no code implementations • 6 Apr 2020 • Alessio Elmi, Davide Mazzini, Pietro Tortella
We present an approach to perform 3D pose estimation of multiple people from a few calibrated camera views.
Ranked #9 on 3D Multi-Person Pose Estimation on Panoptic (using extra training data)
no code implementations • 22 May 2019 • Davide Mazzini, Raimondo Schettini
We propose a network architecture to perform efficient scene understanding.
no code implementations • 19 Dec 2018 • Simone Bianco, Davide Mazzini, Paolo Napoletano, Raimondo Schettini
In this work we propose a new deep multibranch neural network to solve the tasks of artist, style, and genre categorization in a multitask formulation.
no code implementations • 19 Jul 2018 • Davide Mazzini
We propose a Neural Network named Guided Upsampling Network which consists of a multiresolution architecture that jointly exploits high-resolution and large context information.
no code implementations • 10 Jan 2017 • Simone Bianco, Marco Buzzelli, Davide Mazzini, Raimondo Schettini
In this paper we propose a method for logo recognition using deep learning.
Ranked #1 on Image Classification on FlickrLogos-32