This paper explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, we apply a convolutional neural network approach on RGB videos and extend it to three dimensional convolutions. Thi...

Resolution decrease and motion blur are two typical image degradation processes that usually addressed by deep networks, specifically convolutional neural networks (CNNs). However, since real images obtained through multiple degradations, the vast majority of current CNN methods employ a single process inevitably need to be improved account for effects. In this work, motivated decoupling multip...

Convolutional neural networks excel in image recognition tasks, but this comes at the cost of high computational and memory complexity. To tackle this problem, [1] developed a tensor factorization framework to compress fully-connected layers. In this paper, we focus on compressing convolutional layers. We show that while the direct application of the tensor framework [1] to the 4-dimensional ke...

Our goal is to classify 3D models directly using convolutional neural network. Most of existing approaches rely on a set of human-engineered features. We use 3D convolutional neural network to let the network learn the features over 3D space to minimize classification error. We trained and tested over ShapeNet dataset with data augmentation by applying random transformations. We made various vi...

In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers act as the feature extractor, which capture the abstraction of ...

Convolutional neural networks (CNNs) are a popular and highly performant choice for pixel-wise dense prediction or generation. One of the commonly required components in such CNNs is a way to increase the resolution of the network’s input. The lower resolution inputs can be, for example, low-dimensional noise vectors in image generation [7] or low resolution (LR) feature maps for network vis...

In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts. Our method performs MCTS in batches, explores the Monte Carlo search tree using Thompson sampling and a convolutional network, and evaluates convnet-based rollouts on the GPU. We achieve strong win rates against open source Go programs and attain competitive results against state of the art ...

This paper deals with the unification of local and non-local signal processing on graphs within a single convolutional neural network (CNN) framework. Building upon recent works on graph CNNs, we propose to use convolutional layers that take as inputs two variables, a signal and a graph, allowing the network to adapt to changes in the graph structure. In this article, we explain how this framew...

Quantitative analysis of brain MRI at the age of 6 months is difficult because of the limited contrast between white matter and gray matter. In this study, we use a dilated triplanar convolutional neural network in combination with a non-dilated 3D convolutional neural network for the segmentation of white matter, gray matter and cerebrospinal fluid in infant brain MR images, as provided by the...