FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3008659735> ?p ?o ?g. }

• W3008659735 abstract "Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation.However, existing methods still perform poorly on challenging video tasks such as long-term forecasting. This is because these kinds of challenging tasks require learning long-term spatio-temporal correlations in the video sequence. In this paper, we propose a higher-order convolutional LSTM model that can efficiently learn these correlations, along with a succinct representations of the history. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. To make this feasible in terms of computation and memory requirements, we propose a novel convolutional tensor-train decomposition of the higher-order model. This decomposition reduces the model complexity by jointly approximating a sequence of convolutional kernels asa low-rank tensor-train factorization. As a result, our model outperforms existing approaches, but uses only a fraction of parameters, including the baseline models.Our results achieve state-of-the-art performance in a wide range of applications and datasets, including the multi-steps video prediction on the Moving-MNIST-2and KTH action datasets as well as early activity recognition on the Something-Something V2 dataset." @default.
• W3008659735 created "2020-03-06" @default.
• W3008659735 creator A5006048318 @default.
• W3008659735 creator A5008267969 @default.
• W3008659735 creator A5023215207 @default.
• W3008659735 creator A5025693806 @default.
• W3008659735 creator A5037162168 @default.
• W3008659735 creator A5056503617 @default.
• W3008659735 date "2020-02-21" @default.
• W3008659735 modified "2023-09-27" @default.
• W3008659735 title "Convolutional Tensor-Train LSTM for Spatio-temporal Learning" @default.
• W3008659735 cites W1485009520 @default.
• W3008659735 cites W1522301498 @default.
• W3008659735 cites W1533861849 @default.
• W3008659735 cites W1798945469 @default.
• W3008659735 cites W196214544 @default.
• W3008659735 cites W1993482030 @default.
• W3008659735 cites W2024165284 @default.
• W3008659735 cites W2034328688 @default.
• W3008659735 cites W2064675550 @default.
• W3008659735 cites W2105724942 @default.
• W3008659735 cites W2116435618 @default.
• W3008659735 cites W2131524184 @default.
• W3008659735 cites W2133665775 @default.
• W3008659735 cites W2282641050 @default.
• W3008659735 cites W2345668077 @default.
• W3008659735 cites W2401640538 @default.
• W3008659735 cites W2407277018 @default.
• W3008659735 cites W2424778531 @default.
• W3008659735 cites W2528489519 @default.
• W3008659735 cites W2615413256 @default.
• W3008659735 cites W2625366777 @default.
• W3008659735 cites W2738900641 @default.
• W3008659735 cites W2765363933 @default.
• W3008659735 cites W2765932895 @default.
• W3008659735 cites W2768975186 @default.
• W3008659735 cites W2783879794 @default.
• W3008659735 cites W2796303840 @default.
• W3008659735 cites W2796873224 @default.
• W3008659735 cites W2800283575 @default.
• W3008659735 cites W2803450289 @default.
• W3008659735 cites W2902227449 @default.
• W3008659735 cites W2908080566 @default.
• W3008659735 cites W2911892705 @default.
• W3008659735 cites W2916976785 @default.
• W3008659735 cites W2948412951 @default.
• W3008659735 cites W2950739196 @default.
• W3008659735 cites W2950946978 @default.
• W3008659735 cites W2952453038 @default.
• W3008659735 cites W2952902402 @default.
• W3008659735 cites W2962988160 @default.
• W3008659735 cites W2963045453 @default.
• W3008659735 cites W2963125871 @default.
• W3008659735 cites W2963341956 @default.
• W3008659735 cites W2963402657 @default.
• W3008659735 cites W2963403868 @default.
• W3008659735 cites W2963629403 @default.
• W3008659735 cites W2963657860 @default.
• W3008659735 cites W2963704562 @default.
• W3008659735 cites W2964184826 @default.
• W3008659735 cites W2964327849 @default.
• W3008659735 cites W2965132998 @default.
• W3008659735 cites W2969855422 @default.
• W3008659735 cites W2970213198 @default.
• W3008659735 cites W3034633006 @default.
• W3008659735 cites W3098172343 @default.
• W3008659735 cites W3112282987 @default.
• W3008659735 cites W3121797243 @default.
• W3008659735 cites W648786980 @default.
• W3008659735 hasPublicationYear "2020" @default.
• W3008659735 type Work @default.
• W3008659735 sameAs 3008659735 @default.
• W3008659735 citedByCount "2" @default.
• W3008659735 countsByYear W30086597352021 @default.
• W3008659735 crossrefType "posted-content" @default.
• W3008659735 hasAuthorship W3008659735A5006048318 @default.
• W3008659735 hasAuthorship W3008659735A5008267969 @default.
• W3008659735 hasAuthorship W3008659735A5023215207 @default.
• W3008659735 hasAuthorship W3008659735A5025693806 @default.
• W3008659735 hasAuthorship W3008659735A5037162168 @default.
• W3008659735 hasAuthorship W3008659735A5056503617 @default.
• W3008659735 hasConcept C108583219 @default.
• W3008659735 hasConcept C114614502 @default.
• W3008659735 hasConcept C119857082 @default.
• W3008659735 hasConcept C153180895 @default.
• W3008659735 hasConcept C154945302 @default.
• W3008659735 hasConcept C155281189 @default.
• W3008659735 hasConcept C164226766 @default.
• W3008659735 hasConcept C190502265 @default.
• W3008659735 hasConcept C202444582 @default.
• W3008659735 hasConcept C2778112365 @default.
• W3008659735 hasConcept C33923547 @default.
• W3008659735 hasConcept C41008148 @default.
• W3008659735 hasConcept C54355233 @default.
• W3008659735 hasConcept C81363708 @default.
• W3008659735 hasConcept C86803240 @default.
• W3008659735 hasConceptScore W3008659735C108583219 @default.
• W3008659735 hasConceptScore W3008659735C114614502 @default.
• W3008659735 hasConceptScore W3008659735C119857082 @default.
• W3008659735 hasConceptScore W3008659735C153180895 @default.

• next