Article
Environmental Sciences
Cuiping Shi, Xinlei Zhang, Jingwei Sun, Liguo Wang
Summary: A lightweight convolutional neural network with multi-level feature fusion has been proposed, which maximizes information extraction and avoids information loss, achieving higher classification accuracy and lower model complexity, realizing a trade-off between model accuracy and running speed.
Article
Environmental Sciences
Jinbiao Zhu, Jie Pan, Wen Jiang, Xijuan Yue, Pengyu Yin
Summary: This paper proposes a SAR image fusion classification method based on multi-band information, which addresses the uncertainty issue in SAR image classification by using decision-level combination and Dempster-Shafer evidence theory. It utilizes a convolutional neural network for single-band SAR image classification and fuses the classification results from different bands to improve accuracy.
Article
Environmental Sciences
Xin He, Yushi Chen
Summary: This study introduces a modified MLP method, utilizing spectral-spatial feature mapping and spectral-spatial information mixing for HSI classification. Multiscale-MLP and Soft-MLP are further proposed to improve classification performance by extracting abundant spectral-spatial information with different scales and applying soft split operation. The results show that these MLP-based methods remain competitive for HSI classification compared to CNN.
Article
Plant Sciences
Saleh Albahli, Momina Masood
Summary: Maize leaf disease has a significant impact on the quality and overall crop yield. This study introduces an end-to-end learning CNN architecture called Efficient Attention Network (EANet) based on the EfficientNetv2 model to identify various maize crop diseases. The inclusion of a spatial-channel attention mechanism allows EANet to accurately recognize multiple diseases and handle background noise in realistic field conditions. Experimental results demonstrate that the EANet model outperforms conventional CNNs in terms of performance.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Environmental Sciences
Yuhao Qing, Wenyi Liu
Summary: A new multi-scale residual convolutional neural network model (MRA-NET) for hyperspectral image classification was proposed, which utilizes an efficient channel attention network to improve deep learning classification accuracy. The evaluation on three public datasets demonstrated higher classification accuracy compared to current networks.
Article
Computer Science, Artificial Intelligence
Feng Zhao, Junjie Zhang, Zhe Meng, Hanqiang Liu, Zhenhui Chang, Jiulun Fan
Summary: This article proposes a hybrid network called MVAHN for hyperspectral image (HSI) classification, which combines convolutional neural network (CNN) and transformer structures. It also utilizes a graph convolutional module (GCM) to extract multiple types of feature information. Experimental results show that MVAHN achieves high accuracy on various datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Jiang Liu, Yan Zhang, Danjv Lv, Jing Lu, Shanshan Xie, Jiali Zi, Yue Yin, Haifeng Xu
Summary: This paper investigates the recognition of birdsongs and proposes an ensemble multi-scale convolution neural network (EMSCNN) classification framework based on the feature spectrogram from the wavelet transform. Experimental results show that the proposed model achieves high accuracy and stability in bird species recognition.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Artificial Intelligence
Ronghua Shang, Jiaming Wang, Licheng Jiao, Xiaohui Yang, Yangyang Li
Summary: This paper proposes a spatial feature-based convolutional neural network (SF-CNN) for solving PolSAR classification problems. The special structure of SF-CNN can expand the training set by combining different samples and enhance the network's ability to extract discriminative features in low-dimensional feature space. Experimental results show that SF-CNN outperforms standard CNN in PolSAR image classification tasks.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Ben Chen, Feiwei Qin, Yanli Shao, Jin Cao, Yong Peng, Ruiquan Ge
Summary: The study proposes a novel method for diagnosing leukemia by classifying white blood cells in bone marrow using the WBC-GLAformer model. The model combines the features of convolutional neural networks and transformers to enrich the features and improve classification accuracy by selecting discriminative regions.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Engineering, Biomedical
Shuomin Xiao, Aiping Qu, Haiqin Zhong, Penghui He
Summary: Accurate classification of nuclei in histology images is crucial for cancer diagnosis, prognosis, and therapeutic response prediction. However, the high heterogeneity and complex morphology of nuclei pose challenges to this task. To address these issues, we propose a novel scale and region-enhanced decoding network for nuclei classification. Our method utilizes a region enhancement module and a scale-aware feature fusion module to improve feature maps and learn multi-scale features. Experimental results demonstrate that our method achieves the highest accuracy on multiple datasets, outperforming state-of-the-art methods.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Environmental Sciences
Cuiping Shi, Xin Zhao, Liguo Wang
Summary: This paper proposes a lightweight convolutional neural network based on attention-oriented multi-branch feature fusion (AMB-CNN) for remote sensing image scene classification, which utilizes methods such as multi-branch feature fusion and depth separable convolution to achieve good performance in classification accuracy.
