Search Results for author: Tarek El-Gaaly

Found 7 papers, 2 papers with code

Detecting Deep-Fake Videos from Appearance and Behavior

no code implementations29 Apr 2020 Shruti Agarwal, Tarek El-Gaaly, Hany Farid, Ser-Nam Lim

Synthetically-generated audios and videos -- so-called deep fakes -- continue to capture the imagination of the computer-graphics and computer-vision communities.

Metric Learning

3D Object Recognition with Ensemble Learning --- A Study of Point Cloud-Based Deep Learning Models

1 code implementation17 Apr 2019 Daniel Koguciuk, Łukasz Chechliński, Tarek El-Gaaly

In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification and detection.

3D Classification 3D Object Detection +4

BinGAN: Learning Compact Binary Descriptors with a Regularized GAN

1 code implementation NeurIPS 2018 Maciej Zieba, Piotr Semberecki, Tarek El-Gaaly, Tomasz Trzcinski

In this paper, we propose a novel regularization method for Generative Adversarial Networks, which allows the model to learn discriminative yet compact binary representations of image patches (image descriptors).

Dimensionality Reduction Retrieval

Convolutional Models for Joint Object Categorization and Pose Estimation

no code implementations16 Nov 2015 Mohamed Elhoseiny, Tarek El-Gaaly, Amr Bakry, Ahmed Elgammal

In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable of capturing pose information over different categories of objects.

Object Object Categorization +2

Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance

no code implementations9 Aug 2015 Amr Bakry, Mohamed Elhoseiny, Tarek El-Gaaly, Ahmed Elgammal

How does fine-tuning of a pre-trained CNN on a multi-view dataset affect the representation at each layer of the network?

Factorization of View-Object Manifolds for Joint Object Recognition and Pose Estimation

no code implementations23 Mar 2015 Haopeng Zhang, Tarek El-Gaaly, Ahmed Elgammal, Zhiguo Jiang

Due to large variations in shape, appearance, and viewing conditions, object recognition is a key precursory challenge in the fields of object manipulation and robotic/AI visual reasoning in general.

Object Object Recognition +2

Measuring Atmospheric Scattering from Digital Images of Urban Scenery using Temporal Polarization-Based Vision

no code implementations14 Jul 2014 Tarek El-Gaaly, Joshua Gluckman

In doing so, we also present a method of recovering an accurate depthmap of the scene and recovering the scene without the visual effects of haze.

Cannot find the paper you are looking for? You can Submit a new open access paper.