李兵｜武汉大学｜学者主页

2026

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

Guan-Yi Qin, Jiejing Liang, Bingbing Zhang, Lishen Qu, Yanxin Guan, Huimin Zeng, Lei Zhang, R. Timofte, Jian-Hui Sun, Xinli Yue, Tao Shao, Huanle Hou, Wen-Jie Liao, Shu-Hao Han, Jie Yuan, Chun-Le Guo, Chongyi Li, Ze-Wen Chen, Yun-Ze Liu, Jian Guo, Juan Wang, Yun Zeng, Bing Li, Wei-Ming Hu, He Li, De-Hua Liu, Xinjie Zhang, Qiang Li, Lingyong Yan, Wei Dong, Qingsen Yan, Xingcan Li, Sheng Zhou, M. Yin, Yin-Xian Zhang, Hongbo Wang, Jikai Xu, Zhao-Hui Fan, Dandan Zhu, Wei Sun, Wei-Xia Zhang, Kun Zhu, Nana Zhang, Kai-Wei Zhang, Qianqian Zhang, Zhi-Han Zhang, W. Gordon, Lin Wu, Jiachen Tu, Guoyi Xu, Yao-Xin Jiang, Cici Liu, Yaokun Shi

arXiv.org

精选作品

期刊论文

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

Open-Tag: A Generative Framework for Open-World Multimodal Tagging

SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering

Deepfake Detection via Exploring Degradation Inconsistency

Multi-modal face anti-spoofing via self-supervised learning

The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization

Ocean: Object-aware Anchor-free Tracking with Matching-relation Learning

Arbitrary Ratio Feature Compression via Next Token Prediction

QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization

A Consumption-Generation Driven Deep Embedding Framework for Next Activity Prediction

A Two-Stage Learning Guided Multi-Objective Evolutionary Algorithm for Task Offloading in Edge Computing

Enhancing Intent Understanding and Preference Learning for Sequential Recommendation

A Hierarchical Preference-Guided Multi-Objective Reinforcement Learning Method for Task Offloading in Vehicular Edge Computing

MDGRec:基于多元关系融合的移动应用第三方库推荐方法

Noise-Optimized Distribution Distillation for Dataset Condensation

FiGVCL: Fine-Grained Benchmark and Method for Video Copy Localization

Reversing Flow for Image Restoration

Visual-Instructed Degradation Diffusion for All-in-One Image Restoration

IssueCourier: Multi-Relational Heterogeneous Temporal Graph Neural Network for Open-Source Issue Assignment

Empirical mode decomposition with multivariable time series feature learning for QoS prediction

MHP-RCA: Multivariate Hawkes Process-based Root Cause Analysis in microservice systems

ReconRCA: Root Cause Analysis in Microservices with Incomplete Metrics

TracePicker: Optimization-Based Trace Sampling for Microservice-Based Systems

TVDiag: A Task-oriented and View-invariant Failure Diagnosis Framework for Microservice-based Systems with Multimodal Data

DDASR: Deep Diverse API Sequence Recommendation

DARTScore: DuAl-Reconstruction Transformer for Video Captioning Evaluation

IterDepth: Iterative Residual Refinement for Outdoor Self-Supervised Multi-Frame Monocular Depth Estimation

Learn from Noise: Detecting Deepfakes via Regional Noise Consistency

Token Caching for Diffusion Transformer Acceleration

MicroIRC: Instance-level Root Cause Localization for Microservice Systems

PBScaler: A Bottleneck-Aware Autoscaling Framework for Microservice-Based Applications

TGformer: A Graph Transformer Framework for Knowledge Graph Embedding

How LLMs Aid in UML Modeling: An Exploratory Study with Novice Analysts

PRKG: Pre-Training Representation and Knowledge-Graph-Enhanced Web Service Recommendation for Mashup Creation

Dynamic adjustment of hyperparameters for anchor-based detection of objects with large image size differences

Learning to Exploit the Sequence-Specific Prior Knowledge for Image Processing Pipelines Optimization

Hierarchical Curriculum Learning for No-Reference Image Quality Assessment

Circle-Net: An Unsupervised Lightweight-Attention Cyclic Network for Hyperspectral and Multispectral Image Fusion

Jointing Recurrent Across-Channel and Spatial Attention for Multi-Object Tracking With Block-Erasing Data Augmentation

AUNet: Learning Relations Between Action Units for Face Forgery Detection

Self-Prior Guided Pixel Adversarial Networks for Blind Image Inpainting

ViLEM: Visual-Language Error Modeling for Image-Text Retrieval

Learning from the Raw Domain: Cross Modality Distillation for Compressed Video Action Recognition

TranSkeleton: Hierarchical Spatial–Temporal Transformer for Skeleton-Based Action Recognition

Ranking-Based Color Constancy With Limited Training Samples

SDFormer: A shallow-to-deep feature interaction for knowledge graph embedding

BGCL: Bi-subgraph network based on graph contrastive learning for cold-start QoS prediction

Attention-Based Deep Reinforcement Learning for Edge User Allocation

A Deep Reinforcement Learning-Based Pointer Scoring Network for Edge Task Scheduling

Understanding Bugs in Multi-Language Deep Learning Frameworks

A Deep Reinforcement Learning Approach to Online Microservice Deployment in Mobile Edge Computing

Inter-Intra Cross-Modality Self-Supervised Video Representation Learning by Contrastive Clustering

Cross-Architecture Knowledge Distillation

Teacher-Guided Learning for Blind Image Quality Assessment

Cascaded Decoding and Multi-Stage Inference for Spatio-Temporal Video Grounding

Learning Target-aware Representation for Visual Tracking via Informative Interactions

Attention-Aware Learning for Hyperparameter Prediction in Image Processing Pipelines

CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation

Exploring Motion Information for Distractor Suppression in Visual Tracking

Learning Video-Text Aligned Representations for Video Captioning

Long-Short Term Cross-Transformer in Compressed Domain for Few-Shot Video Classification

SSAU-Net: A Spectral–Spatial Attention-Based U-Net for Hyperspectral Image Fusion

Narrowing the Gap: Improved Detector Training With Noisy Location Annotations

Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning

PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning

Multi-scale self-attention-based feature enhancement for detection of targets with small image sizes

Learning to Explore Distillability and Sparsability: A Joint Framework for Model Compression

Learnable Pixel Clustering Via Structure and Semantic Dual Constraints for Unsupervised Image Segmentation

A method of value model convergence and profit optimization for crossover services

Multi-information fusion based few-shot Web service classification

Goal Model Convergence and Conflict Detection for Crossover Services

Code smells detection via modern code review: a study of the OpenStack and Qt communities

Web API recommendation via combining graph attention representation and deep factorization machines quality prediction

Improving generality and accuracy of existing public development project selection methods: a study on GitHub ecosystem

Aligned metric representation based balanced multiset ensemble learning for heterogeneous defect prediction

基于图神经网络的软件系统中关键类的识别

One More Check: Making "Fake Background" Be Tracked Again

DPFPS: Dynamic and Progressive Filter Pruning for Compressing Convolutional Neural Networks from Scratch