Publications (21)
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
Xin Li, Kun Yuan, Bingchen Li +110
This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Qualit…
Extreme eigenvalues of principal minors of random matrix with moment conditions
Jianwei Hu, Seydou Keita, Kang Fu
Let be a random sample of size from a -dimensional population distribution, where . Consider a symmetric matrix $W=X^\top…
FedUTR: Federated Recommendation with Augmented Universal Textual Representation for Sparse Interaction Scenarios
Kang Fu, Honglei Zhang, Zikai Zhang +5
Federated recommendations (FRs) have emerged as an on-device privacy-preserving paradigm, attracting considerable attention driven by rising demands for data security. Existing FRs…
Evaluating Image Editing with LLMs: A Comprehensive Benchmark and Intermediate-Layer Probing Approach
Shiqi Gao, Zitong Xu, Kang Fu +3
Evaluating text-guided image editing (TIE) methods remains a challenging problem, as reliable assessment should simultaneously consider perceptual quality, alignment with textual i…
MDiffFR: Modality-Guided Diffusion Generation for Cold-start Items in Federated Recommendation
Kang Fu, Honglei Zhang, Xuechao Zou +1
Federated recommendations (FRs) provide personalized services while preserving user privacy by keeping user data on local clients, which has attracted significant attention in rece…
Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model
Kang Fu, Huiyu Duan, Zicheng Zhang +4
Recent advancements in text-to-image (T2I) generation have spurred the development of text-to-3D asset (T23DA) generation, leveraging pretrained 2D text-to-image diffusion models f…
Two-Sample Test for Stochastic Block Models via Maximum Entry-wise Deviation
Kang Fu, Jianwei Hu, Seydou Keita +1
The stochastic block model is a popular tool for detecting community structures in network data. Detecting the difference between two community structures is an important issue for…
Enhancing Image Quality Assessment Ability of LMMs via Retrieval-Augmented Generation
Kang Fu, Huiyu Duan, Zicheng Zhang +5
Large Multimodal Models (LMMs) have recently shown remarkable promise in low-level visual perception tasks, particularly in Image Quality Assessment (IQA), demonstrating strong zer…
CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos
Wei Sun, Linhan Cao, Kang Fu +5
Video compression is a standard procedure applied to all videos to minimize storage and transmission demands while preserving visual quality as much as possible. Therefore, evaluat…
ICME 2025 Generalizable HDR and SDR Video Quality Measurement Grand Challenge
Yixu Chen, Bowen Chen, Hai Wei +16
This paper reports IEEE International Conference on Multimedia \& Expo (ICME) 2025 Grand Challenge on Generalizable HDR and SDR Video Quality Measurement. With the rapid developmen…
Hypothesis testing for general network models
Kang Fu, Jianwei Hu, Seydou Keita
The network data has attracted considerable attention in modern statistics. In research on complex network data, one key issue is finding its underlying connection structure given…
AttentionLut: Attention Fusion-based Canonical Polyadic LUT for Real-time Image Enhancement
Kang Fu, Yicong Peng, Zicheng Zhang +4
Recently, many algorithms have employed image-adaptive lookup tables (LUTs) to achieve real-time image enhancement. Nonetheless, a prevailing trend among existing methods has been…
Quality-guided Skin Tone Enhancement for Portrait Photography
Shiqi Gao, Huiyu Duan, Xinyue Li +7
In recent years, learning-based color and tone enhancement methods for photos have become increasingly popular. However, most learning-based image enhancement methods just learn a…
RAWIW: RAW Image Watermarking Robust to ISP Pipeline
Kang Fu, Xiaohong Liu, Jun Jia +4
Invisible image watermarking is essential for image copyright protection. Compared to RGB images, RAW format images use a higher dynamic range to capture the radiometric characteri…
LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)
Wei Luo, Yiting Lu, Xin Li +32
This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings. The…
Fourth-order compact finite difference schemes for solving biharmonic equations with Dirichlet boundary conditions
Kejia Pan, Jin Li, Zhilin Li +1
In this study, we propose a genuine fourth-order compact finite difference scheme for solving biharmonic equations with Dirichlet boundary conditions in both two and three dimensio…
Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment
Shiqi Gao, Kang Fu, Zitong Xu +4
Current no-reference image quality assessment (NR-IQA) models for enhanced images often struggle to generalize, as they tend to overfit to the distinct patterns of specific enhance…
LMME3DHF: Benchmarking and Evaluating Multimodal 3D Human Face Generation with LMMs
Woo Yi Yang, Jiarui Wang, Sijing Wu +6
The rapid advancement in generative artificial intelligence have enabled the creation of 3D human faces (HFs) for applications including media production, virtual reality, security…
Hypothesis testing for homogenous of nodes in -models
Kang Fu, Jianwei Hu, Meng Sun
The -model has been extensively utilized to model degree heterogeneity in networks, wherein each node is assigned a unique parameter. In this article, we consider the hypothesi…
Variance-reduced sampling importance resampling
Yao Xiao, Kang Fu, Kun Li
The sampling importance resampling method is widely utilized in various fields, such as numerical integration and statistical simulation. In this paper, two modified methods are pr…
Two-Sample Test for Stochastic Block Models via the Largest Singular Value
Kang Fu, Jianwei Hu, Seydou Keita +1
The stochastic block model is widely used for detecting community structures in network data. However, the research interest of much literature focuses on the study of one sample o…