Article
Computer Science, Artificial Intelligence
Fang Nan, Wei Jing, Feng Tian, Jizhong Zhang, Kuo-Ming Chao, Zhenxin Hong, Qinghua Zheng
Summary: In this study, a novel generative adversarial network-based feature level super-resolution method was proposed for robust facial expression recognition. By using a pre-trained FER model as a feature extractor, and training generator and discriminator networks with low-resolution and high-resolution image features, satisfying results were achieved under different down-sample factors, with better performance on low-resolution images compared to methods using image super-resolution and expression recognition separately.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Xingang Liu, Chenqi Li, Cheng Dai, Jinfeng Lai, Han-Chieh Chao
Summary: This paper proposes a novel nonnegative tensor factorization method (NTF-LRS) for facial expression recognition, which constructs a data tensor model and adopts a low-rank subspace model for reconstruction to improve the discriminant abilities of multi-dimensional data. Experimental results show that this tensor-based method effectively avoids the curse of dimensionality and preserves the original structure of samples.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Wenjing Zhang, Peng Song, Dongliang Chen, Weijian Zhang
Summary: This paper proposes a novel transfer learning method (LSTSL) for cross-corpus facial expression recognition, which learns a common subspace for linear representation of target samples by a few source samples. The method utilizes l(2,1)-norm and maximum mean discrepancy (MMD) to enhance recognition performance, outperforming state-of-the-art transfer learning methods in cross-corpus facial expression recognition.
DIGITAL SIGNAL PROCESSING
(2021)
Article
Engineering, Electrical & Electronic
Jiawei Shi, Songhao Zhu, Dongsheng Wang, Zhiwei Liang
Summary: This paper proposes a feature extraction pattern for facial expression recognition, which weakens the negative impact of padding through secondary processing of high-dimensional features, resulting in significant performance improvement.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Tingsong Ma, Wenhong Tian, Yuanlun Xie
Summary: This paper proposes a knowledge distillation approach to transfer high-resolution features from a teacher network to a simpler structured student network trained on low-resolution inputs. Experimental results show that the proposed approach achieves higher accuracy than existing models in object detection and facial expression recognition tasks.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zhe Sun, Hehao Zhang, Suwei Ma, Zhengping Hu
Summary: Automatic facial expression recognition is a well-studied research area that faces challenges from noise interference and cross-dataset recognition issues. This study proposes a novel approach combining deep subspace filter learning and discriminative classification criteria to enhance recognition performance, with experiments showing superiority over state-of-the-art methods.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Engineering, Electrical & Electronic
Xi Zhang, Feifei Zhang, Changsheng Xu
Summary: This paper proposes an end-to-end deep model for simultaneous facial expression recognition and facial image synthesis. The model is based on Generative Adversarial Network (GAN) and has several merits: the performance of facial image synthesis and facial expression recognition tasks can be boosted through the unified model, paired images are not required in the facial image synthesis network, the generated facial images can expand the training set and ease overfitting, different expressions are encoded in a disentangled manner, allowing for synthesizing facial images with arbitrary expressions.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa
Summary: This research proposes a novel DeriveNet model for VLR/LR classification, which focuses on learning effective class boundaries by utilizing the class-specific domain knowledge. The DeriveNet model achieves state-of-the-art performance across different VLR/LR classification tasks, demonstrating its utility.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Robotics
Ahmad Khaliq, Michael Milford, Sourav Garg
Summary: In this paper, the authors propose an improved NetVLAD representation learning method, which utilizes a low-resolution image pyramid encoding to obtain richer place representations. The resulting multi-resolution feature pyramid can be easily aggregated using the VLAD algorithm, eliminating the need for concatenating or summing multiple patches. Experimental results demonstrate that the proposed method achieves state-of-the-art performance in global descriptor-based retrieval.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Information Systems
Jose L. Gomez-Sirvent, Francisco Lopez de la Rosa, Maria T. Lopez, Antonio Fernandez-Caballero
Summary: This paper proposes a residual voting network for the classification of low-resolution facial expression images. The network uses soft-voting of predictions from each image crop to determine the sample's class. The proposed model achieves comparable accuracy on AffectNet and RAF-DB compared to other methods using larger images.
