activity
20242026
collaborators

16 papers

cs.CV2026

Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation

Ali Zia, Muhammad Umer Ramzan, Abdelwahed Khamis +2

Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation…

cs.CV2026

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation

Ali Zia, Usman Ali, Abdul Rehman +5

Test-time adaptation (TTA) has emerged as a promising paradigm for mitigating distribution shifts in deep models. However, existing TTA approaches for anomaly segmentation remain l…

cs.LG2026

TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection

Farid Hazratian, Ali Zia, Hien Duy Nguyen

Out-of-distribution (OOD) robustness is difficult to diagnose when target-domain labels are unavailable. We consider a more restrictive source-only variant of unsupervised accuracy…

cs.CV2026

Implicit spatial-frequency fusion of hyperspectral and lidar data via kolmogorov-arnold networks

Zekun Long, Judy X. Yang, Jing Wang +3

Hyperspectral image (HSI) classification is challenging in complex scenes due to spectral ambiguity, spatial heterogeneity, and the strong coupling between material properties and…

cs.CV2026

Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection

Ali Zia, Usman Ali, Muhammad Umer Ramzan +3

Training-free video anomaly detection (VAD) has recently emerged as a scalable alternative to supervised approaches, yet existing methods largely rely on static prompting and geome…

cs.CV2026

Component-Aware Sketch-to-Image Generation Using Self-Attention Encoding and Coordinate-Preserving Fusion

Ali Zia, Muhammad Umer Ramzan, Usman Ali +3

Translating freehand sketches into photorealistic images remains a fundamental challenge in image synthesis, particularly due to the abstract, sparse, and stylistically diverse nat…