In this paper, we present a novel framework to detect line segments in man-made environments. Specifically, we propose to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative …
In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal segmentation …
This paper presents a novel Separation-and-UnioN Network (SUNNet) for simultaneous human parsing and pose estimation. Our SUNNet consists of two stages: feature separation and feature union. In feature separation stage, we leverage a common feature …
We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details. Our technique employs expression analysis for proxy face geometry generation and combines supervised and …
This paper tackles RGBD based gaze estimation with Convolutional Neural Networks (CNNs). Specifically, we propose to decompose gaze point estimation into eyeball pose, head pose, and 3D eye position estimation. Compared with RGB image-based gaze …
This paper presents a novel spherical convolutional neural network based scheme for saliency detection for 360 videos. Specifically, in our spherical convolution neural network definition, kernel is defined on a spherical crown, and the convolution …
This report aims to study how to train a deep learning based classifier when only large scale noisy dataset is available. In order to overcome dataset noise, a series of training as well as testing methods are proposed, including bootstrapping method …