-
CLSTM-SNP: Convolutional Neural Network to Enhance Spiking Neural P Systems for Named Entity Recognition Based on Long Short-Term Memory Network Neural Process Lett. (IF 3.1) Pub Date : 2024-03-18 Qin Deng, Xiaoliang Chen, Zaiyan Yang, Xianyong Li, Yajun Du
-
A Feature Selection Method Based on Feature-Label Correlation Information and Self-Adaptive MOPSO Neural Process Lett. (IF 3.1) Pub Date : 2024-03-18 Fei Han, Fanyu Li, Qinghua Ling, Henry Han, Tianyi Lu, Zijian Jiao, Haonan Zhang
-
Deep Reinforcement Learning Model for Stock Portfolio Management Based on Data Fusion Neural Process Lett. (IF 3.1) Pub Date : 2024-03-17 Haifeng Li, Mo Hai
-
An Adaptive Learning Rate Deep Learning Optimizer Using Long and Short-Term Gradients Based on G–L Fractional-Order Derivative Neural Process Lett. (IF 3.1) Pub Date : 2024-03-15 Shuang Chen, Changlun Zhang, Haibing Mu
-
Multi-modal Domain Adaptation Method Based on Parameter Fusion and Two-Step Alignment Neural Process Lett. (IF 3.1) Pub Date : 2024-03-15 Lan Wu, Han Wang, Lishuang Gong, Yuan Yao, Xin Guo, Binquan Li
-
A New Optimization Model for MLP Hyperparameter Tuning: Modeling and Resolution by Real-Coded Genetic Algorithm Neural Process Lett. (IF 3.1) Pub Date : 2024-03-14 Fatima Zahrae El-Hassani, Meryem Amri, Nour-Eddine Joudar, Khalid Haddouch
-
Dissipativity of Stochastic Competitive Neural Networks with Multiple Time Delays Neural Process Lett. (IF 3.1) Pub Date : 2024-03-14 Dandan Tang, Baoxian Wang, Caiqing Hao
-
Deep Convolutional Neural Network Compression Method: Tensor Ring Decomposition with Variational Bayesian Approach Neural Process Lett. (IF 3.1) Pub Date : 2024-03-13
Abstract Due to deep neural networks (DNNs) a large number of parameters, DNNs increase the demand for computing and storage during training, reasoning and deployment, especially when DNNs stack deeper and wider. Tensor decomposition can not only compress DNN models but also reduce parameters and storage requirements while maintaining high accuracy and performance. About tensor ring (TR) decomposition
-
Co-GZSL: Feature Contrastive Optimization for Generalized Zero-Shot Learning Neural Process Lett. (IF 3.1) Pub Date : 2024-03-12 Qun Li, Zhuxi Zhan, Yaying Shen, Bir Bhanu
-
Multi-back-propagation Algorithm for Signal Neural Network Decomposition Neural Process Lett. (IF 3.1) Pub Date : 2024-03-12 Paulo Salgado, T.-P. Azevedo Perdicoúlis
-
PEB-TAXO: Projecting Entities as Boxes for Taxonomy Expansion Neural Process Lett. (IF 3.1) Pub Date : 2024-03-12 Yuhang Zhang, Jiwei Qin, Chongren Feng
-
Non-separation Method-Based Global Stability Criteria for Takagi–Sugeno Fuzzy Quaternion-Valued BAM Delayed Neural Networks Using Quaternion-valued Auxiliary Function-Based Integral Inequality Neural Process Lett. (IF 3.1) Pub Date : 2024-03-12 Sriraman Ramalingam, Oh-Min Kwon
-
SiamRAAN: Siamese Residual Attentional Aggregation Network for Visual Object Tracking Neural Process Lett. (IF 3.1) Pub Date : 2024-03-11 Zhiyi Xin, Junyang Yu, Xin He, Yalin Song, Han Li
-
CFGPFSR: A Generative Method Combining Facial and GAN Priors for Face Super-Resolution Neural Process Lett. (IF 3.1) Pub Date : 2024-03-09 Jinbo Liu, Zhonghua Liu, Weihua Ou, Kaibing Zhang, Yong Liu
-
New Insights on Bidirectional Associative Memory Neural Networks with Leakage Delay Components and Time-Varying Delays Using Sampled-Data Control Neural Process Lett. (IF 3.1) Pub Date : 2024-03-07
Abstract The sampling data control of bidirectional associative memory (BAM) neural network with leakage delay is considered in this article. The BAM model is viewed as a mixed delay that combines a distributed delay, a discrete delay that varies over time, and a delay in the leaking period. The sampling system is then converted to a continuous time-delay system using an input delay method. In order
-
Rethinking Zero-DCE for Low-Light Image Enhancement Neural Process Lett. (IF 3.1) Pub Date : 2024-03-07 Aizhong Mi, Wenhui Luo, Yingxu Qiao, Zhanqiang Huo
-
