Zhiyong Gao

Latest

• An End-to-End Learning Framework for Video Compression
• MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
• Content adaptive and error propagation aware deep video compression
• Deep Non-local Kalman Network for Video Compression Artifact Reduction
• End-to-End Optimized ROI Image Compression
• In-loop perceptual model-based rate-distortion optimization for HEVC real-time encoder
• A Novel Deep Progressive Image Compression Framework
• Depth-Aware Video Frame Interpolation
• DVC: An End-to-End Deep Video Compression Framework
• Efficient Variable Rate Image Compression with Multi-scale Decomposition Network
• Large Scale Near-duplicate Image Retrieval via Patch Embedding
• Video-based early Autism Detection via Temporal Pyramid Networks,
• Viewport-Adaptive 360-degree Video Coding
• A Wavelet-based Learning for Face Hallucination with Loop Architecture
• BAN, A Barcode Accurate Detection Network
• Deep Kalman Filtering Network for Video Compression Artifact Reduction
• High-Order Model and Dynamic Filtering for Frame Rate Up-Conversion
• KalmanFlow 2.0: Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering
• KalmanFlow: Efficient Kalman Filtering for Video Optical Flow
• Novel Integration of Frame Rate Up Conversion and HEVC Coding Based on Rate-Distortion Optimization
• Rcdfnn: Robust Change Detection Based on Convolutional Fusion Neural Network
• Video Stitching Based on Optical Flow
• A Novel Frame Rate Up Conversion Using Iterative Non-Local Means Interpolation
• Data generation for improving person re-identification
• Deep spatial-temporal fusion network for video-based person re-identification
• Edge Guided Salient Object Detection
• High-quality and real-time frame interpolation on heterogeneous computing system
• Iterative convolutional neural network for noisy image super-resolution
• Moving segmentation in HEVC compressed domain based on logistic regression
• Spatiotemporal salient object detection based on distance transform and energy optimization
• Frame Rate Up-Conversion Using Linear Quadratic Motion Estimation and Trilateral Filtering Motion Smoothing
• Principal Component Analysis-based Visual Saliency Detection
• Frame Rate Up-Conversion Method for Video Processing Applications