Pietro Morerio
Post Doc
Post Doc

About
I received my B. Sc. and M. Sc. in Physics from the University of Milan (Italy) in 2007 and 2010 (summa cum laude). I was Research Fellow at the University of Genoa (Italy) from 2011 to 2012, working in Video Analysis for Interactive Cognitive Environments. I pursued a PhD in Computational Intelligence at the same institution in 2016. Currently I am a Postdoctoral Researcher at Istituto Italiano di Tecnologia (IIT). My research focuses on machine learning, deep learning and computer vision.
Interests
computer vision machine learning AI deep learning multimodal learningIIT Publications
- 2021
-
Audio-Visual Localization by Synthetic Acoustic Image Generation
Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) -
Distillation Multiple Choice Learning for Multimodal Action Recognition
IEEE Winter Conference on Applications of Computer Vision -
DOI
Excitation Dropout: Encouraging Plasticity in Deep Neural Networks
International Journal of Computer Vision -
Intra-Camera Supervised Person Re-Identification
International Journal of Computer Vision -
Single Image Human Proxemics Estimation for Visual Social Distancing
IEEE Winter Conference on Applications of Computer Vision - 2020
-
DOI
Audio-visual model distillation using acoustic images
Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020, pp. 2843-2852 -
Compact CNN Structure Learning by Knowledge Distillation
International Conference on Pattern Recognition, pp. 8 -
Complex-Object Visual Inspection: Empirical Studies on A Multiple Lighting Solution
International Conference on Pattern Recogntion -
DOI
Generative pseudo-label refinement for unsupervised domain adaptation
Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020, pp. 3119-3128 -
DOI
Learning with Privileged Information via Adversarial Discriminative Modality Distillation
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, (no. 10), pp. 2581-2593 -
DOI
Leveraging Acoustic Images for Effective Self-supervised Audio Representation Learning
Lecture Notes in Computer Science, vol. 12367 LNCS, pp. 119-135 -
DOI
Predicting Intentions from Motion: The Subject-Adversarial Adaptation Approach
International Journal of Computer Vision, vol. 128, (no. 1), pp. 220-239 - 2019
-
DOI
Cross-modal Learning by Hallucinating Missing Modalities in RGB-D Vision
Multimodal Scene Understanding: Algorithms, Applications and Deep Learning, pp. 383-401, Publisher: Elsevier -
DOI
Scalable and compact 3D action recognition with approximated RBF kernel machines
Pattern Recognition, vol. 93, pp. 25-35 -
DOI
Unsupervised Domain-Adaptive Person Re-Identification Based on Attributes
Proceedings - International Conference on Image Processing, ICIP, vol. 2019-September, pp. 4110-4114 - 2018
-
DOI
Adversarial Feature Augmentation for Unsupervised Domain Adaptation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 5495-5504 -
Dropout as a low-rank regularizer for matrix factorization
International Conference on Artificial Intelligence and Statistics, AISTATS 2018, pp. 435-444 -
Minimal-entropy correlation alignment for unsupervised deep domain adaptation
6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings -
DOI
Modality distillation with multiple stream networks for action recognition
Lecture Notes in Computer Science, vol. 11212 LNCS, pp. 106-121 -
DOI
Video Gesture Analysis for Autism Spectrum Disorder Detection
Proceedings - International Conference on Pattern Recognition, vol. 2018-August, pp. 3421-3426 - 2017
-
DOI
A compact kernel approximation for 3D action recognition
Lecture Notes in Computer Science, vol. 10484 LNCS, pp. 211-222 -
DOI
Curriculum Dropout
Proceedings of the IEEE International Conference on Computer Vision, vol. 2017-October, pp. 3564-3572 -
DOI
Hand pose recognition in First Person Vision through graph spectral analysis
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 1872-1876 -
DOI
Left/right hand segmentation in egocentric videos
Computer Vision and Image Understanding, vol. 154, pp. 73-81 -
DOI
When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2017-July, pp. 1251-1258 - 2016
-
DOI
A Cognitive Control-Inspired Approach to Object Tracking
IEEE Transactions on Image Processing, vol. 25, (no. 6), pp. 2697-2711 - 2015
-
DOI
A dynamic approach and a new dataset for hand-detection in first person vision
Lecture Notes in Computer Science, vol. 9256, pp. 274-287 -
DOI
Bio-inspired relevant interaction modelling in cognitive crowd management
Journal of Ambient Intelligence and Humanized Computing, vol. 6, (no. 2), pp. 171-192 -
DOI
Filtering SVM frame-by-frame binary classification in a detection framework
Proceedings - International Conference on Image Processing, ICIP, vol. 2015-December, pp. 2552-2556 -
DOI
Optimizing superpixel clustering for real-time egocentric-vision applications
IEEE Signal Processing Letters, vol. 22, (no. 4), pp. 469-473 -
DOI
The evolution of first person vision methods: A survey
IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, (no. 5), pp. 744-760 -
DOI
Towards a unified framework for hand-based methods in First Person Vision
2015 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2015 - 2014
-
A generative superpixel method
FUSION 2014 - 17th International Conference on Information Fusion -
DOI
Exploiting an event based state estimator in presence of sparse measurements in video analytics
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 1871-1875 - 2013
-
A bio-inspired knowledge representation method for anomaly detection in cognitive Video Surveillance systems
Proceedings of the 16th International Conference on Information Fusion, FUSION 2013, pp. 242-249 -
DOI
Event definition for stability preservation in bio-inspired cognitive crowd monitoring
2013 18th International Conference on Digital Signal Processing, DSP 2013 -
Hand detection in First Person Vision
Proceedings of the 16th International Conference on Information Fusion, FUSION 2013, pp. 1502-1507 -
Run length encoded Dynamic Bayesian Networks for probabilistic interaction modeling
European Signal Processing Conference - 2012
-
A multi-sensor cognitive approach for active security monitoring of abnormal overcrowding situations
15th International Conference on Information Fusion, FUSION 2012, pp. 2215-2222 -
DOI
Distributed cognitive radio architecture with automatic frequency switching
2012 IEEE Workshop on Complexity in Engineering, COMPENG 2012 - Proceedings, pp. 139-142 -
DOI
Early fire and smoke detection based on colour features and motion analysis
Proceedings - International Conference on Image Processing, ICIP, pp. 1041-1044 -
DOI
People count estimation in small crowds
Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012, pp. 476-480 -
DOI
Performance evaluation of multi-camera visual tracking
Proceedings - 2012 IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2012, pp. 464-469
Load more