We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures. The pipeline of this architecture consists of three parts. Through the first part, we encode an input face image to resolution-preserved deconvolutional feature maps via a deep network with stacked con...

In this work we pursue a data-driven approach to the problem of estimating surface normals from a single intensity image, focusing in particular on human faces. We introduce new methods to exploit the currently available facial databases for dataset construction and tailor a deep convolutional neural network to the task of estimating facial surface normals ‘in-the-wild’. We train a fully convol...

Deep convolutional neural networks are powerful tools for learning visual representations from images. However, designing efficient deep architectures to analyse volumetric medical images remains challenging. This work investigates efficient and flexible elements of modern convolutional networks such as dilated convolution and residual connection. With these essential building blocks, we propos...

Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of convolutional neural networks to perturbations to the internal weights and architecture of the network itself. We show that convolutional networks are surprisingly r...

3D convolutional neural network (3D CNN) captures spatial and temporal information on data such as video sequences. However, due to the convolution pooling mechanism, loss that occurs seems unavoidable. To improve visual explanations classification in CNN, we propose two approaches; (i) aggregate layer-wise global local (global–local) discrete gradient using trained 3DResNext network, (ii) impl...

Landslide detection is crucial for disaster management and prevention. With the advent of multi-channel optical remote sensing technology, detecting landslides have become more accessible accurate. Although use convolutional neural network (CNN) has significantly increased accuracy landslide on images, most previous methods using CNN lack ability to obtain global context information due structu...

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, t...

In the greater part of this thesis, we develop a set of convolutional networks that infer predictions at each pixel of an input image. This is a common problem that arises in many computer vision applications: For example, predicting a semantic label at each pixel describes not only the image content, but also fine-grained locations and segmentations; at the same time, finding depth or surface ...

Artificial intelligence models have been widely applied for natural gas consumption forecasting over the past decades, especially short-term forecasting. This paper proposes a three-layer neural network model that can extract key information from input factors and improve weight optimization mechanism of long memory (LSTM) to effectively forecast consumption. In proposed model, convolutional (C...