Search Results for author: Zhilei Liu

Found 19 papers, 2 papers with code

Updating the silent speech challenge benchmark with deep learning

no code implementations20 Sep 2017 Yan Ji, Licheng Liu, Hongcui Wang, Zhilei Liu, Zhibin Niu, Bruce Denby

The 2010 Silent Speech Challenge benchmark is updated with new results obtained in a Deep Learning strategy, using the same input features and decoding strategy as in the original article.

Conditional Adversarial Synthesis of 3D Facial Action Units

no code implementations21 Feb 2018 Zhilei Liu, Guoxian Song, Jianfei Cai, Tat-Jen Cham, Juyong Zhang

Employing deep learning-based approaches for fine-grained facial expression analysis, such as those involving the estimation of Action Unit (AU) intensities, is difficult due to the lack of a large-scale dataset of real faces with sufficiently diverse AU labels for training.

Data Augmentation Image Generation

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

Speech Emotion Recognition Considering Local Dynamic Features

no code implementations21 Mar 2018 Haotian Guan, Zhilei Liu, Longbiao Wang, Jianwu Dang, Ruiguo Yu

Recently, increasing attention has been directed to the study of the speech emotion recognition, in which global acoustic features of an utterance are mostly used to eliminate the content differences.

Speech Emotion Recognition

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 +1

Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection

no code implementations23 Oct 2019 Zhilei Liu, Jiahui Dong, Cuicui Zhang, Longbiao Wang, Jianwu Dang

Most existing AU detection works considering AU relationships are relying on probabilistic graphical models with manually extracted features.

Action Unit Detection Facial Action Unit Detection +1

Region Based Adversarial Synthesis of Facial Action Units

no code implementations23 Oct 2019 Zhilei Liu, Diyi Liu, Yunpeng Wu

Facial expression synthesis or editing has recently received increasing attention in the field of affective computing and facial expression modeling.

Generative Adversarial Network

Facial Expression Restoration Based on Improved Graph Convolutional Networks

no code implementations23 Oct 2019 Zhilei Liu, Le Li, Yunpeng Wu, Cuicui Zhang

Facial expression analysis in the wild is challenging when the facial image is with low resolution or partial occlusion.

Generative Adversarial Network Super-Resolution

Controllable Descendant Face Synthesis

no code implementations26 Feb 2020 Yong Zhang, Le Li, Zhilei Liu, Baoyuan Wu, Yanbo Fan, Zhifeng Li

Most of the existing methods train models for one-versus-one kin relation, which only consider one parent face and one child face by directly using an auto-encoder without any explicit control over the resemblance of the synthesized face to the parent face.

Attribute Face Generation +1

Joint Face Completion and Super-resolution using Multi-scale Feature Relation Learning

no code implementations29 Feb 2020 Zhilei Liu, Yunpeng Wu, Le Li, Cuicui Zhang, Baoyuan Wu

This paper proposes a multi-scale feature graph generative adversarial network (MFG-GAN) to implement the face restoration of images in which both degradation modes coexist, and also to repair images with a single type of degradation.

Facial Inpainting Generative Adversarial Network +2

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

Teacher-Student Competition for Unsupervised Domain Adaptation

no code implementations19 Oct 2020 Ruixin Xiao, Zhilei Liu, Baoyuan Wu

With the supervision from source domain only in class-level, existing unsupervised domain adaptation (UDA) methods mainly learn the domain-invariant representations from a shared feature extractor, which causes the source-bias problem.

Unsupervised Domain Adaptation

Talking Head Generation with Audio and Speech Related Facial Action Units

no code implementations19 Oct 2021 Sen Chen, Zhilei Liu, Jiaxing Liu, Zhengxiang Yan, Longbiao Wang

Quantitative and qualitative experiments demonstrate that our method outperforms existing methods in both image quality and lip-sync accuracy.

Talking Head Generation

Cross-subject Action Unit Detection with Meta Learning and Transformer-based Relation Modeling

no code implementations18 May 2022 Jiyuan Cao, Zhilei Liu, Yong Zhang

Ablation study and visualization show that our MARL can eliminate identity-caused differences, thus obtaining a robust and generalized AU discriminative embedding representation.

Action Unit Detection Emotion Recognition +3

Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors

no code implementations12 Oct 2022 Chenggong Zhang, Zhilei Liu

In this paper, we propose a novel recurrent convolutional network based framework for face super-resolution, which progressively introduces both global shape and local texture information.

Super-Resolution

NeRF-AD: Neural Radiance Field with Attention-based Disentanglement for Talking Face Synthesis

no code implementations23 Jan 2024 Chongke Bi, Xiaoxing Liu, Zhilei Liu

However, most existing NeRF-based methods either burden NeRF with complex learning tasks while lacking methods for supervised multimodal feature fusion, or cannot precisely map audio to the facial region related to speech movements.

Disentanglement Face Generation

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