Due to the increase in computational resources and accessibility of data...
In this work, we focus on generating graphical representations of noisy,...
Joint visual and language modeling on large-scale datasets has recently ...
The remarkable success of deep learning in various domains relies on the...
We present LARNet, a novel end-to-end approach for generating human acti...
We focus on the problem of novel-view human action synthesis. Given an a...
This paper summarizes the TinyAction challenge which was organized in
Ac...
We address the problem of novel view video prediction; given a set of in...
Neural networks trained on real-world datasets with long-tailed label
di...
Action recognition and detection in the context of long untrimmed video
...
The recent research in semi-supervised learning (SSL) is mostly dominate...
We propose SSA2D, a simple yet effective end-to-end deep network for
act...
Human action recognition is an important problem in computer vision. It ...
The existing research in action recognition is mostly focused on high-qu...
In this work we propose a capsule-based approach for semi-supervised vid...
In this paper, we propose an end-to-end capsule network for pixel level
...
The recent success in deep learning has lead to various effective
repres...
The recent advances in Deep Convolutional Neural Networks (DCNNs) have s...