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 ref13 ref56 ref12 ref15 ref58 ref14 ref53 li (ref68) 2017 ref52 ref55 ref11 ref54 ref10 li (ref41) 2018 ref17 ref16 ref19 oneata (ref22) 2014 ref51 ref50 liu (ref84) 2017 han (ref8) 2013; 43 collobert (ref86) 2011 ref46 ref45 ref48 ref47 ref42 ref85 yan (ref43) 2018 ref44 ref49 ioffe (ref87) 2015 lea (ref59) 2016 ref7 yu (ref34) 2014 ref9 ref4 ref3 ref6 ref5 ref82 he (ref80) 2016 ref40 ref83 ref79 ref35 van den oord (ref75) 2016 ref37 ref36 ref31 ref30 ref77 ref33 ref32 ref2 ref1 ref38 yu (ref78) 2016 ref71 ref70 ref73 ref72 dauphin (ref76) 2017 ref24 ref67 ref23 ref26 ref69 ref25 ref64 ref20 ref63 ref66 liu (ref81) 2017 ref65 ref21 zhu (ref39) 2016 du (ref18) 2015 ref28 ref27 ref29 ref60 lecun (ref74) 1995 ref62 ref61 |
| References_xml | – ident: ref66 doi: 10.1109/ICCV.2017.317 – ident: ref82 doi: 10.1109/CVPR.2017.106 – ident: ref19 doi: 10.1007/978-3-319-46487-9_50 – ident: ref44 doi: 10.1109/LSP.2017.2690339 – ident: ref79 doi: 10.1109/CVPR.2016.90 – ident: ref12 doi: 10.1109/TPAMI.2017.2771306 – ident: ref37 doi: 10.1007/978-3-319-46478-7_23 – start-page: 630 year: 2016 ident: ref80 article-title: Identity mappings in deep residual networks publication-title: Proc Eur Conf Comput Vis – ident: ref27 doi: 10.1016/j.patcog.2016.05.019 – ident: ref1 doi: 10.1007/978-3-319-46448-0_17 – ident: ref24 doi: 10.1109/ICCV.2013.342 – ident: ref23 doi: 10.5244/C.25.65 – ident: ref70 doi: 10.1109/CVPR.2016.119 – year: 2017 ident: ref68 article-title: Skeleton boxes: Solving skeleton based action detection with a single deep convolutional neural network publication-title: ArXiv – ident: ref25 doi: 10.1007/s11263-013-0683-3 – ident: ref60 doi: 10.1109/ICCV.2017.610 – ident: ref4 doi: 10.1109/CVPR.2017.390 – ident: ref40 doi: 10.1109/CVPR.2016.115 – ident: ref13 doi: 10.1109/ICIP.2017.8296967 – ident: ref61 doi: 10.1109/WACV.2015.138 – ident: ref17 doi: 10.1109/WACV.2014.6836044 – ident: ref2 doi: 10.1109/CVPR.2013.343 – ident: ref77 doi: 10.1109/TPAMI.2017.2712608 – ident: ref35 doi: 10.1109/TPAMI.2016.2640292 – ident: ref7 doi: 10.24963/ijcai.2017/342 – start-page: 448 year: 2015 ident: ref87 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proc 32nd Int Conf Mach Learn – ident: ref9 doi: 10.1016/j.cviu.2017.01.011 – year: 2014 ident: ref22 article-title: The lear submission at thumos 2014 – ident: ref32 doi: 10.1109/ICPR.2014.772 – ident: ref47 doi: 10.1109/ACPR.2015.7486569 – year: 2016 ident: ref75 article-title: Wavenet: A generative model for raw audio publication-title: CoRR – ident: ref16 doi: 10.1109/ICCV.2017.621 – ident: ref54 doi: 10.1109/TMM.2017.2778559 – ident: ref46 doi: 10.1145/2964284.2967191 – ident: ref28 doi: 10.1016/j.jvcir.2013.03.001 – ident: ref14 doi: 10.1109/WACV.2017.24 – start-page: 1414 year: 2017 ident: ref81 article-title: Manifold warp segmentation of human action publication-title: IEEE Trans Neural Netw Learn Syst – ident: ref50 doi: 10.1007/978-3-319-10602-1_39 – ident: ref85 doi: 10.1109/CVPR.2017.391 – ident: ref31 doi: 10.1109/TPAMI.2015.2505295 – ident: ref64 doi: 10.5244/C.31.52 – ident: ref69 