Harmonious Mutual Learning for Facial Emotion Recognition Neural Process Lett. (IF 3.1) Pub Date : 2024-03-07
Abstract Facial emotion recognition in the wild is an important task in computer vision, but it still remains challenging since the influence of backgrounds, occlusions and illumination variations in facial images, as well as the ambiguity of expressions. This paper proposes a harmonious mutual learning framework for emotion recognition, mainly through utilizing attention mechanisms and probability
-
Density-Based Discriminative Nonnegative Representation Model for Imbalanced Classification Neural Process Lett. (IF 3.1) Pub Date : 2024-03-07 Yanting Li, Shuai Wang, Junwei Jin, Hongwei Tao, Jiaofen Nan, Huaiguang Wu, C. L. Philip Chen
-
CEEMDAN-Based Hybrid Machine Learning Models for Time Series Forecasting Using MARS Algorithm and PSO-Optimization Neural Process Lett. (IF 3.1) Pub Date : 2024-03-06 Sandip Garai, Ranjit Kumar Paul, Md Yeasin, A. K. Paul
-
A Novel Boundary-Guided Global Feature Fusion Module for Instance Segmentation Neural Process Lett. (IF 3.1) Pub Date : 2024-03-06 Linchun Gao, Shoujun Wang, Songgui Chen
-
HF-YOLO: Advanced Pedestrian Detection Model with Feature Fusion and Imbalance Resolution Neural Process Lett. (IF 3.1) Pub Date : 2024-03-06 Lihu Pan, Jianzhong Diao, Zhengkui Wang, Shouxin Peng, Cunhui Zhao
-
A Correlation-Redundancy Guided Evolutionary Algorithm and Its Application to High-Dimensional Feature Selection in Classification Neural Process Lett. (IF 3.1) Pub Date : 2024-03-06 Xiang Sun, Shunsheng Guo, Shiqiao Liu, Jun Guo, Baigang Du
-
DE3TC: Detecting Events with Effective Event Type Information and Context Neural Process Lett. (IF 3.1) Pub Date : 2024-03-06
Abstract Event Detection (ED) is a crucial information extraction task that aims to identify the event triggers and classify them into predefined event types. However, most existing methods did not perform well when processing events with implicit triggers. And most methods considered ED as a sentence-level task, lacking effective context for event semantics. Moreover, how to maintain good performance
-
FEASE: Feature Selection and Enhancement Networks for Action Recognition Neural Process Lett. (IF 3.1) Pub Date : 2024-03-06 Lu Zhou, Yuanyao Lu, Haiyang Jiang
-
Image Deblurring Using Feedback Mechanism and Dual Gated Attention Network Neural Process Lett. (IF 3.1) Pub Date : 2024-03-06 Jian Chen, Shilin Ye, Zhuwu Jiang, Zhenghan Fang
-
Enhancing Generalization in Few-Shot Learning for Detecting Unknown Adversarial Examples Neural Process Lett. (IF 3.1) Pub Date : 2024-03-05
Abstract Deep neural networks, particularly convolutional neural networks, are vulnerable to adversarial examples, undermining their reliability in visual recognition tasks. Adversarial example detection is a crucial defense mechanism against such attacks but often relies on empirical observations and specialized metrics, posing challenges in terms of data efficiency, generalization to unknown attacks
-
Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions Neural Process Lett. (IF 3.1) Pub Date : 2024-03-04 Hongliang Zhang, Yuteng Zhang, Rui Wang, Haiyang Pan, Bin Chen
-
FTUNet: A Feature-Enhanced Network for Medical Image Segmentation Based on the Combination of U-Shaped Network and Vision Transformer Neural Process Lett. (IF 3.1) Pub Date : 2024-03-04 Yuefei Wang, Xi Yu, Yixi Yang, Shijie Zeng, Yuquan Xu, Ronghui Feng
-
Stability and Hopf Bifurcation Analysis of A Fractional-Order BAM Neural Network with Two Delays Under Hybrid Control Neural Process Lett. (IF 3.1) Pub Date : 2024-03-02 Yuan Ma, Yumei Lin, Yunxian Dai
-
Exponential Synchronization of Complex Dynamic Networks with Time Delay and Uncertainty via Adaptive Event-Triggered Control Neural Process Lett. (IF 3.1) Pub Date : 2024-03-02 Yinguang Zhao, Yuechao Ma
-
Parameter-Free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients Neural Process Lett. (IF 3.1) Pub Date : 2024-03-02
