Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118758421> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3118758421 abstract "Recently 3D scene understanding attracts attention for many applications, however, annotating a vast amount of 3D data for training is usually expensive and time consuming. To alleviate the needs of ground truth, we propose a self-supervised schema to learn 4D spatio-temporal features (i.e. 3 spatial dimensions plus 1 temporal dimension) from dynamic point cloud data by predicting the temporal order of sampled and shuffled point cloud clips. 3D sequential point cloud contains precious geometric and depth information to better recognize activities in 3D space compared to videos. To learn the 4D spatio-temporal features, we introduce 4D convolution neural networks to predict the temporal order on a self-created large scale dataset, NTU-PCLs, derived from the NTU-RGB+D dataset. The efficacy of the learned 4D spatio-temporal features is verified on two tasks: 1) Self-supervised 3D nearest neighbor retrieval; and 2) Self-supervised representation learning transferred for action recognition on a smaller 3D dataset. Our extensive experiments prove the effectiveness of the proposed self-supervised learning method which achieves comparable results w.r.t. the fully-supervised methods on action recognition on MSRAction3D dataset." @default.
- W3118758421 created "2021-01-18" @default.
- W3118758421 creator A5008636823 @default.
- W3118758421 creator A5009867298 @default.
- W3118758421 creator A5062430868 @default.
- W3118758421 creator A5067049252 @default.
- W3118758421 creator A5074244244 @default.
- W3118758421 date "2021-01-01" @default.
- W3118758421 modified "2023-09-23" @default.
- W3118758421 title "Self-supervised 4D Spatio-temporal Feature Learning via Order Prediction of Sequential Point Cloud Clips" @default.
- W3118758421 cites W1679894842 @default.
- W3118758421 cites W2031334527 @default.
- W3118758421 cites W204268067 @default.
- W3118758421 cites W2057232399 @default.
- W3118758421 cites W2064675550 @default.
- W3118758421 cites W2105101328 @default.
- W3118758421 cites W2108598243 @default.
- W3118758421 cites W2120852116 @default.
- W3118758421 cites W2143267104 @default.
- W3118758421 cites W2144380653 @default.
- W3118758421 cites W2173046955 @default.
- W3118758421 cites W2211722331 @default.
- W3118758421 cites W2321533354 @default.
- W3118758421 cites W2465488276 @default.
- W3118758421 cites W2609719703 @default.
- W3118758421 cites W2751555739 @default.
- W3118758421 cites W2883451034 @default.
- W3118758421 cites W2948242301 @default.
- W3118758421 cites W2962824791 @default.
- W3118758421 cites W2963076818 @default.
- W3118758421 cites W2963125977 @default.
- W3118758421 cites W2963524571 @default.
- W3118758421 cites W2964037671 @default.
- W3118758421 cites W2964134613 @default.
- W3118758421 cites W2982529734 @default.
- W3118758421 cites W2982683655 @default.
- W3118758421 cites W3006205814 @default.
- W3118758421 cites W3100220783 @default.
- W3118758421 cites W3114753236 @default.
- W3118758421 doi "https://doi.org/10.1109/wacv48630.2021.00381" @default.
- W3118758421 hasPublicationYear "2021" @default.
- W3118758421 type Work @default.
- W3118758421 sameAs 3118758421 @default.
- W3118758421 citedByCount "5" @default.
- W3118758421 countsByYear W31187584212021 @default.
- W3118758421 countsByYear W31187584212022 @default.
- W3118758421 crossrefType "proceedings-article" @default.
- W3118758421 hasAuthorship W3118758421A5008636823 @default.
- W3118758421 hasAuthorship W3118758421A5009867298 @default.
- W3118758421 hasAuthorship W3118758421A5062430868 @default.
- W3118758421 hasAuthorship W3118758421A5067049252 @default.
- W3118758421 hasAuthorship W3118758421A5074244244 @default.
- W3118758421 hasConcept C119857082 @default.
- W3118758421 hasConcept C131979681 @default.
- W3118758421 hasConcept C153180895 @default.
- W3118758421 hasConcept C154945302 @default.
- W3118758421 hasConcept C41008148 @default.
- W3118758421 hasConcept C59404180 @default.
- W3118758421 hasConcept C81363708 @default.
- W3118758421 hasConcept C82990744 @default.
- W3118758421 hasConceptScore W3118758421C119857082 @default.
- W3118758421 hasConceptScore W3118758421C131979681 @default.
- W3118758421 hasConceptScore W3118758421C153180895 @default.
- W3118758421 hasConceptScore W3118758421C154945302 @default.
- W3118758421 hasConceptScore W3118758421C41008148 @default.
- W3118758421 hasConceptScore W3118758421C59404180 @default.
- W3118758421 hasConceptScore W3118758421C81363708 @default.
- W3118758421 hasConceptScore W3118758421C82990744 @default.
- W3118758421 hasLocation W31187584211 @default.
- W3118758421 hasOpenAccess W3118758421 @default.
- W3118758421 hasPrimaryLocation W31187584211 @default.
- W3118758421 hasRelatedWork W2738858320 @default.
- W3118758421 hasRelatedWork W2774550181 @default.
- W3118758421 hasRelatedWork W2897284294 @default.
- W3118758421 hasRelatedWork W2940661641 @default.
- W3118758421 hasRelatedWork W3093612317 @default.
- W3118758421 hasRelatedWork W3184380613 @default.
- W3118758421 hasRelatedWork W3203877373 @default.
- W3118758421 hasRelatedWork W4287776258 @default.
- W3118758421 hasRelatedWork W4292817738 @default.
- W3118758421 hasRelatedWork W564581980 @default.
- W3118758421 isParatext "false" @default.
- W3118758421 isRetracted "false" @default.
- W3118758421 magId "3118758421" @default.
- W3118758421 workType "article" @default.