doi: 10.1109/WACV.2017.25 – year: 2016 ident: ref59 article-title: Temporal convolutional networks for action segmentation and detection publication-title: ArXiv – ident: ref6 doi: 10.1109/ICCV.2017.233 – year: 2017 ident: ref76 article-title: Language modeling with gated convolutional networks publication-title: Proc Int Conf Mach Learn – ident: ref33 doi: 10.1109/CVPRW.2012.6239234 – ident: ref63 doi: 10.1109/CVPR.2017.155 – ident: ref56 doi: 10.1109/ICCV.2013.389 – ident: ref29 doi: 10.1109/TPAMI.2013.198 – year: 2018 ident: ref43 article-title: Spatial temporal graph convolutional networks for skeleton-based action recognition publication-title: ArXiv – ident: ref55 doi: 10.1007/978-3-642-33718-5_21 – ident: ref72 doi: 10.1109/CVPR.2018.00871 – ident: ref26 doi: 10.1016/j.patrec.2014.04.011 – volume: 43 start-page: 1318 year: 2013 ident: ref8 article-title: Enhanced computer vision with microsoft kinect sensor: A review publication-title: IEEE Trans Cybern doi: 10.1109/TCYB.2013.2265378 – ident: ref67 doi: 10.1007/978-3-319-46478-7_13 – start-page: 50 year: 2014 ident: ref34 article-title: Discriminative orderlet mining for real-time recognition of human-object interaction publication-title: Proc Asian Conf Comput Vis – year: 2017 ident: ref84 article-title: Pku-mmd: A large scale benchmark for continuous multi-modal human action understanding publication-title: ArXiv – ident: ref49 doi: 10.1109/CVPRW.2012.6239175 – ident: ref62 doi: 10.5244/C.31.92 – year: 1995 ident: ref74 article-title: Convolutional networks for images, speech, and time series publication-title: The Handbook of Brain Theory and Neural Networks – ident: ref48 doi: 10.1109/CVPR.2017.486 – ident: ref42 doi: 10.1109/CVPRW.2017.207 – ident: ref30 doi: 10.1109/CVPR.2014.82 – ident: ref21 doi: 10.1109/TPAMI.2008.260 – ident: ref36 doi: 10.1109/CVPRW.2012.6239233 – ident: ref52 doi: 10.1109/ICCV.2015.365 – ident: ref15 doi: 10.1109/TIP.2017.2785279 – ident: ref51 doi: 10.1109/ICCV.2011.6126349 – ident: ref11 doi: 10.1109/ICCV.2015.460 – ident: ref20 doi: 10.1109/CVPR.2006.200 – ident: ref3 doi: 10.1007/978-3-319-48881-3_28 – start-page: 3697 year: 2016 ident: ref39 article-title: Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks publication-title: Proc 13th AAAI Conf Artif Intell – ident: ref45 doi: 10.1109/CVPR.2017.137 – ident: ref5 doi: 10.3758/BF03212378 – year: 2011 ident: ref86 article-title: Torch7: A matlab-like environment for machine learning publication-title: Proc NIPSW – ident: ref38 doi: 10.1016/B978-0-12-813445-0.00005-8 – year: 2018 ident: ref41 article-title: Spatio-temporal graph convolution for skeleton based action recognition publication-title: ArXiv – ident: ref83 doi: 10.1109/ICCV.2015.169 – ident: ref10 doi: 10.1016/j.patcog.2015.11.019 – year: 2016 ident: ref78 article-title: Multi-scale context aggregation by dilated convolutions publication-title: Proc Int Conf Learn Representations – ident: ref71 doi: 10.1109/WACV.2017.29 – ident: ref57 doi: 10.1109/CVPR.2016.293 – ident: ref53 doi: 10.1109/TPAMI.2013.2297321 – ident: ref73 doi: 10.1145/2522848.2532595 – ident: ref65 doi: 10.1109/CVPR.2017.678 – ident: ref58 doi: 10.1109/ICCV.2017.392 – start-page: 1110 year: 2015 ident: ref18 article-title: Hierarchical recurrent neural network for skeleton based action recognition publication-title: Proc IEEE Conf Comput Vis Pattern Recognit |