Article
Computer Science, Artificial Intelligence
Wenjing Zhang, Peng Song, Wenming Zheng
Summary: In this paper, a novel transfer learning approach, named LGDSTL, is proposed for cross-database facial expression recognition (FER). The approach considers both the local and global geometric structures and utilizes pairwise regression function and data reconstruction constraint to reduce the discrepancy between different databases.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Xiaofeng Liu, Linghao Jin, Xu Han, Jane You
Summary: This paper focuses on the long-standing problem of extracting effective expression representations invariant to identity-specific attributes in facial expression recognition. By exploring facial expression representation in the compressed video domain and eliminating inter-subject variations, the expression features are expected to be purer and more robust. The proposed method achieves comparable or better performance than recent image-based methods, with faster inference speed, on typical FER benchmarks without the need for identity labels or multiple expression samples from the same person.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Theory & Methods
Cheng-Yaw Low, Andrew Beng-Jin Teoh
Summary: This paper proposes a new identity-extended data augmentation (DA) strategy for low-resolution face recognition (LRFR) that satisfies the requirements of affinity and diversity. The proposed method utilizes identity-extended examples to improve representation learning. Experimental results demonstrate that this approach outperforms other methods on real-world LR face datasets.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Engineering, Electrical & Electronic
Yong Chen, Juan Zhang, Jinshan Zeng, Wenzhen Lai, Xinfeng Gui, Tai-Xiang Jiang
Summary: In this paper, a new method called Subspace-based Guided Nonlocal Low-Rank Approximation (SGNLR) is proposed for hyperspectral image (HSI) denoising. The method takes advantage of the abundant spatial information in the representation coefficients of high signal-to-noise ratio bands (HSNRBs) to improve denoising performances. Extensive experiments on both simulated and real-world data demonstrate the outperformance of the proposed method.
Article
Remote Sensing
Kemal Gurkan Toker, Seniha Esen Yuksel
Summary: Nearest subspace classifier (NSC) is a simple classifier that only considers spectral information. This paper proposes an improved NSC-based method that incorporates both spectral and spatial information, and analyzes the closeness between subspaces for classification.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Alam Abbas Syed, Hassan Foroosh
Summary: This paper presents effective methods using spherical polar Fourier transform data for two different applications: 3D volumetric registration and machine learning classification network. The proposed method for registration offers unique and effective techniques, handling arbitrary large rotation angles and showing robustness. The modified classification network achieves robust classification results in processing spherical data.
Article
Engineering, Electrical & Electronic
Ruibo Fan, Mingli Jing, Jingang Shi, Lan Li, Zizhao Wang
Summary: In this study, a new low-rank sparse decomposition algorithm named TVRPCA+ is proposed for foreground-background separation. The algorithm combines spectral norm, structured sparse norm, and total variation regularization to suppress noise and obtain cleaner foregrounds. Experimental results demonstrate that TVRPCA+ achieves high performance in complex backgrounds and noise scenarios.
Article
Engineering, Electrical & Electronic
Omair Aldimashki, Ahmet Serbes
Summary: This paper proposes a coarse-to-fine FrFT-based algorithm for chirp-rate estimation of multi-component LFM signals, which achieves improved performance and a reduced signal-to-noise breakdown threshold by utilizing mathematical models for coarse estimation and a refined estimate-and-subtract strategy. Extensive simulation results demonstrate that the proposed algorithm performs very close to the Cramer-Rao lower bound, with the advantages of eliminating leakage effect, avoiding error propagation, and maintaining acceptable computational cost compared to other state-of-the-art methods.
Article
Engineering, Electrical & Electronic
Xinlei Shi, Xiaofei Zhang, Yuxin Sun, Yang Qian, Jinke Cao
Summary: In this paper, a low-complexity localization approach for multiple sources using two-dimensional discrete Fourier transform (2D-DFT) is proposed. The method computes the cross-covariance and utilizes phase offset method and total least square solution to obtain accurate position estimates.
Article
Engineering, Electrical & Electronic
Prabhanjan Mannari, Ratnasingham Tharmarasa, Thiagalingam Kirubarajan
Summary: This paper discusses the problem of extended target tracking for a single 2D extended target with a known convex polytope shape and dynamics. It proposes a framework based on the existing point multitarget tracking framework to address the challenges of uncertainty in shape and kinematics, as well as self-occlusion. The algorithm developed using this framework is capable of dynamically changing the number of parameters used to describe the shape and estimating the whole target shape even when different parts of the target are visible at different frames.
