1 code implementation • 3 Feb 2022 • Benjamin Filtjens, Bart Vanrumste, Peter Slaets
State-of-the-art action segmentation approaches use multiple stages of temporal convolutions.
1 code implementation • 29 Mar 2021 • Benjamin Filtjens, Pieter Ginis, Alice Nieuwboer, Peter Slaets, Bart Vanrumste
Furthermore, a novel deep neural network architecture is proposed that aims to better capture the spatial and temporal dependencies than the state-of-the-art baselines.