| SSID | ssj0014503 |
| Score | 2.5940976 |
| Snippet | Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action... |
| SourceID | swepub proquest pubmed crossref ieee |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1453 |
| SubjectTerms | Action prediction dilated convolution Microsoft Windows Pattern recognition Real-time systems scale selection Skeleton skeleton data sliding window Task analysis Three-dimensional displays Videos |
| Title | Skeleton-Based Online Action Prediction Using Scale Selection Network |
| URI | https://ieeexplore.ieee.org/document/8640046 https://www.ncbi.nlm.nih.gov/pubmed/30762531 https://www.proquest.com/docview/2400102563 https://www.proquest.com/docview/2229117306 https://research.chalmers.se/publication/517262 |
| Volume | 42 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3fT9swED4BT-NhQGEjwKYg8balNLbjxI9lAnUTrZAAiTcrdmwhgVpE2xf-eu6cH4IKTTxEipKL1eTuemf77vsATpwXtiq8TLwXIsEIbZPCc5sIkUtZVcyajBqFxxM5uhX_7rK7Nfjd9cI450LxmevTadjLr2Z2SUtlp4Uki5PrsI4Tt7pXq9sxEFlgQcYMBj0cpxFtg8xAnd5cDcd_qYpL9RmxJWZExoO2jak_T9_Fo0Cw8lGuuQIkGoLPxRaM259d15w89JcL07cvK4iOn32vbfjaZKHxsDabHVhz0x5stQwPcePwPdh8A1e4C-fXDxikiHP4DGNfFdcwpfEwtEbEV8-05xNOQx0CjoLBJ74ORDt0dVJXnO_B7cX5zZ9R0tAwJFawfJFwwVzBC9R2yZlPmSkHqWfeeGtSWzo-8M7lnDmcXBbeFgQJWHBeZcLIUlVS8W-wMZ1N3T7EOUMJYxUeqSi5xGTZ4lg5yhPEko8gbZWhbYNRTlQZjzrMVQZKB11q0qVudBnBr-6Zpxqh47_Su_T9O8nm00dw1OpcN04811Rem1JOyCM47m6j-9GeSjl1syXKMIbhAv8mcYjvta10Y7cmFsFlbTzdHcL0bsCc7rW9D0w5cz13Os_Rp4xi-KwSWmDuqlWZZ5p74XklOSbb2cHHr3AIXxitBYQVoiPYWDwv3Q9MmBbmZ_CUVyyfDiM |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwzV3NbtQwEB5V5QAcKLT8pBQIEpxQthvbcZIDhwVa7dLdVaVupd5M7NiqVLRbdXeF4Fl4Fd6NGceJoKq4VeIQKUocK4nH82PPfB_AG-uEqQsnE-eESNBCm6Rw3CRC5FLWNTM6o0LhyVQOT8Xns-xsA352tTDWWp98Znt06vfy64VZ01LZfiFJ4mRIoTyy379hgLZ8P_qEo_mWscOD2cdhEjgEEiNYvkq4YLbgBb5qxZlLma76qWNOO6NTU1ned9bmnFmMjApnCsKzKzivM6FlVdaSoJZQwd9BPyNjTXVYt0chMs-7jD4T6hQMXNqSnH65PzseTEaUN1b2GPEzZkT_g7MJgw2e_mUBPaXLTd7tNehSb-4Ot-BX-6OaLJeL3nqle-bHNQzJ__VPPoQHwc-OB83EeAQbdr4NWy2HRRxU2jbc_wOQcQcOTi7QDBOr8ge07nXcALHGA1_8ER9f0a6WP_WZFtgLmtf4xFMJ0dVpk1P_GE5v5dOewOZ8MbfPIM4ZttCmxCMVFZcYDhjsK8f2BCLlIkjbwVcmoLATGchX5aOxfqm87CiSHRVkJ4J33TOXDQbJP1vv0Hh3LcNQR7DXypgKamqpKIE4Ja-XR_C6u40KhnaNqrldrLENY2gQ0RBgF08b2ez6bkU6gnEjrN0dQi0PcFXnypx7LqClWlqV56g1dMnw2VIogd65Kqs8U9wJx2vJMZzIdm_-hFdwdzibjNV4ND16DvcYrXz49bA92Fxdre0LdA9X-qWfpTF8uW1h_g1LwGz4 |
| 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=Skeleton-Based+Online+Action+Prediction+Using+Scale+Selection+Network&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Liu%2C+Jun&rft.au=Shahroudy%2C+Amir&rft.au=Wang%2C+Gang&rft.au=Duan%2C+Ling+Yu&rft.date=2020-06-01&rft.issn=0162-8828&rft.volume=42&rft.issue=6&rft.spage=1453&rft_id=info:doi/10.1109%2FTPAMI.2019.2898954&rft.externalDocID=oai_research_chalmers_se_77becb92_3094_4929_9a75_3f4f3d633265 |
| 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 |