Lip reading for low-resource languages by learning and combining general speech knowledge and language-specific knowledge

M Kim, JH Yeo, J Choi, YM Ro - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper proposes a novel lip reading framework, especially for low-resource languages,
which has not been well addressed in the previous literature. Since low-resource languages …

Joint expression synthesis and representation learning for facial expression recognition

X Zhang, F Zhang, C Xu - … on Circuits and Systems for Video …, 2021 - ieeexplore.ieee.org
Facial expression recognition (FER) is a challenging task due to the large appearance
variations and the lack of sufficient training data. Conventional deep approaches either learn …

Distributed intelligence in industrial and automotive cyber–physical systems: a review

N Piperigkos, A Gkillas, G Arvanitis… - Frontiers in Robotics …, 2024 - frontiersin.org
Cyber–physical systems (CPSs) are evolving from individual systems to collectives of
systems that collaborate to achieve highly complex goals, realizing a cyber–physical system …

A coarse-to-fine facial landmark detection method based on self-attention mechanism

P Gao, K Lu, J Xue, L Shao, J Lyu - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Facial landmark detection in the wild remains a challenging problem in computer vision.
Deep learning-based methods currently play a leading role in solving this. However, these …

Expression-tailored talking face generation with adaptive cross-modal weighting

D Zeng, S Zhao, J Zhang, H Liu, K Li - Neurocomputing, 2022 - Elsevier
The key of talking face generation is to synthesize the identity-preserving natural facial
expressions with accurate audio-lip synchronization. To accomplish this, it requires to …

Stacked attention hourglass network based robust facial landmark detection

Y Huang, H Huang - Neural Networks, 2023 - Elsevier
Deep learning based facial landmark detection (FLD) has made rapid progress. However,
the accuracy and robustness of FLD algorithms are degraded heavily when the face is …

Adaptive robust loss for landmark detection

Y Tian, D Su, S Li - Information Fusion, 2024 - Elsevier
Using a loss function with appropriate properties to supervise the training of the neural
network can substantially improve its accuracy and speed. A majority of loss functions …

Face Shape-Guided Deep Feature Alignment for Face Recognition Robust to Face Misalignment

HI Kim, K Yun, YM Ro - IEEE Transactions on Biometrics …, 2022 - ieeexplore.ieee.org
For the past decades, face recognition (FR) has been actively studied in computer vision
and pattern recognition society. Recently, due to the advances in deep learning, the FR …

2D Wasserstein loss for robust facial landmark detection

Y Yan, S Duffner, P Phutane, A Berthelier, C Blanc… - Pattern Recognition, 2021 - Elsevier
The recent performance of facial landmark detection has been significantly improved by
using deep Convolutional Neural Networks (CNNs), especially the Heatmap Regression …

Empowering cyberphysical systems of systems with intelligence

S Nousias, N Piperigkos, G Arvanitis… - arxiv preprint arxiv …, 2021 - arxiv.org
Cyber Physical Systems have been going into a transition phase from individual systems to
a collecttives of systems that collaborate in order to achieve a highly complex cause …