Explanipedia

TCLformer: Enhancing Multi-Scale Time Series Forecasting with Temporal Decomposition and Sparse Convolutional Attention Open

Xiaohe Wu, Kun Zhang, Chenxi Cai, Dianying Chen, Yaodi Liu · 2025

Real-world multivariate time series (MTS) often contain complex multi-scale temporal dependencies, and accurately capturing their short-term and long-term patterns remains a challenging task. Although Transformer-based models have made sig…

Study of the recovery of energy confinement and density pump-out following impurity injection in EAST high-density plasmas Open

Kaibo Nan, Jilei Hou, Zhen Zhou, Jie Zhang, Zhe Yuan , et al. · 2025

This work presents an investigation conducted on the Experimental Advanced Superconducting Tokamak (EAST) high-density H-mode discharges with low-Z impurity (argon) injection, aiming to explore potential approaches and mechanisms for the r…

Pseudo-Label Guided Real-World Image De-weathering: A Learning Framework with Imperfect Supervision Open

Heming Xu, Xiaohui Liu, Zhilu Zhang, Hongzhi Zhang, Xiaohe Wu , et al. · 2025

Real-world image de-weathering aims at removingvarious undesirable weather-related artifacts, e.g., rain, snow,and fog. To this end, acquiring ideal training pairs is crucial.Existing real-world datasets are typically constructed paired da…

<i>S</i><sup>2</sup>C‐HAR: A Semi‐Supervised Human Activity Recognition Framework Based on Contrastive Learning Open

Xue Li, Mingxing Liu, Lanshun Nie, Wenxiao Cheng, Xiaohe Wu , et al. · 2025

Human activity recognition (HAR) has emerged as a critical element in various domains, such as smart healthcare, smart homes, and intelligent transportation, owing to the rapid advancements in wearable sensing technology and mobile computi…

DeblurDiff: Real-World Image Deblurring with Generative Diffusion Models Open

Lingshun Kong, Jiawei Zhang, Dongqing Zou, Jimmy Ren, Xiaohe Wu , et al. · 2025

Diffusion models have achieved significant progress in image generation. The pre-trained Stable Diffusion (SD) models are helpful for image deblurring by providing clear image priors. However, directly using a blurry image or pre-deblurred…

A Two-Stage Boundary-Enhanced Contrastive Learning approach for nested named entity recognition Open

Yaodi Liu, Kun Zhang, Rong Tong, Chenxi Cai, Dianying Chen , et al. · 2025

Generative Inbetweening through Frame-wise Conditions-Driven Video Generation Open

Tianyi Zhu, Dongwei Ren, Qilong Wang, Xiaohe Wu, Wangmeng Zuo · 2024

Generative inbetweening aims to generate intermediate frame sequences by utilizing two key frames as input. Although remarkable progress has been made in video generation models, generative inbetweening still faces challenges in maintainin…

Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention Open

Hannan Lu, Xiaohe Wu, Shudong Wang, Xiameng Qin, Xinyu Zhang , et al. · 2024

Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms …

Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs Open

Xinya Shu, Yu Li, Dongwei Ren, Xiaohe Wu, Jin Li , et al. · 2024

For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurrin…

A Flat-Span Contrastive Learning Method for Nested Named Entity Recognition Open

Yaodi Liu, Kun Zhang, Rong Tong, Chenxi Cai, Dianying Chen , et al. · 2024

Most Named entity recognition (NER) methods can only handle flat entities and ignore nested entities. In Natural language processing (NLP), it is common to contain other entities within entities. Therefore, we propose a Flat-Span contrasti…

Learning Real-World Image De-weathering with Imperfect Supervision Open

Xiaohui Liu, Zhilu Zhang, Xiaohe Wu, Chaoyu Feng, Xiaotao Wang , et al. · 2024

Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumina…

Reconstruction of Poloidal Magnetic Fluxes on EAST based on Neural Networks with Measured Signals Open

Feifei Long, Xiangze Xia, Jian Liu, Zixi Liu, Xiaodong Wu , et al. · 2024

The accurate construction of tokamak equilibria, which is critical for the effective control and optimization of plasma configurations, depends on the precise distribution of magnetic fields and magnetic fluxes. Equilibrium fitting codes, …

S2c-Har：A Semi-Supervised Human Activity Recognition Framework Based on Contrastive Learning Open

