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, Information Systems
Selvarajah Thuseethan et al.
Summary: This study proposes a novel facial microexpression detection framework called Deep3DCANN, which integrates a deep 3D convolutional neural network, a deep artificial neural network, and a fusion mechanism to effectively detect microexpressions. It performs well on benchmark databases and effectively recognizes frame-wise microexpression changes in video sequences.
INFORMATION SCIENCES
(2023)
Article
Engineering, Electrical & Electronic
Gen-Bing Liong et al.
Summary: Facial Micro-Expressions (MEs) can reveal hidden emotions in high stake situations, and this paper proposes a shallow multi-stream multi-output network architecture, MEAN, that effectively learns meaningful representation from ME class labels and location-wise pseudo-labels. It is the first work to use deep learning approach for ME analysis on long videos, and achieves good performance on various datasets.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2023)
Article
Engineering, Electrical & Electronic
Jingling Tang et al.
Summary: Human facial expressions are crucial in interpersonal communication, but existing algorithms for micro-expression recognition have limited performance. In this study, we propose a novel algorithm that combines optical flow and dynamic image convolutional neural networks to improve micro-expression recognition. Experimental results show that our algorithm achieves state-of-the-art results in publicly available micro-expression databases.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Education & Educational Research
Imane Lasri et al.
Summary: Facial expression recognition has the potential to assess the engagement level of deaf and hard-of-hearing students in the education field. This study proposes a novel approach using a deep convolutional neural network model and transfer learning technique to detect the engagement level from the facial emotions of these students. Experimental results show that the proposed method outperforms other state-of-the-art approaches.
EDUCATION AND INFORMATION TECHNOLOGIES
(2023)
Article
Sakshi Indolia et al.
Journal of Ambient Intelligence and Humanized Computing
(2023)
Article
Computer Science, Information Systems
Adamu Muhammad Buhari et al.
Summary: This paper proposes a novel geometrical-based invisible emotion magnification algorithm (IEMA) for real-time micro-expression recognition. The algorithm utilizes facial landmarks to compute magnification elements and facial movement direction, and applies them to the coordinates of facial apex frames to enhance the magnitude of facial muscle movement. The experimental results show that the proposed IEMA outperforms other micro-expression magnification methods in terms of accuracy and F1-score, and meets the minimum requirement for real-time micro-expression recognition.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Jiuk Hong et al.
Summary: This article proposes a novel model for facial micro-expression recognition by using a transformer and motion features. The model is verified and evaluated on two datasets, and achieves state-of-the-art performance on both datasets.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Linqin Cai et al.
Summary: This paper investigates micro-expression recognition based on deep learning methods and proposes a three-dimensional SE-DenseNet architecture, which can accurately describe micro-expressions and performs well on public datasets.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Jinsheng Wei et al.
Summary: Micro-expression recognition is of great research value and presents significant challenges. In this paper, a new feature extraction method called LBP-FIP is proposed to address the extraction of dynamic texture features in oblique muscle movement direction in micro-expression videos. Experimental results on CASME II and SMIC databases demonstrate that LBP-FIP provides more effective information and discriminative features for micro-expression recognition compared to LBP-TOP, and it outperforms other LBP-based features, particularly on CASME II.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Bo Sun et al.
Summary: This article discusses the challenges and bottleneck of micro-expression recognition and proposes a novel knowledge transfer technique to improve accuracy. The technique involves extracting knowledge from a pre-trained teacher neural network and transferring it to a shallow student neural network. Experimental results show that this method outperforms existing systems.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)
Article
Computer Science, Information Systems
Shuhua Liu et al.
Summary: Micro-expression recognition is a challenging task with multiple real-life applications. This paper proposes a micro-expression recognition model called SQU-C3D, which combines SqueezeNet and C3D methods. The model accurately locates the apex frame and learns the features of key frames for micro-expression recognition. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods on micro-expression databases.
MULTIMEDIA SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Sirui Zhao et al.
Summary: Micro-expressions (MEs) are spontaneous and subtle facial movements that occur in high-stake situations and reveal genuine human feelings and cognition. In this paper, a deep prototypical learning framework called ME-PLAN is proposed for the MER problem, and its superiority and effectiveness are demonstrated through extensive experiments.
Article
Computer Science, Information Systems
Selvarajah Thuseethan et al.
Summary: The paper proposes a deep learning technique that effectively recognizes unknown emotion categories by constantly absorbing upcoming emotion categories and preserving existing knowledge. By evaluating the proposed method on benchmark emotion datasets, the results confirm its superior performance in recognizing unknown emotional states compared to continual learning benchmarks and transfer learning baselines.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Proceedings Paper
Automation & Control Systems
Xinhua Zhao et al.
Summary: This paper presents a novel method of Multimodal fusion micro-expression recognition using a visual transformer, which achieves state-of-the-art performance in terms of accuracy. The proposed model matches well with the expression action units and obtains more promising recognition results than other methods.
PROCEEDINGS OF 2022 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (IEEE ICMA 2022)
(2022)
Article
Engineering, Electrical & Electronic
Jie Zhu et al.
Summary: In this letter, a high-performance spatiotemporal feature learning based on sparse transformer is proposed to effectively extract strong associated spatiotemporal feature by distinguishing spatial attention map and attentively fusing temporal feature for micro-expression recognition. The method achieves remarkable results compared to state-of-the-art methods, demonstrating successful integration of sparse representation into self-attention mechanism for micro-expression recognition.
IEEE SIGNAL PROCESSING LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Madhumita A. Takalkar et al.
Summary: Research in the field of micro-expressions has become increasingly important, with the proposal of an architecture called LGAttNet, which utilizes a dual attention network for frame-wise automatic micro-expression detection. This method extracts local and global facial features using an attention network, showing robustness and superiority compared to state-of-the-art approaches on publicly available databases.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Xuan Nie et al.
Summary: This research introduces a dual-stream multi-task framework called GEME to improve micro-expression recognition accuracy by incorporating gender characteristics. By selecting gender-specific features of micro-expressions and adding them to the micro-expression features, the study shows an improvement in recognition accuracy. The network learns gender-specific and micro-expression features together to achieve a better representation.
Article
Computer Science, Artificial Intelligence
Sirui Zhao et al.
Summary: This paper proposes a novel method MERSiamC3D based on few-shot learning for MEs recognition, which combines two-stage learning (prior learning and target learning) and utilizes Focal Loss for feature learning to address the challenges of accurately recognizing MEs. An adaptive construction method based on adaptive convolutional neural network is also proposed to retain the spatiotemporal information of the original MEs video effectively.
Article
Computer Science, Information Systems
Zhaoqiang Xia et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2020)
Article
Computer Science, Artificial Intelligence
Monu Verma et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Information Systems
Dong Yoon Choi et al.
Article
Computer Science, Artificial Intelligence
Ali Mollahosseini et al.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2019)
Article
Engineering, Electrical & Electronic
Y. S. Gan et al.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2019)
Article
Computer Science, Artificial Intelligence
Jing Li et al.
PATTERN ANALYSIS AND APPLICATIONS
(2019)
Proceedings Paper
Imaging Science & Photographic Technology
Huai-Qian Khor et al.
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2019)
Article
Computer Science, Information Systems
Swati Nigam et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2018)
Article
Engineering, Electrical & Electronic
Hua Lu et al.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2018)
Article
Computer Science, Artificial Intelligence
Adrian K. Davison et al.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2018)
Article
Computer Science, Artificial Intelligence
Xianye Ben et al.
NEURAL COMPUTING & APPLICATIONS
(2016)
Article
Computer Science, Artificial Intelligence
Yong-Jin Liu et al.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2016)
Review
Multidisciplinary Sciences
Yann LeCun et al.
Article
Optics
Yingchun Guo et al.
Article
Multidisciplinary Sciences
Wen-Jing Yan et al.