Abstract Approximation of the value functions in value-based deep reinforcement learning induces overestimation bias, resulting in suboptimal policies. We show that when the reinforcement signals received by the agents have a high variance, deep actor-critic approaches that overcome the overestimation bias lead to a substantial underestimation bias. We first address the detrimental issues in the existing
-
Stability of Fractional Reaction-Diffusion Memristive Neural Networks Via Event-Based Hybrid Impulsive Controller Neural Process Lett. (IF 3.1) Pub Date : 2024-03-02 Huiyu Wang, Shutang Liu, Xiang Wu, Jie Sun, Wei Qiao
-
Breaking Time Invariance: Assorted-Time Normalization for RNNs Neural Process Lett. (IF 3.1) Pub Date : 2024-03-01 Cole Pospisil, Vasily Zadorozhnyy, Qiang Ye
-
A Polishing Model for Machine-Generated Ancient Chinese Poetry Neural Process Lett. (IF 3.1) Pub Date : 2024-03-01
Abstract Machine poetry generation has been studied for decades, among which ancient Chinese poetry is still challenging in the field of poetry generation due to its unique regularity and rhythm. The quality improvement of ancient Chinese poetries is one of the most promising research areas of ancient Chinese Natural Language Processing. This paper proposes an ancient Chinese poetry polishing model
-
Novel LMI-Based Boundary Stabilization of Stochastic Delayed Reaction-Diffusion Cohen–Grossberg BAM Neural Networks with Impulsive Effects Neural Process Lett. (IF 3.1) Pub Date : 2024-02-28 V. Gokulakrishnan, R. Srinivasan, M. Syed Ali, Grienggrai Rajchakit, Bandana Priya
-
Consensus of multi-agent systems with randomly occurring nonlinearities via uncertain pinning control under switching topologies Neural Process Lett. (IF 3.1) Pub Date : 2024-02-28 Xin Sui, Yongqing Yang, Fei Wang
-
PCTDepth: Exploiting Parallel CNNs and Transformer via Dual Attention for Monocular Depth Estimation Neural Process Lett. (IF 3.1) Pub Date : 2024-02-26 Chenxing Xia, Xiuzhen Duan, Xiuju Gao, Bin Ge, Kuan-Ching Li, Xianjin Fang, Yan Zhang, Ke Yang
-
A Time-Series-Based Sample Amplification Model for Data Stream with Sparse Samples Neural Process Lett. (IF 3.1) Pub Date : 2024-02-26
Abstract The data stream is a dynamic collection of data that changes over time, and predicting the data class can be challenging due to sparse samples, complex interdependent characteristics between data, and random fluctuations. Accurately predicting the data stream in sparse data can create complex challenges. Due to its incremental learning nature, the neural networks suitable approach for streaming
-
A Domain Adaptive Semantic Segmentation Method Using Contrastive Learning and Data Augmentation Neural Process Lett. (IF 3.1) Pub Date : 2024-02-26 Yixiao Xiang, Lihua Tian, Chen Li
-
DPR-GAN: Dual-Stream Progressive Refinement for Adversarial 3D Point Cloud Generation Neural Process Lett. (IF 3.1) Pub Date : 2024-02-24 Xiangyang Wang, Jiale Chen, Rui Wang
-
Conv-Attention: A Low Computation Attention Calculation Method for Swin Transformer Neural Process Lett. (IF 3.1) Pub Date : 2024-02-24 Zhehang Lou, Suyun Luo, Xiaoci Huang, Dan Wei
-
Stability Analysis of Deep Belief Network: Based SD-AR Model for Nonlinear Time Series Neural Process Lett. (IF 3.1) Pub Date : 2024-02-23
Abstract As for nonlinear time series prediction, many different kinds of varying-coefficient models have been proposed and analysised in recent years. A kind of varying functional-coefficient autoregressive model, called the deep belief network-based state-dependent autoregressive (DBN-AR) model is considered in this paper. The stability conditions and existing conditions of limit cycle of the DBN-AR
-
Adaptive Evolutionary Reinforcement Learning with Policy Direction Neural Process Lett. (IF 3.1) Pub Date : 2024-02-23 Caibo Dong, Dazi Li
-
About Latent Roles in Forecasting Players in Team Sports Neural Process Lett. (IF 3.1) Pub Date : 2024-02-23 Luca Scofano, Alessio Sampieri, Giuseppe Re, Matteo Almanza, Alessandro Panconesi, Fabio Galasso
-
Research on Event Target Recognition Based on DRUNet and Multi-scale Attention Neural Process Lett. (IF 3.1) Pub Date : 2024-02-23 Zi-Long Liu, Bing Tan
-
A Dynamic Adaptive and Resource-Allocated Selection Method Based on TOPSIS and VIKOR in Federated Learning Neural Process Lett. (IF 3.1) Pub Date : 2024-02-23 Lin Li, Wei Shi, Shuyu Chen, Jun Liu, Jiangping Huang, Pengcheng Liu
-
Text-Vision Relationship Alignment for Referring Image Segmentation Neural Process Lett. (IF 3.1) Pub Date : 2024-02-22
Abstract Referring image segmentation aims to segment object in an image based on a referring expression. Its difficulty lies in aligning expression semantics with visual instances. The existing methods based on semantic reasoning are limited by the performance of external syntax parser and do not explicitly explore the relationships between visual instances. This article proposes an end-to-end method
-
Residual Contextual Hourglass Network for Single-Image Deraining Neural Process Lett. (IF 3.1) Pub Date : 2024-02-22 Weina Zhou, Linhui Ye, Xiu Wang
-
APRE: Annotation-Aware Prompt-Tuning for Relation Extraction Neural Process Lett. (IF 3.1) Pub Date : 2024-02-21 Chao Wei, Yanping Chen, Kai Wang, Yongbin Qin, Ruizhang Huang, Qinghua Zheng
-
NAVS: A Neural Attention-Based Visual SLAM for Autonomous Navigation in Unknown 3D Environments Neural Process Lett. (IF 3.1) Pub Date : 2024-02-21 Yu Wu, Niansheng Chen, Guangyu Fan, Dingyu Yang, Lei Rao, Songlin Cheng, Xiaoyong Song, Yiping Ma
-
Stronger Heterogeneous Feature Learning for Visible-Infrared Person Re-Identification Neural Process Lett. (IF 3.1) Pub Date : 2024-02-20 Hao Wang, Xiaojun Bi, Changdong Yu
-
Elastic Deep Sparse Self-Representation Subspace Clustering Network Neural Process Lett. (IF 3.1) Pub Date : 2024-02-20 Qiaoping Wang, Xiaoyun Chen, Yan Li, Yanming Lin
-
FCPFNet: Feature Complementation Network with Pyramid Fusion for Semantic Segmentation Neural Process Lett. (IF 3.1) Pub Date : 2024-02-20 Jingsheng Lei, Chente Shu, Qiang Xu, Yunxiang Yu, Shengying Yang
-
TLS-RWKV: Real-Time Online Action Detection with Temporal Label Smoothing Neural Process Lett. (IF 3.1) Pub Date : 2024-02-19
Abstract Online action detection (OAD)is a challenging task that involves predicting the ongoing action class in real-time streaming videos, which is essential in the field of autonomous driving and video surveillance. In this article, we propose an approach for OAD based on the Receptance Weighted Key Value (RWKV) model with temporal label smooth. The RWKV model captures temporal dependencies and
-
Few-Shot Semantic Segmentation via Mask Aggregation Neural Process Lett. (IF 3.1) Pub Date : 2024-02-17 Wei Ao, Shunyi Zheng, Yan Meng, Yang Yang
-
Moving Object Detection Method Based on the Fusion of Online Moving Window Robust Principal Component Analysis and Frame Difference Method Neural Process Lett. (IF 3.1) Pub Date : 2024-02-17 Q. L. Zhang, S. L. Li, J. G. Duan, J. Y. Qin, Y. Zhou
-
MGSGA: Multi-grained and Semantic-Guided Alignment for Text-Video Retrieval Neural Process Lett. (IF 3.1) Pub Date : 2024-02-17 Xiaoyu Wu, Jiayao Qian, Lulu Yang
-
Combining Swin Transformer and Attention-Weighted Fusion for Scene Text Detection Neural Process Lett. (IF 3.1) Pub Date : 2024-02-17 Xianguo Li, Xingchen Yao, Yi Liu
-
HIFINet: Examination-Diagnosis-Treatment Hierarchical Feedback Interaction Network for Medication Recommendation Neural Process Lett. (IF 3.1) Pub Date : 2024-02-17
Abstract Medication combination recommendation is critical in clinic, since accurately predicting therapeutic drug can provide essential decision support to physicians. However, current approaches do not consider the multilevel structure of electronic health record (EHR) data or the hierarchical dependencies between multiple visits, leading to suboptimal recommendations. To address these limitations
-
GNNCL: A Graph Neural Network Recommendation Model Based on Contrastive Learning Neural Process Lett. (IF 3.1) Pub Date : 2024-02-16 Jinguang Chen, Jiahe Zhou, Lili Ma