Meeting sessions will be held via Zoom. Links will be posted here and access passwords emailed to all registered participants.
Day 1
14.30 – 14.40
14.40 – 15.20
Claudio Battiloro, "Distributed Online Tensor Completion over Networks of Cooperative Learners", Università di Roma La Sapienza, [video]
Francesca Pistilli, "GraphPointNet: Graph Convolutional Neural Network for Point Cloud Denoising", Politecnico di Torino, [video]
15.20 – 16.20
Deep neural networks and fully supervised training has had tremendous success over the last decade, and in no small part due to the large-scale availability of annotated ground-truthed data. Nevertheless, in many applications where new, unanticipated and heretofore unseen scenarios arise, we are unlikely to find sufficient data due to acquisition costs or real-time considerations, severely limiting the scope of existing supervised learning methods. In this talk we will motivate the problems we face in this context by drawing upon examples from our work on zero-shot recognition, crowd-sourcing, and feedback-limited sequential learning.
[slides]
Venkatesh Saligrama is a faculty member in the Department of Electrical and Computer Engineering, the Department of Computer Science (by courtesy), and a founding member of the Faculty of Computing and Data Sciences at Boston University. He holds a PhD from MIT. His research interests are in Machine Learning and its applications. He has edited a book on Networked Sensing, Information and Control. He has served as an Associate Editor for IEEE Transactions on Information Theory, IEEE Transactions on Signal Processing and edited special issues and books on Networked Sensing, Detection and Estimation. He has served as a Chair of Big Data Special Interest Group for IEEE SPS society. He is an IEEE Fellow and recipient of several awards including the Presidential Early Career Award (PECASE), ONR Young Investigator Award, the NSF Career Award and a NIPS 2014 workshop best student paper award on Analysis of Ranking Data. More information about his work is available at http://sites.bu.edu/data.
Break 16.20–16.30
Day 2
9.00 – 10.30
L. Abady, M. Barni, B. Tondi, "GAN-based generation of synthetic multispectral images"
S. Pino, P. Bestagini, S. Tubaro, M.J. Carman, "Comparing explainers for deepfake detection"
D. Cozzolino, L. Verdoliva, "ID-Reveal: Identity-aware DeepFake Video Detection"
F. Lago, C. Pasquini, G. Boato, "More real than real: a study on human perception of synthetic faces"
D. Baracchi, D. Shullani, M. Iuliani, D. Giani, A. Piva, "Camera Obscura: exploiting in-camera processing for image counter forensic"
Break 10.30–10.40
12.10 – 12.40
12.40 – 13.00