M
Moin Nabi
Researcher at University of Trento
Publications - 69
Citations - 2994
Moin Nabi is an academic researcher from University of Trento. The author has contributed to research in topics: Deep learning & Commonsense reasoning. The author has an hindex of 18, co-authored 69 publications receiving 1924 citations. Previous affiliations of Moin Nabi include Istituto Italiano di Tecnologia.
Papers
More filters
Posted Content
Differentially Private Federated Learning: A Client Level Perspective
TL;DR: The aim is to hide clients' contributions during training, balancing the trade-off between privacy loss and model performance, and empirical studies suggest that given a sufficiently large number of participating clients, this procedure can maintain client-level differential privacy at only a minor cost in model performance.
Proceedings ArticleDOI
Abnormal event detection in videos using generative adversarial nets
TL;DR: In this paper, the authors use GANs to learn an internal representation of the scene normality and then compare the real data with both the appearance and motion representations reconstructed by the GAN and abnormal areas are detected by computing local differences.
Proceedings ArticleDOI
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
TL;DR: Dynamic Generative Memory (DGM) as mentioned in this paper relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking and proposes a dynamic network expansion mechanism that ensures sufficient model capacity to accommodate for continually incoming tasks.
Proceedings ArticleDOI
Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection
TL;DR: In this article, the authors proposed to measure local abnormality by combining semantic information (inherited from existing CNN models) with low-level optical flow, which can be used without the fine-tuning phase.
Proceedings ArticleDOI
Training Adversarial Discriminators for Cross-Channel Abnormal Event Detection in Crowds
TL;DR: Generative Adversarial Nets (GANs), which are trained to generate only the normal distribution of the data, are proposed, which outperforms previous state-of-the-art methods in both the frame-level and the pixel-level evaluation.