Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215524871> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3215524871 abstract "Spatiotemporal predictive learning is to generate future frames given a sequence of historical frames. Conventional algorithms are mostly based on recurrent neural networks (RNNs). However, RNN suffers from heavy computational burden such as time and long back-propagation process due to the seriality of recurrent structure. Recently, Transformer-based methods have also been investigated in the form of encoder-decoder or plain encoder, but the encoder-decoder form requires too deep networks and the plain encoder is lack of short-term dependencies. To tackle these problems, we propose an algorithm named 3D-temporal convolutional transformer (TCTN), where a transformer-based encoder with temporal convolutional layers is employed to capture short-term and long-term dependencies. Our proposed algorithm can be easy to implement and trained much faster compared with RNN-based methods thanks to the parallel mechanism of Transformer. To validate our algorithm, we conduct experiments on the MovingMNIST and KTH dataset, and show that TCTN outperforms state-of-the-art (SOTA) methods in both performance and training speed." @default.
- W3215524871 created "2021-12-06" @default.
- W3215524871 creator A5017627751 @default.
- W3215524871 creator A5025495172 @default.
- W3215524871 creator A5087705980 @default.
- W3215524871 date "2021-12-02" @default.
- W3215524871 modified "2023-09-27" @default.
- W3215524871 title "TCTN: A 3D-Temporal Convolutional Transformer Network for Spatiotemporal Predictive Learning" @default.
- W3215524871 cites W1485009520 @default.
- W3215524871 cites W1568514080 @default.
- W3215524871 cites W2034328688 @default.
- W3215524871 cites W2095705004 @default.
- W3215524871 cites W2116435618 @default.
- W3215524871 cites W2133665775 @default.
- W3215524871 cites W2194775991 @default.
- W3215524871 cites W2518108298 @default.
- W3215524871 cites W2528639018 @default.
- W3215524871 cites W2550143307 @default.
- W3215524871 cites W2586480386 @default.
- W3215524871 cites W2768975186 @default.
- W3215524871 cites W2908080566 @default.
- W3215524871 cites W2963326684 @default.
- W3215524871 cites W2963403868 @default.
- W3215524871 cites W2996936831 @default.
- W3215524871 cites W3016386342 @default.
- W3215524871 cites W3035540643 @default.
- W3215524871 cites W3096609285 @default.
- W3215524871 cites W3109635183 @default.
- W3215524871 cites W3119786062 @default.
- W3215524871 cites W3138340468 @default.
- W3215524871 cites W3169060579 @default.
- W3215524871 hasPublicationYear "2021" @default.
- W3215524871 type Work @default.
- W3215524871 sameAs 3215524871 @default.
- W3215524871 citedByCount "0" @default.
- W3215524871 crossrefType "posted-content" @default.
- W3215524871 hasAuthorship W3215524871A5017627751 @default.
- W3215524871 hasAuthorship W3215524871A5025495172 @default.
- W3215524871 hasAuthorship W3215524871A5087705980 @default.
- W3215524871 hasBestOaLocation W32155248711 @default.
- W3215524871 hasConcept C101738243 @default.
- W3215524871 hasConcept C108583219 @default.
- W3215524871 hasConcept C111919701 @default.
- W3215524871 hasConcept C11413529 @default.
- W3215524871 hasConcept C118505674 @default.
- W3215524871 hasConcept C119599485 @default.
- W3215524871 hasConcept C127413603 @default.
- W3215524871 hasConcept C133488467 @default.
- W3215524871 hasConcept C147168706 @default.
- W3215524871 hasConcept C153180895 @default.
- W3215524871 hasConcept C154945302 @default.
- W3215524871 hasConcept C165801399 @default.
- W3215524871 hasConcept C40506919 @default.
- W3215524871 hasConcept C41008148 @default.
- W3215524871 hasConcept C50644808 @default.
- W3215524871 hasConcept C66322947 @default.
- W3215524871 hasConcept C81363708 @default.
- W3215524871 hasConceptScore W3215524871C101738243 @default.
- W3215524871 hasConceptScore W3215524871C108583219 @default.
- W3215524871 hasConceptScore W3215524871C111919701 @default.
- W3215524871 hasConceptScore W3215524871C11413529 @default.
- W3215524871 hasConceptScore W3215524871C118505674 @default.
- W3215524871 hasConceptScore W3215524871C119599485 @default.
- W3215524871 hasConceptScore W3215524871C127413603 @default.
- W3215524871 hasConceptScore W3215524871C133488467 @default.
- W3215524871 hasConceptScore W3215524871C147168706 @default.
- W3215524871 hasConceptScore W3215524871C153180895 @default.
- W3215524871 hasConceptScore W3215524871C154945302 @default.
- W3215524871 hasConceptScore W3215524871C165801399 @default.
- W3215524871 hasConceptScore W3215524871C40506919 @default.
- W3215524871 hasConceptScore W3215524871C41008148 @default.
- W3215524871 hasConceptScore W3215524871C50644808 @default.
- W3215524871 hasConceptScore W3215524871C66322947 @default.
- W3215524871 hasConceptScore W3215524871C81363708 @default.
- W3215524871 hasLocation W32155248711 @default.
- W3215524871 hasOpenAccess W3215524871 @default.
- W3215524871 hasPrimaryLocation W32155248711 @default.
- W3215524871 hasRelatedWork W13158784 @default.
- W3215524871 hasRelatedWork W13538861 @default.
- W3215524871 hasRelatedWork W17658120 @default.
- W3215524871 hasRelatedWork W17729602 @default.
- W3215524871 hasRelatedWork W3540334 @default.
- W3215524871 hasRelatedWork W4558901 @default.
- W3215524871 hasRelatedWork W5939791 @default.
- W3215524871 hasRelatedWork W7958345 @default.
- W3215524871 hasRelatedWork W8153826 @default.
- W3215524871 hasRelatedWork W9770290 @default.
- W3215524871 isParatext "false" @default.
- W3215524871 isRetracted "false" @default.
- W3215524871 magId "3215524871" @default.
- W3215524871 workType "article" @default.