Youqiang Zhang
YOU?
Author Swipe
View article: SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers
SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers Open
The generation and editing of audio-conditioned talking portraits guided by multimodal inputs, including text, images, and videos, remains under explored. In this paper, we present SkyReels-Audio, a unified framework for synthesizing high-…
View article: Ensemble Network-Based Distillation for Hyperspectral Image Classification in the Presence of Label Noise
Ensemble Network-Based Distillation for Hyperspectral Image Classification in the Presence of Label Noise Open
Deep learning has made remarkable strides in hyperspectral image (HSI) classification, significantly improving classification performance. However, the challenge of obtaining accurately labeled training samples persists, primarily due to t…
View article: Relationship between autism spectrum disorder and peripapillary intraretinal layer thickness: a pediatric retrospective cross-sectional study
Relationship between autism spectrum disorder and peripapillary intraretinal layer thickness: a pediatric retrospective cross-sectional study Open
This study highlights significant differences in retinal features between ASD and NT groups, with implications for understanding ASD pathogenesis and complexity. The findings suggest that easily observable retinal features hold promise as …
View article: Dimba: Transformer-Mamba Diffusion Models
Dimba: Transformer-Mamba Diffusion Models Open
This paper unveils Dimba, a new text-to-image diffusion model that employs a distinctive hybrid architecture combining Transformer and Mamba elements. Specifically, Dimba sequentially stacked blocks alternate between Transformer and Mamba …
View article: CFSE: a Chinese short text classification method based on character frequency sub-word enhancement
CFSE: a Chinese short text classification method based on character frequency sub-word enhancement Open
As a foundation task of natural language processing, text classification is widely used in information retrieval, public opinion analysis, and other related tasks. Facing the problem of sparse features of Chinese short texts, which affects…
View article: Agreement and Disagreement-Based Co-Learning with Dual Network for Hyperspectral Image Classification with Noisy Labels
Agreement and Disagreement-Based Co-Learning with Dual Network for Hyperspectral Image Classification with Noisy Labels Open
Deep learning-based label noise learning methods provide promising solutions for hyperspectral image (HSI) classification with noisy labels. Currently, label noise learning methods based on deep learning improve their performance by modify…
View article: H2A2Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification
H2A2Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification Open
Deep learning (DL) has recently been a core ingredient in modern computer vision tasks, triggering a wave of revolutions in various fields. The hyperspectral image (HSI) classification task is no exception. A wide range of DL-based methods…
View article: Subpixel Multilevel Scale Feature Learning and Adaptive Attention Constraint Fusion for Hyperspectral Image Classification
Subpixel Multilevel Scale Feature Learning and Adaptive Attention Constraint Fusion for Hyperspectral Image Classification Open
Convolutional neural networks (CNNs) play an important role in hyperspectral image (HSI) classification due to their powerful feature extraction ability. Multiscale information is an important means of enhancing the feature representation …
View article: Hybrid Data-Driven Modeling for an AC/DC Power System Considering Renewable Energy Uncertainty
Hybrid Data-Driven Modeling for an AC/DC Power System Considering Renewable Energy Uncertainty Open
The development of grid-connected renewable energy sources and the widespread use of power electronic devices have exacerbated the uncertain, time-varying, and non-linear characteristics of power systems, making accurate and real-time mode…
View article: Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification
Compound Multiscale Weak Dense Network with Hybrid Attention for Hyperspectral Image Classification Open
Recently, hyperspectral image (HSI) classification has become a popular research direction in remote sensing. The emergence of convolutional neural networks (CNNs) has greatly promoted the development of this field and demonstrated excelle…
View article: Double-Branch Network with Pyramidal Convolution and Iterative Attention for Hyperspectral Image Classification
Double-Branch Network with Pyramidal Convolution and Iterative Attention for Hyperspectral Image Classification Open
Deep-learning methods, especially convolutional neural networks (CNN), have become the first choice for hyperspectral image (HSI) classification to date. It is a common procedure that small cubes are cropped from hyperspectral images and t…
View article: Architecture Design of Digital Twin Platform for AC&DC Hybrid Transmission System with MMC-HVDC
Architecture Design of Digital Twin Platform for AC&DC Hybrid Transmission System with MMC-HVDC Open
With the development of power electronic devices, more and more high-power power electronic devices were used in high-voltage DC transmission. The purpose is to improve the stability of grid and the acceptance ability of new energy. The Yu…
View article: Adaptive Nonnegative Sparse Representation for Hyperspectral Image Super-Resolution
Adaptive Nonnegative Sparse Representation for Hyperspectral Image Super-Resolution Open
As the hyperspectral images (HSIs) usually have a low spatial resolution, HSI super-resolution has recently attracted more and more attention to enhance the spatial resolution of HSIs. A common method is to fuse the low-resolution (LR) HSI…
View article: Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance
Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance Open
In the past few years, the sparse representation (SR) graph-based semi-supervised learning (SSL) has drawn a lot of attention for its impressive performance in hyperspectral image classification with small numbers of training samples. Amon…
View article: Ensemble learning based on approximate reducts and bootstrap sampling
Ensemble learning based on approximate reducts and bootstrap sampling Open
Ensemble learning is an effective approach for improving the generalization ability of base classifiers. To generate a set of accurate and diverse base classifiers, different data perturbation schemes have been proposed. For instance, Bagg…
View article: Active Semi-Supervised Random Forest for Hyperspectral Image Classification
Active Semi-Supervised Random Forest for Hyperspectral Image Classification Open
Random forest (RF) has obtained great success in hyperspectral image (HSI) classification. However, RF cannot leverage its full potential in the case of limited labeled samples. To address this issue, we propose a unified framework that em…
View article: Na+/K+ Hybrid Battery Based on a Sulfurized Polyacrylonitrile Cathode
Na+/K+ Hybrid Battery Based on a Sulfurized Polyacrylonitrile Cathode Open
Sulfurized polyacrylonitrile (SPAN) nanocomposites were synthesized and used as a cathode in a novel rechargeable Na+/K+ hybrid battery with high performance for the first time. When 0.9 mol NaPF6 and 0.1 mol KPF6 were dissolved in ethylen…
View article: CIEEC 2018 Table of Contents
CIEEC 2018 Table of Contents Open
View article: Mechanical interlocking of cotton fibers on slightly textured surfaces of metallic cylinders
Mechanical interlocking of cotton fibers on slightly textured surfaces of metallic cylinders Open