Article
Computer Science, Information Systems
Shaikh Abdus Samad, J. Gitanjali
Summary: Feature space enrichment is crucial for the development of attention mechanisms in CNNs. The research presents SCMA, an attention mechanism that combines channel and spatial attention to extract features efficiently while balancing parameter efficiency and accuracy.
Article
Engineering, Geological
Penglei Li, Yi Wang, Guosen Xu, Lizhe Wang
Summary: This study presents a novel robust rainfall-induced landslide detection model guided by contrastive learning. The model combines deep learning techniques, such as residual blocks and channel attention modules, to accurately predict landslide locations. It also utilizes contrastive dice similarity coefficient loss to maintain consistency in landslide regions. Experimental results demonstrate that the proposed model performs excellently, outperforming other classic segmentation methods in crucial criteria.
Article
Engineering, Electrical & Electronic
Shui-Hua Wang, Steven Lawrence Fernandes, Ziquan Zhu, Yu-Dong Zhang
Summary: To detect COVID-19 patients more accurately, a 12-layer attention-based VGG-style network called AVNC was proposed, using a chest CT dataset and incorporating attention module and data augmentation method, achieving high sensitivity, precision, and F1 scores.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Information Systems
Shimaa Saber, Khalid Amin, Pawel Plawiak, Ryszard Tadeusiewicz, Mohamed Hammad
Summary: Person re-identification is a method that uses multiple non-overlapping cameras for identification, and it has been successfully applied in computer vision applications. To address issues such as occlusion, illumination changes, and pose changes, a new graph convolutional network with attention modules is proposed. Experimental results demonstrate the high generalization ability and superior performance of the proposed method.
INFORMATION SCIENCES
(2022)
Article
Thermodynamics
Hakan Acikgoz, Umit Budak, Deniz Korkmaz, Ceyhun Yildiz
Summary: This paper introduces a novel deep neural network (WSFNet) for efficiently forecasting multi-step ahead wind speed, incorporating dense connections and channel attention modules, as well as utilizing variational mode decomposition for preprocessing, achieving competitive performance.
Article
Computer Science, Artificial Intelligence
Hanliang Jiang, Fuhao Shen, Fei Gao, Weidong Han
Summary: This study aims to build an efficient and (partially) explainable automatic classification model for pulmonary nodules. By using neural architecture search and convolutional block attention module, excellent accuracy/speed trade-off is achieved and helps to understand the reasoning process. Ensemble of diverse neural networks is utilized to improve prediction accuracy and robustness.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Jingying Chen, Lei Yang, Lei Tan, Ruyi Xu
Summary: This paper proposes a novel orthogonal channel attention-based multi-task learning approach for multi-view facial expression recognition. By utilizing a Siamese CNN and a multi-task learning framework, as well as designing a separated channel attention module and an orthogonal channel attention loss, this approach achieves good recognition accuracy on two datasets.
PATTERN RECOGNITION
(2022)
Article
Engineering, Electrical & Electronic
Hou Xiaoqi, Gao Yong
Summary: This paper proposes a new waveform separation-demodulation scheme for single-channel blind separation, achieving separation and demodulation through a convolutional time-domain network and low-complexity per-survivor processing method, surpassing other network structures in performance evaluation.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Environmental Sciences
Qing Liu, Yongsheng Dong, Zhiqiang Jiang, Yuanhua Pei, Boshi Zheng, Lintao Zheng, Zhumu Fu
Summary: With the development of image segmentation technology, the importance of image context information in semantic segmentation has been recognized. In order to capture rich context information effectively, we proposed a Multi-Pooling Context Network (MPCNet) for image semantic segmentation. The network includes Pooling Context Aggregation Module and Spatial Context Module to capture deep context information and detailed spatial context respectively. Experimental results on multiple datasets demonstrate the effectiveness of our proposed network in context extraction.
Article
Engineering, Electrical & Electronic
Ziqiang Lu, Yanwu Dong, Jie Li, Ziying Lu, Pengjie He, Haibo Ru
Summary: This study introduces a new channel attention module LCM, which optimizes the correlation between channel features by integrating global information and channel dependence, showing superiority in experiments.
JOURNAL OF SENSORS
(2022)
Article
Computer Science, Information Systems
Tong Fu, Liquan Chen, Zhangjie Fu, Kunliang Yu, Yu Wang
Summary: This paper introduces a new approach for image steganalysis based on convolutional neural networks that focuses on complex regional texture features and improves detection accuracy. Experimental results demonstrate that the proposed model outperforms existing models in terms of detection accuracy.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2022)
Article
Computer Science, Artificial Intelligence
Sujit Kumar Das, Suyel Namasudra, Awnish Kumar, Nageswara Rao Moparthi
Summary: This paper presents an efficient approach based on Convolutional Neural Network (CNN) called AESPNet for the identification of Diabetic Foot Ulcer (DFU). Compared with other standard CNN-based schemes, AESPNet demonstrates better performance in DFU classification.
IMAGE AND VISION COMPUTING
(2023)
Article
Multidisciplinary Sciences
Fucai Hu, Xiaohui Song, Ruhan He, Yongsheng Yu
Summary: This paper proposes a sound source localization (SSL) model based on residual network and channel attention mechanism. The method uses log-Mel spectrogram and GCC-PHAT as input features, and extracts time-frequency information using the residual structure and channel attention mechanism, resulting in improved localizing performance.
SCIENTIFIC REPORTS
(2023)
Article
Automation & Control Systems
Arshiana Shamir, Nokap Park, Bumshik Lee
Summary: A novel deep-learning network is proposed for brightness enhancement of old images, which combines curve map estimation and attention-guided illumination map to adjust the dynamic range and illumination of the images. Experimental results show that the proposed method outperforms existing methods in brightness enhancement on old photo and video datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Environmental Sciences
Yuanyuan Wu, Mengxing Huang, Yuchun Li, Siling Feng, Di Wu
Summary: This study introduces a pan-sharpening method combining remote sensing images with CNN, proposing a distributed fusion framework based on residual CNN, RDFNet, to improve image resolution and preserve spectral information. Experimental results show that RDFNet performs superiorly in enhancing spatial resolution and fusion quality.
Article
Computer Science, Artificial Intelligence
Zhigang Liu, Dongyu Li, Shuzhi Sam Ge, Feng Tian
APPLIED INTELLIGENCE
(2020)
Article
Engineering, Electrical & Electronic
Liu Zhigang, Du Juan, Tian Feng, Wen Jiazheng
Summary: Accurate recognition of small traffic signs is crucial for the safety of intelligent transportation systems. A novel recognition framework named attentive context region-based detection framework (AC-RDF) is proposed in this paper, which utilizes attentive context feature and attentive loss function to improve recognition accuracy. Experimental results on the Tsinghua-Tencent 100K dataset demonstrate the superiority of the proposed framework in detecting small traffic signs and achieving state-of-the-art performance.
CHINESE JOURNAL OF ELECTRONICS
(2021)
Article
Computer Science, Information Systems
Zhigang Liu, Juan Du, Feng Tian, Jiazheng Wen
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.