• Publications
  • Influence
Single Image Dehazing via Multi-scale Convolutional Neural Networks
TLDR
We propose a multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps. Expand
  • 543
  • 136
  • PDF
Cluster-Based Co-Saliency Detection
TLDR
Co-saliency is used to discover the common saliency on the multiple images, which is a relatively underexplored area. Expand
  • 290
  • 64
  • PDF
Gated Fusion Network for Single Image Dehazing
TLDR
In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input by applying White Balance, Contrast Enhancing and Gamma Correction. Expand
  • 194
  • 37
  • PDF
Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation
TLDR
We propose a deep learning architecture, named M-Net, which solves the OD and OC segmentation jointly in a one-stage multi-label system. Expand
  • 242
  • 33
  • PDF
Depth Enhanced Saliency Detection Method
TLDR
We propose a saliency detection method using the additional depth information to represent the nature advantage in 3D image. Expand
  • 102
  • 33
  • PDF
Low-Rank Tensor Constrained Multiview Subspace Clustering
TLDR
We introduce a low-rank tensor constraint to explore the complementary information from multiple views and, accordingly, establish a novel method called Low-rank Tensor constrained Multiview Subspace Clustering (LT-MSC). Expand
  • 155
  • 27
  • PDF
Self-Adaptively Weighted Co-Saliency Detection via Rank Constraint
TLDR
We provide a general saliency map fusion framework, which exploits the relationship of multiple saliency cues and obtains the self-adaptive weight to generate the final saliency/co-saliency map. Expand
  • 118
  • 26
  • PDF
Total Variation Regularized RPCA for Irregularly Moving Object Detection Under Dynamic Background
TLDR
We propose TVRPCA to handle the scenarios with complex dynamic backgrounds, and slowly moving or lingering objects, based on the assumption that the moving foreground objects should be contiguous in both space and time. Expand
  • 101
  • 26
  • PDF
Diversity-induced Multi-view Subspace Clustering
TLDR
We extend the self-representation based subspace clustering to multiview setting, and propose a Diversity-induced Multi-view Subspace Clustering method, which outperforms the state-of-the-art methods. Expand
  • 212
  • 24
  • PDF
Image Deblurring via Extreme Channels Prior
TLDR
In this paper, we propose a novel BCP based on the observation that these bright pixels in the clear images are not likely to be bright after the blur process. Expand
  • 112
  • 23
  • PDF