Article
Engineering, Electrical & Electronic
Yongsong Li, Zhengzhou Li, Jie Li, Junchao Yang, Abubakar Siddique
Summary: This paper proposes a weighted adaptive ring top-hat transformation (WARTH) for extracting infrared small targets in complex backgrounds. The WARTH method effectively measures local and global feature information using an adaptive ring-shaped structural element and a target awareness indicator, resulting in accurate detection of small targets with minimized false alarms.
Article
Engineering, Electrical & Electronic
Yu Wang, Zhen Qin, Jun Tao, Yili Xia
Summary: In this paper, an enhanced sparsity-aware recursive least squares (RLS) algorithm is proposed, which combines the proportionate updating (PU) and zero-attracting (ZA) mechanisms, and introduces a general convex regularization (CR) function and variable step-size (VSS) technique to improve performance.
Article
Engineering, Electrical & Electronic
Neil J. Bershad, Jose C. M. Bermudez
Summary: This paper analyzes the impact of processing delay on the Least Mean Squares (LMS) algorithm in system identification, highlighting bias issues in the resulting weight vector.
Article
Engineering, Electrical & Electronic
Kanghui Jiang, Defu Jiang, Mingxing Fu, Yan Han, Song Wang, Chao Zhang, Jingyu Shi
Summary: In this paper, a novel method for velocity estimation using multicarrier signals in a single dwell is proposed, which effectively addresses the issue of Doppler ambiguity in pulse Doppler radars.
Article
Engineering, Electrical & Electronic
Xiao-Jun Zhang, Peng-Lang Shui, Yu-Fan Xue
Summary: This paper proposes a method for low-velocity small target detection in maritime surveillance radars. It models sea clutter sequences using the spherical invariant random vector (SIRV) model with block tridiagonal speckle covariance matrix and inverse Gamma distributed texture. The proposed detector, which is a long-time adaptive generalized likelihood ratio test with linear threshold detector (GLRT-LTD), shows competitive detection performance in experiments.
Article
Engineering, Electrical & Electronic
Aiyi Zhang, Fulai Liu, Ruiyan Du
Summary: This paper proposes an adaptive weighted robust data recovery method with total variation regularization for hyperspectral image. The method models the HSI recovery problem as a tensor robust principal component analysis optimization problem, decomposing the data into low-rank HSI data, outliers, and noise component. An adaptive weighted strategy is then defined to impose on the tensor nuclear norm and outliers, using the priori information of singular values and strengthening the sparsity of outliers.
Article
Engineering, Electrical & Electronic
Hamid Asadi, Babak Seyfe
Summary: This paper presents a novel approach for estimating the model order in the presence of observation errors. The proposed method is based on correntropy estimation of eigenvalues in the observation space, which is further enhanced by resampling the observations using the bootstrap method. The algorithm partitions the observation space into signal and noise subspaces using the covariance matrix of mixtures, and determines the model order based on a correntropy estimator with kernel functions. Theoretical analysis and comparative evaluations demonstrate the superiority of this information-theoretic approach.
Article
Engineering, Electrical & Electronic
Buket colak Guvenc, Engin Cemal Menguc
Summary: In this paper, a novel family of online censoring based complex-valued least mean kurtosis (CLMK) algorithms is proposed. The algorithms censor less informative complex-valued data streams and reduce the costs of data processing without affecting accuracy. Robust algorithms are also developed to handle outliers. The simulation results confirm the attractive features of the proposed algorithms in large-scale system identification and regression scenarios.
Article
Engineering, Electrical & Electronic
Yun Su, Weixian Tan, Yifan Dong, Wei Xu, Pingping Huang, Jianxin Zhang, Diankun Zhang
Summary: In this study, a novel method for detecting low-resolution and small targets in millimeter wave radar images is proposed. The Wavelet-Conv structure and Wavelet-Attention mechanism are introduced to overcome the limitations of existing detectors. Experimental results demonstrate that the proposed method improves recall and mean average precision while maintaining competitive inference speed.
Article
Engineering, Electrical & Electronic
Xin Wang, Xingxing Jiang, Qiuyu Song, Jie Liu, Jianfeng Guo, Zhongkui Zhu
Summary: This study proposes a variational mode extraction (VME) method for extracting specific modes from complicated signals. By exploring the convergence property of VME, strategies for identifying ICF and determining the balance parameter are designed, and a bandwidth estimation strategy is constructed. The effectiveness of the proposed method for bearings fault diagnosis is verified and compared with other methods.