Low-Level Vision, Image Processing
Image Inpainting with Onion Convolutions
Accurate and Efficient Single Image Super-Resolution with Matrix Channel Attention Network
Second-order Camera-aware Color Transformation for Cross-domain Person Re-identification
CS-MCNet:A Video Compressive Sensing Reconstruction Network with Interpretable Motion Compensation
MCGKT-Net: Multi-level Context Gating Knowledge Transfer Network for Single Image Deraining
Degradation Model Learning for Real-World Single Image Super-resolution
Chromatic Aberration Correction Using Cross-Channel Prior in Shearlet Domain
Raw-Guided Enhancing Reprocess of Low-Light Image via Deep Exposure Adjustment
Robust High Dynamic Range (HDR) Imaging with Complex Motion and Parallax
Low-light Color Imaging via Dual Camera Acquisition
Frequency Attention Network: Blind Noise Removal for Real Images
Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
^Color Enhancement using Global Parameters and Local Features Learning
An Efficient Group Feature Fusion Residual Network for Image Super-Resolution
Adversarial Image Composition with Auxiliary Illumination
Overwater Image Dehazing via Cycle-Consistent Generative Adversarial Network
Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
Multi-scale Attentive Residual Dense Network for Single Image Rain Removal
FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization
Human Motion Deblurring using Localized Body Prior
Synergistic Saliency and Depth Prediction for RGB-D Saliency Detection
Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array
Deep Priors inside an Unrolled and Adaptive Deconvolution Model
Motion and Tracking
Adaptive Spatio-Temporal Regularized Correlation Filters for UAV-based Tracking
^Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation
Self-supervised Sparse to Dense Motion Segmentation
Recursive Bayesian Filtering for Multiple Human Pose Tracking from Multiple Cameras
Adversarial Refinement Network for Human Motion Prediction
Semantic Synthesis of Pedestrian Locomotion
Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
Visual Tracking by TridentAlign and Context Embedding
Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
A Two-Stage Minimum Cost Multicut Approach to Self-Supervised Multiple Person Tracking
Learning Local Feature Descriptors for Multiple Object Tracking
VAN: Versatile Affinity Network for End-to-end Online Multi-Object Tracking
COMET: Context-Aware IoU-Guided Network for Small Object Tracking
Adversarial Semi-Supervised Multi-Domain Tracking
Tracking-by-Trackers with a Distilled and Reinforced Model
^Motion Prediction Using Temporal Inception Module
A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking
Modeling Cross-Modal interaction in a Multi-detector, Multi-modal Tracking Framework
Dense Pixel-wise Micro-motion Estimation of Object Surface by using Low Dimensional Embedding of Laser Speckle Pattern.