相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Weiguang Zhang et al.
Summary: Facial expressions are crucial in conveying human emotional signals, and their recognition has been a significant research topic in pattern recognition. Deep learning methods have achieved remarkable success in facial expression recognition. However, as convolution neural networks evolve and network depth increases, these methods face challenges such as degraded network performance and loss of feature information. To overcome these issues, a novel facial expression recognition algorithm based on an improved residual neural network is proposed. By designing a residual neural network to extract both deep and shallow features, this algorithm effectively prevents network performance degradation. Additionally, replacing the Rectified Linear Units activation function with the Mish activation function improves gradient flow and prevents feature information loss. Incorporating an inception module further enhances the richness of feature information within the same receptive field. Experimental results on the CK+ and KDEF public datasets demonstrate that the proposed algorithm successfully solves the problems of degraded network performance and insufficient extracted feature information, achieving recognition accuracy rates of 96.37% and 93.38% on the two datasets, respectively.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Andreas Aakerberg et al.
Summary: This study introduces a novel framework for generating realistic LR/HR training pairs to address the issue of poor performance of existing SR methods on real LR images. Experimental results demonstrate that the proposed method leads to more detailed reconstructions and less noise.
IET IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Jinyan Ma et al.
Summary: The proposed face alignment algorithm DSCN combines capsule network and attention mechanism to address occlusion issues, achieving low failure rates and small mean errors on multiple datasets.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Zou Yang et al.
Summary: The paper proposes a mixed attention hourglass network (MAttHG) to address unconstrained face alignment challenges, capturing rich contextual correlations and enhancing robustness through the integration of attention modules from different feature levels. Additionally, a head pose prediction module is designed to adaptively adjust training sample weights and address data imbalance. The experimental results demonstrate the superiority of MAttHG over state-of-the-art face alignment methods.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Jun Wan et al.
Summary: This article proposes a multiorder multiconstraint deep network (MMDN) for learning more powerful feature correlations and shape constraints, including an implicit multiorder correlating geometry-aware (IMCG) model and an explicit probability-based boundary-adaptive regression (EPBR) method. Experimental results demonstrate the superior performance of MMDN on challenging benchmark data sets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jin Lu et al.
Summary: This article proposes a single-model multi-task approach that integrates IoT, computer vision, and artificial intelligence to improve people's daily lives in smart homes, smart cities, and smart industries. By using a single model to complete all tasks, the approach achieves significant improvements in inference speed, especially in scenes with high face density.
IET IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Jiahui Zhang et al.
Summary: The study introduces a two-stage cascade regression model, where the first stage aligns the salient shape and the second stage further predicts the full shape.
IET IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Shahar Mahpod et al.
Summary: This study introduces a novel approach for facial landmark localization using a deep learning architecture, which shows promising results especially in challenging localization conditions.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2021)
Article
Computer Science, Artificial Intelligence
Jun Wan et al.
Summary: The paper introduces a CCDN for robust facial landmark detection, which enhances semantic feature learning by introducing the CTM module and COCS regularizer to learn more fine and complementary features, improving accuracy under extremely challenging scenarios.
Article
Computer Science, Artificial Intelligence
Haibo Jin et al.
Summary: The proposed PIPNet model combines heatmap regression and neighbor regression modules to solve the issues of high computational cost, lack of global shape constraints, and domain gaps in traditional facial landmark detection models. The self-training strategy with curriculum improves the cross-domain generalization capability of PIPNet.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Shenqi Lai et al.
Summary: This paper introduces a robust facial landmark detection framework that has achieved promising results through model improvements and the introduction of new training methods.
2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ali Pourramezan Fard et al.
Summary: ASM assisted loss function helps improve the performance of face alignment and pose estimation tasks with a lightweight Convolutional Neural Network architecture. By gradually adjusting the regression problem and defining multi-tasks in the loss function, the network is guided to learn a smoother distribution of facial landmark points and achieve better performance in both tasks simultaneously. Comparisons with a larger model, MobileNetV2, show that ASMNet achieves comparable performance in face alignment and significantly better performance in face pose estimation with fewer parameters and operations.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Article
Computer Science, Artificial Intelligence
Zhen-Hua Feng et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Computer Science, Artificial Intelligence
Junfeng Zhang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhen-Hua Feng et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Xuanyi Dong et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenyan (Wayne) Wu et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Marek Kowalski et al.
2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
George Trigeorgis et al.
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Xavier P. Burgos-Artizzu et al.
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2013)