Marco Ciccone

name.surname AT


I am Ph.D candidate in Computer Science at Politecnico di Milano,
advised by Prof. Matteo Matteucci and Dr. Jonathan Masci.

During my Ph.D I was also a research intern at NVIDIA and NNAISENSE.
Previously, I proudly worked at the development of Horus.



My research focuses on representation learning and meta-learning.

I am currently interested in understanding meta-learning algorithms and scaling them to complex heterogenous tasks and multimodal distributions. My long term research mission is to understand and build intelligent modular systems that can solve new problems with very weak supervision and few data by re-using and improving previously acquired skills.

Although I mainly work on computer vision problems, I have always been fascinated by Game Theory and I have recently gained an interest in Multi-Agent Reinforcement Learning (MARL). In particular, I am interested in the study of the learning dynamics of multiple agents and the emergence of cooperative behaviors.

Featured Work

MatrixLSTM Overview

We reconstruct a dense feature representation from sparse events using a grid of LSTM cells so that we could apply standard frame-based CNNs architectures for tasks such as image recognition and optical flow.

Led by Marco Cannici, joint with myself, Andrea Romanoni and Matteo Matteucci

STAC overview

We condition team members over signals implementing a coordination-device via hyper-networks to induce cooperative behaviors and learn to play correlated equilibria.

Joint work with Andrea Celli, Raffaele Bongo and Nicola Gatti

Async Conv Overview
Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras
Event-based Vision and Smart Cameras CVPR Workshop, 2019
(Best Paper Award)

We propose a novel approach to passing event-data through a CNN that respects the asynchronous nature of DVS sensors.

Led by Marco Cannici, joint with myself, Andrea Romanoni and Matteo Matteucci

Attention Event Overview

We propose two attentive models for event-based vision: an algorithm that tracks events activity within the field of view to locate regions of interest and a fully differentiable attention procedure based on DRAW neural model.

Led by Marco Cannici, joint with myself, Andrea Romanoni and Matteo Matteucci

ReConvNet overview
ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation
The DAVIS Challenge on Video Object Segmentation - CVPR Workshop, 2018

We consider Video Object Segmentation from a Meta-Learning perspective where each task consists of segmenting objects in a video given a single annotation. We learn how to adapt the activations of a neural network to segment a given object via two modulation networks conditioned on the available information at test time.

NAIS-Net overview

We propose a non-autonomous architecture where each block is derived from a time-invariant non-autonomous dynamical system. Each block is asymptotically stable and can be unrolled indefinitely upon convergence to an input-dependent attractor.

Reseg overview
ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation
DeepVision CVPR Workshop, 2016 - (Best Paper Award)

We propose to use recurrent layers (ReNet) to capture global and local context in images and improve semantic segmentation performance.

M.Sc. Thesis overview

My neural baptism: recurrent and convolutional networks for semantic segmentation.


In my spare time, I practice yoga, read novels, and play guitar. When I need to relax, I cook. When I'm not lazy, I go hiking and trekking. When I am sad or happy, I sing. When I can, I travel the world to learn about new cultures.

If you want to discuss anything or just connect, please drop me an email or reach me on Twitter or Linkedin!