10 papers
Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA
Yu Li, Zhengran Shen, Yachun Mi +2
Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP i…
Watts vs. Bytes: Turning Data Centers into Grid Assets via Storage Compute Co-Optimization
Shaohui Liu, Sungho Shin, Deepjyoti Deka
Data center interconnections increasingly face tighter peak-demand and ramp-rate limits while being expected to support grid operations. Satisfying these requirements calls for coo…
Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs
Tengyun Ma, Jiaqi Yao, Daojing He +4
Large Language Models (LLMs) have emerged as powerful tools for diverse applications. However, their uniform token processing paradigm introduces critical vulnerabilities in instru…
Segmenting and Understanding: Region-aware Semantic Attention for Fine-grained Image Quality Assessment with Large Language Models
Chenyue Song, Chen Hui, Haiqi Zhu +4
No-reference image quality assessment (NR-IQA) aims to simulate the process of perceiving image quality aligned with subjective human perception. However, existing NR-IQA methods e…
UGD-IML: A Unified Generative Diffusion-based Framework for Constrained and Unconstrained Image Manipulation Localization
Yachun Mi, Xingyang He, Shixin Sun +6
In the digital age, advanced image editing tools pose a serious threat to the integrity of visual content, making image forgery detection and localization a key research focus. Mos…
Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation
Yachun Mi, Yu Li, Yanting Li +6
Accurate and efficient Video Quality Assessment (VQA) has long been a key research challenge. Current mainstream VQA methods typically improve performance by pretraining on large-s…
VidText: Towards Comprehensive Evaluation for Video Text Understanding
Zhoufaran Yang, Yan Shu, Jing Wang +8
Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. Howeve…
MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment
Yachun Mi, Yu Li, Weicheng Meng +3
The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem t…
Depth-agnostic Single Image Dehazing
Honglei Xu, Yan Shu, Shaohui Liu
Single image dehazing is a challenging ill-posed problem. Existing datasets for training deep learning-based methods can be generated by hand-crafted or synthetic schemes. However,…
CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelings
Yachun Mi, Yu Li, Yan Shu +3
Video Quality Assessment (VQA) aims to simulate the process of perceiving video quality by the human visual system (HVS). The judgments made by HVS are always influenced by human s…