Capsule networks were proposed as an alternative approach to Convolution...
The task of multimodal learning has seen a growing interest recently as ...
Neural networks trained on real-world datasets with long-tailed label
di...
The problem of grounding VQA tasks has seen an increased attention in th...
Multimodal self-supervised learning is getting more and more attention a...
Real-world videos contain many complex actions with inherent relationshi...
The recent research in semi-supervised learning (SSL) is mostly dominate...
Activity detection in surveillance videos is a difficult problem due to
...
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 advances in Deep Convolutional Neural Networks (DCNNs) have s...