Conditional Mutual Information Constrained Deep Learning for Classification [0.03%]
用于分类的深度学习条件互信息约束方法研究
En-Hui Yang,Shayan Mohajer Hamidi,Linfeng Ye et al.
En-Hui Yang et al.
The concepts of conditional mutual information (CMI) and normalized CMI (NCMI) are introduced to measure the concentration and separation performance of a classification deep neural network (DNN) in the output probability distribution space...
Disentanglement of Prosody Representations via Diffusion Models and Scheduled Gradient Reversal [0.03%]
通过扩散模型和计划梯度反转解缠韵律表示
Leyuan Qu,Cornelius Weber,Wei Wang et al.
Leyuan Qu et al.
Prosody plays a fundamental role in human speech and communication, facilitating intelligibility and conveying emotional and cognitive states. Extracting accurate prosodic information from speech is vital for building assistive technology, ...
A Nonlinear Noise-Resistant Zeroing Neural Network Model for Solving Time-Varying Quaternion Generalized Lyapunov Equation and Applications to Color Image Processing [0.03%]
求解时变四元数广义李亚普诺夫方程的非线性抗噪零ING网络模型及其在彩色图像处理中的应用
Lin Xiao,Xiangru Yan,Yongjun He et al.
Lin Xiao et al.
The time-varying Lyapunov equation (TVLE) plays a crucial role in control design and system stability. However, there has been limited research conducted on the time-varying generalized Lyapunov equation in the quaternion field. To tackle t...
Wavelet Transformer: An Effective Method on Multiple Periodic Decomposition for Time Series Forecasting [0.03%]
小波变换：一种有效的时间序列预测多重周期分解方法
Wei Wei,Zi&#x;ang Wang,Bowen Pang et al.
Wei Wei et al.
Time series forecasting has attracted significant interest across various fields in recent years. Notably, Transformers have been extensively investigated for long-term time series forecasting (LTSF) due to their remarkable ability on model...
Temporal-Interim Pose Synthesis and Distillation for Dynamic Human Pose Estimation [0.03%]
时间间隔姿态合成与提炼在动态人体姿态估计中的应用
Renjie Zhang,Di Lin,Xin Wang et al.
Renjie Zhang et al.
In the task of dynamic human pose estimation (dynamic HPE), the temporal relationships between human body parts should be captured comprehensively to understand the dynamic human motions, where the correlated motion information eventually h...
Interpretable Optimization-Inspired Deep Network for Off-Grid Frequency Estimation [0.03%]
用于离网频率估计的可解释优化启发式深层网络
Pingping Pan,Yunjian Zhang,You Li et al.
Pingping Pan et al.
The accuracy of on-grid frequency estimation methods suffers from the quantization error of discrete grids. In this article, a deep unfolded network for off-grid frequency estimation is proposed, dubbed OGFreq. In the OGFreq, there exist tw...
Extended Invariant Risk Minimization for Machine Fault Diagnosis With Label Noise and Data Shift [0.03%]
扩展不变风险最小化在标签噪声和数据变化情况下的机器故障诊断研究
Zhenling Mo,Zijun Zhang,Qiang Miao et al.
Zhenling Mo et al.
Incorrect labels as well as the discrepancy between training and test domain data distributions can significantly affect the effectiveness of supervised data-driven models in machine fault diagnosis applications. Such a challenge can be cha...
Yanru Sun,Zongxia Xie,Haoyu Xing et al.
Yanru Sun et al.
Time series forecasting (TSF) is an essential branch of machine learning with various applications. Most methods for TSF focus on constructing different networks to extract better information and improve performance. However, practical appl...
Xinye Wang,Lei Duan,Lili Guan et al.
Xinye Wang et al.
In this article, we attempt to study a problem of identifying outliers from multiple dimensions, terming it as multidimensional anomaly detection. This task assumes that each sample corresponds to heterogeneous discriminative spaces, where ...
Deep Graph Multi-View Representation Learning With Self-Augmented View Fusion [0.03%]
基于自我增强视图融合的深度图多视角表示学习
Ziheng Jiao,Hongyuan Zhang,Xuelong Li
Ziheng Jiao
Some current researchers attempt to extend the graph neural network (GNN) on multi-view representation learning and learn the latent structure information among the data. Generally, they concatenate the features of each view and employ a si...