Article
Computer Science, Artificial Intelligence
Gao Huang, Zhuang Liu, Geoff Pleiss, Laurens van der Maaten, Kilian Q. Weinberger
Summary: Recent work has shown that adding shorter connections in convolutional networks can make the network deeper, more accurate, and more efficient in training. This paper introduces Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward manner. DenseNets alleviate the vanishing-gradient problem, encourage feature reuse, and improve parameter efficiency, leading to significant improvements in object recognition tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Geochemistry & Geophysics
Obed Tettey Nartey, Kwabena Sarpong, Daniel Addo, Yunbo Rao, Zhiguang Qin
Summary: In this study, a novel approach called PiCovS is proposed for hyperspectral image classification. The method utilizes both pixel-level and superpixel-level features to capture characteristics of irregular regions. By integrating CNN and GCN, and incorporating covariance pooling and attention mechanism, the model achieves high accuracy.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Pengcheng Jiang, Yu Xue, Ferrante Neri
Summary: This paper proposes a multi-objective pruning method (MOP-FMS) based on feature map selection, which takes the number of FLOPs as a pruning objective in addition to the accuracy rate. The authors design an efficient search space, domain-specific crossover and mutation operators, decoding and pruning methods, and use multi-objective optimization for evaluation. Experimental results demonstrate that the proposed method achieves higher pruning rate without sacrificing the accuracy rate.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Eko Prasetyo, Nanik Suciati, Chastine Fatichah
Summary: This paper proposes an image-based fish classification system using a Convolutional Neural Network (CNN) that combines low-level and high-level features using a multi-level residual network strategy, and introduces new techniques in the CNN architecture to improve performance. Experimental results show that the system performs well on fish image datasets.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Madhumita A. Takalkar, Selvarajah Thuseethan, Sutharshan Rajasegarar, Zenon Chaczko, Min Xu, John Yearwood
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, Madhumita A. Takalkar, Mengyang Duan, Haimin Zhang, Min Xu
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
Engineering, Electrical & Electronic
Lingxiang Wu, Min Xu, Lei Sang, Ting Yao, Tao Mei
Summary: The proposed NADGCN model utilizes grid-stream GCN as a supplement to the region stream and enhances the generalization of the language model by adding a noise module. Experimental results show that it outperforms the comparative baseline models.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Haimin Zhang, Min Xu
Summary: This research aims to extract frame-level features and emotion intensities by transferring emotional information from an image emotion dataset for video representation. An end-to-end network is proposed for joint emotion recognition and intensity learning with unsupervised adversarial adaptation. The experimental results show improved performance compared to previous state-of-the-art methods.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Haimin Zhang, Min Xu
Summary: In this paper, a region-based multiscale network is proposed for learning features for local affective regions and the broad context for affective image recognition. Experimental results show that integrating features from the broad context is effective in improving the recognition performance.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
Haimin Zhang, Min Xu
Summary: The paper proposes a multiple kernel ensemble attention method for graph learning, which automatically learns the optimal kernel function and simplifies the hyperparameter tuning process, effectively improving graph learning performance.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Jiahao Xia, Haimin Zhang, Shiping Wen, Shuo Yang, Min Xu
Summary: The study introduces an efficient multitask neural network ATPN for face alignment, face tracking, and head pose estimation. ATPN improves performance in face alignment with shortcut connections and enhances other tasks with heatmap fusion, while also saving time in face detection and increasing real-time capability for video tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Haimin Zhang, Jiahao Xia, Guoqiang Zhang, Min Xu
Summary: Graph convolutional networks have achieved considerable success in various graph domain tasks. However, the interrelation information between adjacent nodes is not well-considered in these models. This article presents a graph representation learning framework that generates improved node embeddings by learning and propagating edge features. Experimental results show that our model achieves improved performance compared to baseline models.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jiahao Xia, Min Xu, Haimin Zhang, Jianguo Zhang, Wenjian Huang, Hu Cao, Shiping Wen
Summary: This paper proposes a novel face alignment framework, DSLPT, for learning the inherent relation and uncertainty estimation of facial landmarks. Unlike most existing methods that regress facial landmarks directly from global features, DSLPT first generates a rough representation of each landmark from a local patch and then adaptively aggregates them by a case dependent inherent relation. Moreover, a coarse-to-fine framework is introduced to gradually converge to the target facial landmarks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Haimin Zhang, Min Xu, Guoqiang Zhang, Kenta Niwa
Summary: This paper proposes a stochastic regularization method to tackle the oversmoothing issue in graph convolutional networks. By stochastically scaling features and gradients, the convergence of features is alleviated and overall performance is improved. Experimental results on seven benchmark datasets for four graph-based tasks demonstrate the effectiveness of the method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Information Systems
Haimin Zhang, Min Xu
Summary: Recognition of emotions in images is a topic of increasing research interest, and recent studies suggest that utilizing local region information can enhance recognition performance. A deep neural network structure leveraging emotion intensity learning has been proposed, showing improved performance in image emotion recognition.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Proceedings Paper
Imaging Science & Photographic Technology
Ruiheng Zhang, Min Xu, Yaxin Shi, Jian Fan, Chengpo Mu, Lixin Xu
2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2020)
Article
Computer Science, Information Systems
Kamran Shaukat, Suhuai Luo, Vijay Varadharajan, Ibrahim A. Hameed, Min Xu
Article
Computer Science, Artificial Intelligence
Zhiyuan Shi, Quan Pan, Min Xu
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.