activity
20242026
collaborators

6 papers

cs.CV2026

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs

Mohamed Eltahir, Lama Ayash, Ali Habibullah +2

Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mitigation is to first select a…

cs.CV2026

VideoAtlas: Navigating Long-Form Video in Logarithmic Compute

Mohamed Eltahir, Ali Habibullah, Yazan Alshoibi +3

Extending language models to video introduces two challenges: representation, where existing methods rely on lossy approximations, and long-context, where caption- or agent-based p…

cs.CV2025

Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers

Mohamed Eltahir, Ali Habibullah, Lama Ayash +2

In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fus…

cs.CV2025

AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks

Mohamed Eltahir, Osamah Sarraj, Abdulrahman Alfrihidi +4

Video-to-text and text-to-video retrieval are dominated by English benchmarks (e.g. DiDeMo, MSR-VTT) and recent multilingual corpora (e.g. RUDDER), yet Arabic remains underserved,…

cs.CV2025

Multimodal Lengthy Videos Retrieval Framework and Evaluation Metric

Mohamed Eltahir, Osamah Sarraj, Mohammed Bremoo +5

Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively wit…

cs.CV2024

AllWeatherNet:Unified Image Enhancement for Autonomous Driving under Adverse Weather and Lowlight-conditions

Chenghao Qian, Mahdi Rezaei, Saeed Anwar +4

Adverse conditions like snow, rain, nighttime, and fog, pose challenges for autonomous driving perception systems. Existing methods have limited effectiveness in improving essentia…