activity
20172019
collaborators

7 papers

cs.CV2019

Shape Constrained Network for Eye Segmentation in the Wild

Bingnan Luo, Jie Shen, Shiyang Cheng +2

Semantic segmentation of eyes has long been a vital pre-processing step in many biometric applications. Majority of the works focus only on high resolution eye images, while little…

cs.CV2019

Dynamic Face Video Segmentation via Reinforcement Learning

Yujiang Wang, Mingzhi Dong, Jie Shen +3

For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key sch…

cs.CV2019

End-to-End Visual Speech Recognition for Small-Scale Datasets

Stavros Petridis, Yujiang Wang, Pingchuan Ma +2

Visual speech recognition models traditionally consist of two stages, feature extraction and classification. Several deep learning approaches have been recently presented aiming to…

cs.CV2018

Face Mask Extraction in Video Sequence

Yujiang Wang, Bingnan Luo, Jie Shen +1

Inspired by the recent development of deep network-based methods in semantic image segmentation, we introduce an end-to-end trainable model for face mask extraction in video sequen…

cs.LG2018

Learning Local Metrics and Influential Regions for Classification

Mingzhi Dong, Yujiang Wang, Xiaochen Yang +1

The performance of distance-based classifiers heavily depends on the underlying distance metric, so it is valuable to learn a suitable metric from the data. To address the problem…

cs.CV2017

End-to-End Audiovisual Fusion with LSTMs

Stavros Petridis, Yujiang Wang, Zuwei Li +1

Several end-to-end deep learning approaches have been recently presented which simultaneously extract visual features from the input images and perform visual speech classification…