Xue Li, Lanshun Nie, Mingxing Liu, Wenxiao Cheng, Haiqi Zhu , et al. · 2024

Pseudo-Isp: Learning Pseudo In-Camera Signal Processing Pipeline from a Color Image Denoiser Open

Yue Cao, Xiaohe Wu, Shuran Qi, Xiao Liu, Zhongqin Wu , et al. · 2024

Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning Open

Qing Miao, Xiaohe Wu, Chao Xu, Yanli Ji, Wangmeng Zuo , et al. · 2023

Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supervised learning (SSL). However, this approach has a limitat…

Learning Real-World Image De-Weathering with Imperfect Supervision Open

Xiaohui Liu, Zhilu Zhang, Xiaohe Wu, Chaoyu Feng, Xiaotao Wang , et al. · 2023

Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumina…

Survey on leveraging pre-trained generative adversarial networks for image editing and restoration Open

Ming Liu, Yuxiang Wei, Xiaohe Wu, Wangmeng Zuo, Lei Zhang · 2023

Generative adversarial networks (GANs) have drawn enormous attention due to their simple yet effective training mechanism and superior image generation quality. With the ability to generate photorealistic high-resolution (e.g., 1024 × 1024…

Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning Open

Qing Miao, Xiaohe Wu, Chao Xu, Yanli Ji, Wangmeng Zuo , et al. · 2023

Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser Open

Yue Cao, Xiaohe Wu, Shuran Qi, Xiao Liu, Zhongqin Wu , et al. · 2021

The success of deep denoisers on real-world color photographs usually relies on the modeling of sensor noise and in-camera signal processing (ISP) pipeline. Performance drop will inevitably happen when the sensor and ISP pipeline of test i…

Engineering Student Development And Retention Strategies At A Historically Black University Open

Morrison Obeng, Xiaohe Wu · 2020

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Engineering Student Development and Retention Strategies at A Historically Black University Abstract Student retention and completion o…

Unpaired Learning of Deep Image Denoising Open

Xiaohe Wu, Ming Liu, Yue Cao, Dongwei Ren, Wangmeng Zuo · 2020

We investigate the task of learning blind image denoising networks from an unpaired set of clean and noisy images. Such problem setting generally is practical and valuable considering that it is feasible to collect unpaired noisy and clean…

Remove Cosine Window from Correlation Filter-based Visual Trackers: When and How Open

Feng Li, Xiaohe Wu, Wangmeng Zuo, David Zhang, Lei Zhang · 2019

Correlation filters (CFs) have been continuously advancing the state-of-the-art tracking performance and have been extensively studied in the recent few years. Most of the existing CF trackers adopt a cosine window to spatially reweight ba…

Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking Open

Yingjie Yao, Xiaohe Wu, Lei Zhang, Shiguang Shan, Wangmeng Zuo · 2018

Correlation filter (CF) based trackers generally include two modules, i.e., feature representation and on-line model adaptation. In existing off-line deep learning models for CF trackers, the model adaptation usually is either abandoned or…

VITAL: VIsual Tracking via Adversarial Learning Open

Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao , et al. · 2018

The tracking-by-detection framework consists of two stages, i.e., drawing samples around the target object in the first stage and classifying each sample as the target object or as background in the second stage. The performance of existin…

Optimal Waveform Design for Smart Noise Jamming Open

Xingyu Xia, Hao Daoliang, Xiaohe Wu · 2017

Optimal jamming waveform design is an effective way to improve the efficiency of electronic countermeasure, which makes it the focus issue in the field of electronic warfare.With new jamming technology emerging, jamming waveforms present c…

Learning Support Correlation Filters for Visual Tracking Open

Wangmeng Zuo, Xiaohe Wu, Liang Lin, Lei Zhang, Ming–Hsuan Yang · 2016

Sampling and budgeting training examples are two essential factors in tracking algorithms based on support vector machines (SVMs) as a trade-off between accuracy and efficiency. Recently, the circulant matrix formed by dense sampling of tr…

F-SVM: Combination of Feature Transformation and SVM Learning via Convex Relaxation Open

Xiaohe Wu, Wangmeng Zuo, Yuanyuan Zhu, Liang Lin · 2015

The generalization error bound of support vector machine (SVM) depends on the ratio of radius and margin, while standard SVM only considers the maximization of the margin but ignores the minimization of the radius. Several approaches have …

Xiaohe Wu YOU? Author Swipe