3 papers
cs.LG2020
Few-Shot Unsupervised Continual Learning through Meta-Examples
Alessia Bertugli, Stefano Vincenzi, Simone Calderara +1
In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence m…
cs.CV2020
DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting
Alessio Monti, Alessia Bertugli, Simone Calderara +1
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an au…
cs.RO2019
Learning to Grasp from 2.5D images: a Deep Reinforcement Learning Approach
Alessia Bertugli, Paolo Galeone
In this paper, we propose a deep reinforcement learning (DRL) solution to the grasping problem using 2.5D images as the only source of information. In particular, we developed a si…