5 citations · 6 across the 3 of their papers we have counts for
7 papers · 1 filter
Estimating more camera poses for ego-centric videos is essential for VQ3D
Jinjie Mai, Chen Zhao, Abdullah Hamdi +2
Visual queries 3D localization (VQ3D) is a task in the Ego4D Episodic Memory Benchmark. Given an egocentric video, the goal is to answer queries of the form "Where did I last see o…
MVTN: Multi-View Transformation Network for 3D Shape Recognition
Abdullah Hamdi, Silvio Giancola, Bernard Ghanem
Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those methods learn different ways to aggregate informa…
AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
Abdullah Hamdi, Sara Rojas, Ali Thabet +1
Deep neural networks are vulnerable to adversarial attacks, in which imperceptible perturbations to their input lead to erroneous network predictions. This phenomenon has been exte…
IAN: Combining Generative Adversarial Networks for Imaginative Face Generation
Abdullah Hamdi, Bernard Ghanem
Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the training set and that enables sampling from th…
Towards Analyzing Semantic Robustness of Deep Neural Networks
Abdullah Hamdi, Bernard Ghanem
Despite the impressive performance of Deep Neural Networks (DNNs) on various vision tasks, they still exhibit erroneous high sensitivity toward semantic primitives (e.g. object pos…
SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
Abdullah Hamdi, Matthias Müller, Bernard Ghanem
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomou…