Research

Feature Selection Guided Auto-Encoder

Shuyang Wang, Zhengming Ding, Yun Fu.

AAAI, 2017.

paper

Discerning Feature Supported Encoder (DFSE) is proposed which integrates auto-encoder and feature selection together into a unified model. Specifically, the feature selection is adapted to learned hidden-layer features to capture the task-relevant ones from the task-irrelevant ones. Meanwhile, the selected hidden units could in turn encode more discriminability only on selected task-relevant units.

Coupled Marginalized Auto-encoders for Cross-domain Multi-view Learning

Shuyang Wang, Zhengming Ding, Yun Fu.

IJCAI, 2016.

paper

We propose a Coupled Marginalized Denoising Autoencoders framework to address the cross-domain problem. Specifically, we design two marginalized denoising auto-encoders, one for the target and the other for source as well as the intermediate one

Face Behind Makeup

Shuyang Wang, Yun Fu.

AAAI, 2016.

paper

We propose a novel automatic makeup detector and remover framework.

A locality-constrained coupled dictionary learning (LC-CDL) framework is proposed to synthesize non-makeup face, so that the makeup could be erased according to the style.

Attractive or Not? Beauty Prediction with Attractiveness-Aware Encoders and Robust Late Fusion

Shuyang Wang, Ming Shao, Yun Fu.

ACM Multimedia, 2014.

paper

Provide a fully automatic framework with no landmark annotation requirement.

(1) We propose an attractiveness aware auto encoder to integrate several low level features for high level attractiveness aware descriptors;

(2) Introduce a low rank representation late fusion framework to boost the performance of ranking scores from different features

Hierarchical Facial Expression Animation by Motion Capture Data

Shuyang Wang, Jinzheng Sha, Huai-yu Wu, Yun Fu.

ICME, 2014

paper/video

We propose a intuitive and realistic control expression animation system based on a single-video tracking and motion capture data preprocessing.

Our vision-based expression editing system has two major features：

• Edit 3D facial expression in real time, while being easy to interact via single-camera

• Clone realistic expressions, including subtle movements on cheeks and forehead that traditional vision-based systems have yet to achieve

Examples-Rules Guided Deep Neural Network for Makeup Recommendation

Taleb Alashkar, Songyao Jiang, Shuyang Wang and Yun Fu

AAAI, 2017.

We consider a fully automatic makeup recommendation system and propose a novel examples-rules guided deep neural network approach. Makeup-related facial traits are classified into structured coding. These facial traits are fed in- to examples-rules guided deep neural recommendation model which makes use of the pairwise of Before-After images and the makeup artist knowledge jointly. To visualize the recommended makeup style, an automatic makeup synthesis system is developed as well.