Search Results for author: Ahmad El-Sallab

Found 9 papers, 0 papers with code

ST-DETR: Spatio-Temporal Object Traces Attention Detection Transformer

no code implementations13 Jul 2021 Eslam Mohamed, Ahmad El-Sallab

We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames.

Moving Object Detection Object +1

MODETR: Moving Object Detection with Transformers

no code implementations21 Jun 2021 Eslam Mohamed, Ahmad El-Sallab

Several methods of incorporating motion cues with the Transformer model are explored, including two-stream RGB and Optical Flow (OF) methods, and multi-stream architectures that take advantage of sequence information.

Autonomous Driving Moving Object Detection +3

End-to-End 3D-PointCloud Semantic Segmentation for Autonomous Driving

no code implementations26 Jun 2019 Mohammed Abdou, Mahmoud Elkhateeb, Ibrahim Sobh, Ahmad El-Sallab

Imbalanced distribution of classes in the dataset is one of the challenges that face 3D semantic scene labeling task.

Autonomous Driving Scene Labeling +2

Optical Flow augmented Semantic Segmentation networks for Automated Driving

no code implementations11 Jan 2019 Hazem Rashed, Senthil Yogamani, Ahmad El-Sallab, Pavel Krizek, Mohamed El-Helw

We also make use of the ground truth optical flow in Virtual KITTI to serve as an ideal estimator and a standard Farneback optical flow algorithm to study the effect of noise.

Optical Flow Estimation Semantic Segmentation

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