Picture for Mohamed Yousef

Mohamed Yousef

Enhancing image captioning with depth information using a Transformer-based framework

Add code
Jul 24, 2023
Viaarxiv icon

No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection

Add code
Mar 19, 2022
Figure 1 for No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection
Figure 2 for No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection
Figure 3 for No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection
Figure 4 for No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection
Viaarxiv icon

OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold

Add code
Jun 12, 2020
Figure 1 for OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
Figure 2 for OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
Figure 3 for OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
Figure 4 for OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
Viaarxiv icon

Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks

Add code
Dec 31, 2018
Figure 1 for Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
Figure 2 for Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
Figure 3 for Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
Figure 4 for Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
Viaarxiv icon