Alessio is a Postdoctoral Research Assistant with the Centre for Intelligent Sensing and the School of Electronic Engineerging and Computer Science at Queen Mary University of London (QMUL), UK. In collaboration with and under the supervision of Prof. Andrea Cavallaro, Alessio currently investigates novel, robust, deployable multi-modal (audio-visual) models for human-to-robot handovers under the project "Collaborative Object Recognition, Shared Manipulation and Learning (CORSMAL)".
Alessio obtained his Ph.D. in Electronic Engineering, with the thesis titled "Local features for view matching across independently moving cameras", from Queen Mary University of London, UK, in September 2020.
Alessio is an IEEE Member and IEEE Signal Processing Society member, and a reviewer for international conferences and journals, including IEEE International Conference on Image Processing (ICIP), IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE International Conference on Pattern Recognition (ICPR), IEEE Transactions on Multimedia, IEEE Robotics and Automation Letters, IEEE Sensors Journal.
Research interests
Computer Vision | Machine and deep learning | Multi-modal fusion | Image and video processing | Perception for robotics
Most recent talk
Cross-Camera View-Overlap Recognition
International Workshop on Distributed Smart Cameras (24 October 2022)
at European Conference on Computer Vision (ECCV)
News
| 2023/01/01 | Joining and contributing for the next year into the project GraphNEx |
| 2022/12/07 | Lecture on interest points (from SIFT, binary descriptor to recent deep learning based methods) at the ECS709 Module: Introduction to Computer Vision (QMUL) |
| 2022/12/06 | Presenting the project CORSMAL and its achievements at the ARQ-Robotics Centre Research Day 2022 |
| 2022/10/21 | Released the data and code associated to the work on Cross-Camera View-Overlap Recognition |
| 2022/12/07 | Lecture on Deep Learning Models for Computer Vision at the ECS709 Module: Introduction to Computer Vision (QMUL) |
| 2022/09/14 | Presented a video demo of the project CORSMAL at IEEE International Conference on Development and Learning (ICDL 2022) |
| 2022/05/27 | Our paper "Audio-Visual Object Classification for Human-Robot Collaboration" has been ranked 4th for the most viewed posters and 22nd for the most downloaded papers at IEEE ICASSP 2022 |
| 2022/05/27 | Outstanding Reviewer Recognition at IEEE ICASSP 2022 (31 reviewers selected) |
| 2022/04/21 | Webpage of the chapter on Visual Adversarial Attacks and Defenses is now online! |
| 2022/03/28 | CORSMAL features as CHIST-ERA Open Science Success Story at the CHIST-ERA Projects Seminar 2022 |
Selected publications
- The CORSMAL benchmark for the prediction of the properties of containers, IEEE Access, vol. 10, 2022
- Audio-Visual Object Classification for Human-Robot Collaboration, IEEE ICASSP 2022
- A spatio-temporal multi-scale binary descriptor, IEEE Transactions on Image Processing 2020.
- Multi-view shape estimation of transparent containers, IEEE ICASSP 2020
- MORB: a multi-scale binary descriptor, IEEE ICIP 2018