Recurrent Multi-Frame Deraining : Combining Physics Guidance and Adversarial …

Existing video rain removal methods mainly focus on rain streak removal and are solely trained based on the synthetic data, which neglect more complex degradation factors, e.g., rain accumulation, …

PSGAN++ : Robust Detail-Preserving Makeup Transfer and Removal

In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup …

Source Data-Absent Unsupervised Domain Adaptation Through Hypothesis Transfer…

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to…

Anytime Recognition with Routing Convolutional Networks

Achieving an automatic trade-off between accuracy and efficiency for a single deep neural network is highly desired in time-sensitive computer vision applications. To achieve anytime prediction, ex…

Tensor Low-Rank Representation for Data Recovery and Clustering

Multi-way or tensor data analysis has attracted increasing attention recently, with many important applications in practice. This article develops a tensor low-rank representation (TLRR) method, wh…

Faster First-Order Methods for Stochastic Non-Convex Optimization on Riemanni…

3D-Aided Dual-Agent GANs For Unconstrained Face Recognition

Online Meta Adaptation for Fast Video Object Segmentation

Joint Rain Detection and Removal from a Single Image with Contextualized Deep…

Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm