Publications
![Your Image](../images/toddler_teaser.png)
ToddlerDiffusion: Flash Interpretable Controllable Diffusion Model
E Mohamed, L Zhao, Tao Hu, M Cord, P Perez, M Elhouseiny.
Under Review.
![Your Image](../images/sketch2skitch.png)
Sketch2Stitch: GANs for Abstract Sketch-Based Dress Synthesis
F Khan, D Morelli, E Mohamed, M Cornia, R Cucchiara, M Elhoseiny
Under Review.
![Your Image](../images/imgcaptioner2.png)
ImageCaptioner$^2$: Image Captioner for Image Captioning Bias Amplification Assessment
E Mohamed, P Sun, Li Erran Li, M Elhoseiny
Under Review.
![Your Image](../images/cot3D_anim.gif)
CoT3DRef: Chain‐of‐Thoughts Data‐Efficient 3D Visual Grounding
E Mohamed, M Ayman, M Ahmed, H Slim, M Elhouseiny.
ICLR 2024.
![Your Image](../images/hrs_teaser.png)
HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models
E Mohamed, P Sun, X Shen, F Khan, L Erran, M Elhoseiny.
ICCV 2023.
![Your Image](../images/LAR_teaser.png)
Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding
E Mohamed, Y Alsaedy, M Elhouseiny.
NeurIPS 2022.
![Your Image](../images/MTL_Trans_teaser.gif)
MTL-TransMODS: Cascaded Multi-Task Learning for Moving Object Detection and Segmentation with Unified Transformers
E Mohamed, A El-sallab.
NeurIPS workshop 2021.
![Your Image](../images/EMCA_teaser.png)
EMCA: Efficient Multiscale Channel Attention Module
E Mohamed, A El-sallab, M Rashwan.
IEEE Access 2022.
![Your Image](../images/GOD_Fisheye.gif)
Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline
H Rashed, E Mohamed, G Sistu, VR Kumar, C Eising, A El-Sallab, S Yogamani.
WACV 2020.
![Your Image](../images/insta_yolo_teaser.png)
INSTA-YOLO: Real Time Instance Segmentation based on YOLO
E Mohamed, A Shaker, A El-Sallab, M Hadhoud.
ICML workshop 2020.
![Your Image](../images/saptial_temporal_teaser.png)
Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentation
E Mohamed, A El-sallab.
IEEE ITSC 2021.
![Your Image](../images/InstanceMotSeg.png)
Monocular Instance Motion Segmentation for Autonomous Driving: KITTI InstanceMotSeg Dataset and Multi-task Baseline
E Mohamed, M Ewaisha, M Siam, H Rashed, S Yogamani, W Hamdy, M El-Dakdouky, A El-Sallab.
IEEE IV 2021.
![Your Image](../images/ST-DETR.png)
ST-DETR: Spatio-Temporal Object Traces Attention Detection Transformer
E Mohamed, A El-sallab.
ICML workshop 2021.
![Your Image](../images/MODETR.png)
MODETR: Moving Object Detection with Transformers
E Mohamed, A El-sallab.
NeurIPS workshop 2020.
![Your Image](../images/content_caching.png)
End-to-End Deep Learning Proactive Content Caching Framework
E Mohamed, H Ben-Ammar, H M Eraqi, S G Aly, T Elbatt, Y Ghamri-Doudane.
Globecom 2022.
![Your Image](../images/pkcam.png)
PKCAM: Previous Knowledge Channel Attention Module
E Mohamed, A El-sallab, M Rashwan.
NeurIPS workshop 2021.
![Your Image](../images/end_end.png)
End-to-End Deep Path Planning and Automatic Emergency Braking Camera Cocoon-based Solution
E Mohamed, M Abdou, OA Nasr.
NeurIPS workshop 2019.