1.A Richly Annotated Pedestrian Dataset for Person Retrieval in Real Surveillance Scenarios

2.Cross-Modal Attentional Context Learning for RGB-D Object Detection

3.Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval

4.A Novel Scheme Based on the Diffusion to Edge Detection

5. DCSR: Dilated Convolutions for Single Image Super-Resolution

6. Depth Super-Resolution via Joint Color-Guided Internal and External Regularizations

7.VRSA Net: VR Sickness Assessment Considering Exceptional Motion for 360° VR Video

8. A Convex Optimization Framework for Video Quality and Resolution Enhancement From Multiple Descriptions

9. On-Device Scalable Image-Based Localization via Prioritized Cascade Search and Fast One-Many RANSAC

10.VIDOSAT: High-Dimensional Sparsifying Transform Learning for Online Video Denoising