International Doctorate in ICT
Job offer info:
Email |
CV
Social:
Google Scholar |
LinkedIn |
Twitter |
Github
My name is Alessandro Simoni. I am a PhD Student enrolled in the International Doctorate in ICT program at the AImageLab research group of the University of Modena and Reggio Emilia (Italy), under the supervision of Prof. Roberto Vezzani.
My PhD thesis defense is expected to be in March 2024.
My research activities are focused on Computer Vision and Deep Learning applied to Collaborative Robotics scenarios, more precisely in topics like 3D Object Reconstruction and 3D Human/Robot Pose Estimation.
I'm actively involved in a project in collaboration with Toyota Motore Europe and Toyota Woven City related to 3D Human-Centric Scene Understanding in outdoor video surveillance scenarios.
I'm also supporting a project with Prometeia involving the 3D Vehicle Reconstruction in real-world scenarios through NeRF-based approaches.
Authored publications:
Alessandro Simoni, Stefano Pini, Guido Borghi, Roberto Vezzani
IROS 2022 + IEEE Robotics and Automation Letters - Oral
arXiv | bibtex | webpage | dataset | code | slides
Thanks to a novel 3D pose representation composed of two decoupled heatmaps, efficient deep networks from the 2D HPE domain can be adapted to accurately compute 3D joints locations in world coordinates. Moreover, depth maps are used to bridge the gap between synthetic and real data.
Alessandro Simoni, Stefano Pini, Roberto Vezzani, Rita Cucchiara
3DV 2021 - Poster
arXiv | bibtex | code | poster | slides | presentation (video)
A multi-category mesh reconstruction framework infers the textured mesh of objects, learning category-specific priors in an unsupervised manner and obtaining smooth shapes with a dynamic mesh subdivision approach.
Alessandro Simoni, Andrea D'Eusanio, Stefano Pini, Guido Borghi, Roberto Vezzani
VISAPP 2021 - Oral
paper | bibtex | slides | presentation (video)
A multi-task framework combines visual features and keypoint localization features in order to improve car model classification accuracy.
Alessandro Simoni, Luca Bergamini, Andrea Palazzi, Simone Calderara, Rita Cucchiara
ICPR 2020 - Poster
arXiv | bibtex | code | poster | slides | presentation (video)
A two-stage approach in which interpretable information are exploited by a novel view synthesis architecture in order to reproduce the future visual appearance of vehicles in an urban scene.
Co-authored publications:
Davide Di Nucci, Alessandro Simoni, Matteo Tomei, Luca Ciuffreda, Roberto Vezzani, Rita Cucchiara
ICIAP 2023 - Oral
A novel synthetic benchmark, named CarPatch, for the NeRF use case of vehicle inspection. It contains multiple-view images annotated with intrinsic and extrinsic camera parameters, the corresponding depth maps and semantic segmentation masks of car components.
Andrea D'Eusanio, Alessandro Simoni, Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara
Pattern Recognition Letters (PRL), 2023
An unsupervised approach used to train a Transformer-based architecture that learns to detect dynamic hand gestures in a continuous temporal sequence.
Andrea D'Eusanio, Stefano Pini, Guido Borghi, Alessandro Simoni, Roberto Vezzani
ICIAP 2021 - Poster
An unsupervised approach used to train a Transformer-based architecture that learns to detect dynamic hand gestures in a continuous temporal sequence.
Ariel Caputo, Andrea Giacchetti, Simone Soso, Deborah Pintani, Andrea D'Eusanio, Stefano Pini, Guido Borghi, Alessandro Simoni, Roberto Vezzani, Rita Cucchiara, et al.
Computers & Graphics, 2021
A Transformer-based architecture and a Finite State Machine (FSM) are able to detect and classify a gesture. One of the proposals in the SHREC2021 contest.
Luca Bergamini, Stefano Pini, Alessandro Simoni, Roberto Vezzani, Simone Calderara, Rick B. D'Eath, Robert B. Fisher
VISAPP 2021 - Poster
Given a large annotated pig dataset, long-term pig behavior analysis is possible, even though estimates from individual frames can be noisy.
Andrea D'Eusanio, Alessandro Simoni, Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara
3DV 2020 - Poster
A Transformer-based architecture that is able to recognize dynamic hand gestures exploiting information from a single active depth sensor (depth maps and surface normals).
Andrea D'Eusanio, Alessandro Simoni, Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara
Informatics, 2020
A multimodal combination of CNNs whose input is represented by RGB, depth and infrared images, achieving a good level of light invariance, a key element in vision-based in-car systems.
IEEE International Conference on Robotics and Automation (ICRA)
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
IEEE International Conference on Pattern Recognition (ICPR)
IEEE Robotics and Automation Letters (RA-L)
Towards a Complete Analysis of People: From Face and Body to Clothes (T-CAP)
International Workshop and Challenge on People Analysis (WCPA)
Advanced Course on Data Science and Machine Learning - ACDL 2021, Certosa di Pontignano (SI), Italy (certificate)
International Computer Vision Summer School - ICVSS 2022, Scicli (RG), Italy (certificate)
ELLIS Summer School on Large-Scale AI for Research and Industry - 2023, Modena (MO), Italy (certificate)