-
Article
Texture compensation with multi-scale dilated residual blocks for image denoising
Deep convolutional neural networks have achieved great success for image denoising recently. However, increasing the depth of the neural network cannot significantly boost the performance of the algorithms for...
-
Chapter and Conference Paper
HaGAN: Hierarchical Attentive Adversarial Learning for Task-Oriented Dialogue System
Task-oriented dialogue system is commonly formulated as a reinforcement learning problem. A reward served as a learning objective is offered at the end of the generated dialogue to help optimize the system. A...
-
Chapter and Conference Paper
Learning Local Feature Descriptors with Quadruplet Ranking Loss
In this work, we propose a novel deep convolutional neural network (CNN) with quadruplet ranking loss to learn local feature descriptors. The proposed model receives quadruplets of two corresponding patches an...
-
Chapter and Conference Paper
A Non-local Method for Robust Noisy Image Completion
The problem of noisy image completion refers to recovering an image from a random subset of its noisy intensities. In this paper, we propose a non-local patch-based algorithm to settle the noisy image completi...
-
Chapter and Conference Paper
Graph Based Energy for Active Object Removal
In this paper, we present a system for completing the blank hole in an image list or a video sequence, which can be used in movie-making industry to produce some special montage effect. To achieve this, we app...
-
Chapter and Conference Paper
An Improved Foreground Extraction Approach
This paper describes an approach to expose the salient visual information from raw sensory data stream. At first, a general framework of media application is introduced. Then, based on the implementation of an...