works on

From the 1 of 22 linked papers with an AI index.

activity
20242026
collaborators

22 papers

cs.CV2026

Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

Mohamed Nagy, Naoufel Werghi, Jorge Dias +1

Polycepta introduces a recursive, object‑centric appearance state estimator for multi‑object tracking that continuously updates each object's visual representation, leading to fewe…

cs.CV2026

Towards Accurate State Estimation: Motion Dynamics Kalman Filter for 3D Multi-Object Tracking

Mohamed Nagy, Naoufel Werghi, Bilal Hassan +2

Precise 3D state estimation in multi-object tracking (MOT) is critical for self-driving cars, particularly for objects occluded. Motion modeling in the Kalman filter with a constan…

cs.CV2026

Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray

Yonathan Michael, Mohamad Alansari, Natnael Takele +2

Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray baggage screening, however, threa…

cs.CV2026

SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking

Mohamad Alansari, Yonathan Michael, Hasan AlMarzouqi +3

We revisit the memory update mechanism in SAM2-based visual object tracking and identify confidence-only mask selection as the dominant cause of drift under occlusion, rapid motion…

cs.RO2026

Collaborative Trajectory Prediction via Late Fusion

Nadya Abdel Madjid, Murad Mebrahtu, Zakhar Yagudin +5

Predicting future trajectories of surrounding traffic agents is critical for safe autonomous navigation and collision avoidance. Despite all advances in the trajectory forecasting…

cs.CR2026

Spike-PTSD: A Bio-Plausible Adversarial Example Attack on Spiking Neural Networks via PTSD-Inspired Spike Scaling

Lingxin Jin, Wei Jiang, Maregu Assefa Habtie +5

Spiking Neural Networks (SNNs) are energy-efficient and biologically plausible, ideal for embedded and security-critical systems, yet their adversarial robustness remains open. Exi…