Search Results for author: Alessia Bertugli

Found 5 papers, 4 papers with code

Generalising via Meta-Examples for Continual Learning in the Wild

1 code implementation28 Jan 2021 Alessia Bertugli, Stefano Vincenzi, Simone Calderara, Andrea Passerini

Future deep learning systems call for techniques that can deal with the evolving nature of temporal data and scarcity of annotations when new problems occur.

Continual Learning Few-Shot Learning

Few-Shot Unsupervised Continual Learning through Meta-Examples

1 code implementation17 Sep 2020 Alessia Bertugli, Stefano Vincenzi, Simone Calderara, Andrea Passerini

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.

Clustering Continual Learning +1

DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting

1 code implementation26 May 2020 Alessio Monti, Alessia Bertugli, Simone Calderara, Rita Cucchiara

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 autonomous agent has to navigate inside a human-centric environment.

Human motion prediction Multi-future Trajectory Prediction +3

AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction

1 code implementation17 May 2020 Alessia Bertugli, Simone Calderara, Pasquale Coscia, Lamberto Ballan, Rita Cucchiara

Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications.

Graph Attention Multi-future Trajectory Prediction +2

Learning to Grasp from 2.5D images: a Deep Reinforcement Learning Approach

no code implementations8 Aug 2019 Alessia Bertugli, Paolo Galeone

Unity 3D allowed us to simulate a real-world setup, where a depth camera is placed in a fixed position and the stream of images is used by our policy network to learn how to solve the task.

Position reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.