G
Giuseppe Vecchio
Researcher at University of Catania
Publications - 6
Citations - 33
Giuseppe Vecchio is an academic researcher from University of Catania. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 1, co-authored 3 publications receiving 13 citations.
Papers
More filters
Journal ArticleDOI
MASK-RL: Multiagent Video Object Segmentation Framework Through Reinforcement Learning
TL;DR: A video object segmentation framework that leverages the combined advantages of user feedback for segmentation and gamification strategy by simulating multiple game players through a reinforcement learning (RL) model that reproduces human ability to pinpoint moving objects and using the simulated feedback to drive the decisions of a fully convolutional deep segmentation network.
Posted Content
SurfaceNet: Adversarial SVBRDF Estimation from a Single Image
TL;DR: In this paper, a patch-based generative adversarial network (GAN) is proposed to estimate spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image.
Journal ArticleDOI
Knowledge-based generative adversarial networks for scene understanding in Cultural Heritage
TL;DR: A method to drive the generation of realistic classical order images using GAN approaches anchored to semantic ontology domain representation is proposed to create automated methods for automatically classifying and successively retrieving photographic data leveraging the current breed of AI methods based on Deep Learning paradigm.
Journal ArticleDOI
Deep Reinforcement Learning for Multi-Agent Interaction
Ibrahim Ahmed,Cillian Brewitt,Ignacio Carlucho,Filippos Christianos,Mhairi Dunion,Elliot Fosong,Samuel Garcin,Shangmin Guo,Balint Gyevnar,Trevor A. McInroe,Georgios Papoudakis,Arrasy Rahman,Lukas Schafer,Massimiliano Tamborski,Giuseppe Vecchio,Cheng Wang,Stefano V. Albrecht +16 more
TL;DR: A broad overview of the ongoing research portfolio of the Autonomous Agents Research Group is provided and open problems for future directions are discussed.
Journal ArticleDOI
MIDGARD: A Simulation Platform for Autonomous Navigation in Unstructured Environments
Giuseppe Vecchio,Simone Palazzo,Dario Calogero Guastella,Ignacio Carlucho,Stefano V. Albrecht,Giovanni Muscato,Concetto Spampinato +6 more
TL;DR: MIDGARD differs from other major simulation platforms in that it proposes a highly configurable procedural landscape generation pipeline, which enables autonomous agents to be trained in diverse scenarios while reducing the efforts and costs needed to create digital content from scratch.