CNN

PPGNet: Learning Point-Pair Graph for Line Segment Detection

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 …

Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

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 …

SUNNet: A Novel Framework for Simultaneous Human Parsing and Pose Estimation

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 …

Photo-Realistic Facial Details Synthesis from Single Image

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 …

RGBD Based Gaze Estimation via Multi-task CNN

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 …

Saliency Detection in 360° Videos

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 …

2nd place in WebVision Challenge on Image Classification Task (Top University Team)

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 …