Attack to Fool and Explain Deep Networks

Deep visual models are susceptible to adversarial perturbations to inputs. Although these signals are carefully crafted, they still appear noise-like patterns to humans. This observation has led to…

Hands-On Bayesian Neural Networks—A Tutorial for Deep Learning Users

Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems. However, since deep learning methods operate as black boxes, the uncertainty associated…

A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing tec…

Deep Learning for 3D Point Clouds: A Survey

Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI…

Image-Based 3D Object Reconstruction : State-of-the-Art and Trends in the Dee…

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D re…

Guest Editors Introduction to he Special Issue on RGB-D Vision : Method and A…

A Multi-Modal, Discriminative and Spatially Invariant CNN for RGB-D Object La…

Automatic Shadow Detection and Removal from a Single Image

Deep reconstruction models for image set classification

3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey