Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Data-Efficient Crosswalk Segmentation from Overhead CCTV via Confidence- and Geometry-Guided Pseudo-Labeling
Abdirashid Omar, Jonghyuk Park
Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoint and appearance shift when…
cs.CV2026
UrbanCDNet: Appearance-Robust and Boundary-Aware Bitemporal Change Detection for Korean Urban Building Monitoring
Abdirashid Omar, Jonghyuk Park
Urban building change detection from bi-temporal aerial imagery is important for redevelopment monitoring, infrastructure management, and unauthorized-construction screening, but K…
cs.CV2026
CoSA: Correlation-Guided Change Attention with Learnable Residual Gating for Remote Sensing Change Detection
Abdirashid Omar, Jonghyuk Park
Remote sensing change detection (CD) from bi-temporal imagery is critical for applications such as urban monitoring, disaster assessment, and environmental management, yet robust l…