activity
20192023
most citedTowards a Unified Approach to Single Image Deraining and Dehazing

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2023

Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias

Zhihao Shi, Jie Wang, Fanghua Lu +5

Node representation learning on attributed graphs -- whose nodes are associated with rich attributes (e.g., texts and protein sequences) -- plays a crucial role in many important d…

cs.CL2022

Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings

Jie Wang, Zhanqiu Zhang, Zhihao Shi +3

Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE). Many existing s…

cs.CV20211 cited

Towards a Unified Approach to Single Image Deraining and Dehazing

Xiaohong Liu, Yongrui Ma, Zhihao Shi +2

We develop a new physical model for the rain effect and show that the well-known atmosphere scattering model (ASM) for the haze effect naturally emerges as its homogeneous continuo…

cs.CV2021

Learning for Unconstrained Space-Time Video Super-Resolution

Zhihao Shi, Xiaohong Liu, Chengqi Li +4

Recent years have seen considerable research activities devoted to video enhancement that simultaneously increases temporal frame rate and spatial resolution. However, the existing…

cs.CV2020

Video Frame Interpolation via Generalized Deformable Convolution

Zhihao Shi, Xiaohong Liu, Kangdi Shi +2

Video frame interpolation aims at synthesizing intermediate frames from nearby source frames while maintaining spatial and temporal consistencies. The existing deep-learning-based…

cs.CV2019

GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing

Xiaohong Liu, Yongrui Ma, Zhihao Shi +1

We propose an end-to-end trainable Convolutional Neural Network (CNN), named GridDehazeNet, for single image dehazing. The GridDehazeNet consists of three modules: pre-processing,…