Search Results for author: Zhiwen Shao

Found 12 papers, 4 papers with code

"Forget" the Forget Gate: Estimating Anomalies in Videos using Self-contained Long Short-Term Memory Networks

no code implementations3 Apr 2021 Habtamu Fanta, Zhiwen Shao, Lizhuang Ma

Abnormal event detection is a challenging task that requires effectively handling intricate features of appearance and motion.

Anomaly Detection Event Detection +1

Fine-Grained Expression Manipulation via Structured Latent Space

no code implementations21 Apr 2020 Junshu Tang, Zhiwen Shao, Lizhuang Ma

Most existing expression manipulation methods resort to discrete expression labels, which mainly edit global expressions and ignore the manipulation of fine details.

SiTGRU: Single-Tunnelled Gated Recurrent Unit for Abnormality Detection

no code implementations30 Mar 2020 Habtamu Fanta, Zhiwen Shao, Lizhuang Ma

In this paper, we propose a novel version of Gated Recurrent Unit (GRU), called Single Tunnelled GRU for abnormality detection.

Anomaly Detection

J$\hat{\text{A}}$A-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention

1 code implementation18 Mar 2020 Zhiwen Shao, Zhilei Liu, Jianfei Cai, Lizhuang Ma

Moreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively.

Action Unit Detection Face Alignment +1

GeoConv: Geodesic Guided Convolution for Facial Action Unit Recognition

no code implementations6 Mar 2020 Yuedong Chen, Guoxian Song, Zhiwen Shao, Jianfei Cai, Tat-Jen Cham, Jianming Zheng

Automatic facial action unit (AU) recognition has attracted great attention but still remains a challenging task, as subtle changes of local facial muscles are difficult to thoroughly capture.

Face Model Facial Action Unit Detection

Spatio-Temporal Relation and Attention Learning for Facial Action Unit Detection

no code implementations5 Jan 2020 Zhiwen Shao, Lixin Zou, Jianfei Cai, Yunsheng Wu, Lizhuang Ma

Specifically, we introduce a spatio-temporal graph convolutional network to capture both spatial and temporal relations from dynamic AUs, in which the AU relations are formulated as a spatio-temporal graph with adaptively learned instead of predefined edge weights.

Action Unit Detection Facial Action Unit Detection

Explicit Facial Expression Transfer via Fine-Grained Representations

no code implementations6 Sep 2019 Zhiwen Shao, Hengliang Zhu, Junshu Tang, Xuequan Lu, Lizhuang Ma

Instead of using an intermediate estimated guidance, we propose to explicitly transfer facial expression by directly mapping two unpaired input images to two synthesized images with swapped expressions.

Multi-class Classification

Unconstrained Facial Action Unit Detection via Latent Feature Domain

1 code implementation25 Mar 2019 Zhiwen Shao, Jianfei Cai, Tat-Jen Cham, Xuequan Lu, Lizhuang Ma

Due to the combination of source AU-related information and target AU-free information, the latent feature domain with transferred source label can be learned by maximizing the target-domain AU detection performance.

Action Unit Detection Domain Adaptation +2

Facial Action Unit Detection Using Attention and Relation Learning

no code implementations10 Aug 2018 Zhiwen Shao, Zhilei Liu, Jianfei Cai, Yunsheng Wu, Lizhuang Ma

By finding the region of interest of each AU with the attention mechanism, AU-related local features can be captured.

Action Unit Detection Facial Action Unit Detection

Deep Multi-Center Learning for Face Alignment

1 code implementation5 Aug 2018 Zhiwen Shao, Hengliang Zhu, Xin Tan, Yangyang Hao, Lizhuang Ma

Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks.

Face Alignment

Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment

1 code implementation ECCV 2018 Zhiwen Shao, Zhilei Liu, Jianfei Cai, Lizhuang Ma

Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection.

Action Unit Detection Face Alignment +1

Learning deep representation from coarse to fine for face alignment

no code implementations31 Jul 2016 Zhiwen Shao, Shouhong Ding, Yiru Zhao, Qinchuan Zhang, Lizhuang Ma

In this paper, we propose a novel face alignment method that trains deep convolutional network from coarse to fine.

Face Alignment

Cannot find the paper you are looking for? You can Submit a new open access paper.