3 papers
cs.CV2026
LARE: Low-Attention Region Encoding for Text-Image Retrieval
Abdulmalik Alquwayfili, Faisal Almeshal, Jumanah Almajnouni +8
Image retrieval in crowded scenes is particularly challenging due to the salience bias of conventional visual encoders, which tend to focus on dominant objects while neglecting low…
cs.CV2026
Look Beyond Saliency: Low-Attention Guided Dual Encoding for Video Semantic Search
Faisal Aljehrai, Mohammed A. Alkhrashi, Alreem Almuhrij +6
Video semantic search in densely crowded scenes remains a challenging task due to visual encoders tendency to prioritize salient foreground regions while neglecting contextually im…
cs.CV2025
VelocityNet: Real-Time Crowd Anomaly Detection via Person-Specific Velocity Analysis
Fatima AlGhamdi, Omar Alharbi, Abdullah Aldwyish +3
Detecting anomalies in crowded scenes is challenging due to severe inter-person occlusions and highly dynamic, context-dependent motion patterns. Existing approaches often struggle…