Shan Tan

Longitudinal Trajectories and Cumulative Burden of Remnant Cholesterol Inflammatory Index and Mortality Risk

Yebin Lan, Yehui Lan, Shuaiqing Chen, Shan Tan et autres

BACKGROUND: Remnant cholesterol (RC) and chronic inflammation are key drivers of residual cardiovascular risk; however, the impact of their joint long-term dynamic patterns on subsequent prognosis remains unclear. This study aimed to systematically evaluate the associations of the remnant cholesterol-inflammation index (RCII) …

cn (code pays fourni par la source)

Benchmarking large multimodal models for structured illumination microscopy quality assessment

F M Li, Shan Tan

Structured illumination microscopy (SIM) operates under diverse experimental conditions, and in the absence of ground-truth (GT) images it is difficult to objectively compare reconstructions produced by different algorithms. Using a dataset with paired high-quality reference reconstructions, we conduct systematic experiments on several …

cn (code pays fourni par la source)

Physics-guided learning of inverse reconstruction for structured illumination microscopy

Jiahao Liu, Shan Tan

Structured illumination microscopy (SIM) reconstruction is a challenging inverse image problem that aims to reconstruct super-resolution images from noisy raw structured-illumination measurements. Due to its highly ill-posed nature, SIM reconstruction is sensitive to noise and optical errors, and conventional frequency-domain reconstruction methods …

cn (code pays fourni par la source)

Image Restoration Learning via Noisy Supervision in Fourier Domain

Haosen Liu, Jiahao Liu, Shan Tan, Edmund Y. Lam

Noisy supervision refers to supervising network learning with targets corrupted by noise, encompassing both weakly supervised learning with noisy targets and fully unsupervised denoising using unpaired noisy images. It alleviates the data collection burden and enhances the practical applicability of deep learning …

hk, cn (code pays fourni par la source)

Score-SIM: Score priors with unpaired learning for flexible structured illumination microscopy image reconstruction

Fangzheng Li, Jiahao Liu, Jun Cheng, Zexin Zhang et autres

Bio-friendly and high-precision super-resolution imaging through self-supervised reconstruction structured illumination microscopy

Jiahao Liu, Xue yan Dong, Huaide Lu, Wei Liu et autres

cn, us, hk (code pays fourni par la source)

In-sensor image memorization, low-level processing, and high-level computing by using above-bandgap photovoltages

Kun Liu, Shan Tan, Zhen Hong Fan, Haipeng Lin et autres

In-sensor computing holds great promise for ultrafast and energy-efficient machine vision. However, the development of a versatile in-sensor computing system that can integrate image memorization, low-level processing, and high-level computing functions remains a challenge, primarily due to the scarcity of photosensors that …

cn (code pays fourni par la source)

HA-SAM: Hierarchically Adapting SAM for Nerve Segmentation in Ultrasound Images

Zihao Peng, Susu Kang, Xuping Huang, Gengyu He et autres

cn (code pays fourni par la source)

Cross Attention Swin Transformer for Multi-Modal Head and Neck Cancer Segmentation in Data Limited Regimes

Shan Tan, Jingting Jiang, Sharif Elguindi, N.Y. Lee et autres

Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition

Yifan Lan, Xin Cai, Jun Ting Cheng, Shan Tan

Deep neural networks (DNNs) have achieved significant success in various applications with large-scale and balanced data. However, data in real-world visual recognition are usually long-tailed, bringing challenges to efficient training and deployment of DNNs. Information bottleneck (IB) is an elegant approach for …

The Tenth NTIRE 2025 Image Denoising Challenge Report

Lei Sun, Hang Guo, Bin Ren, Luc Van Gool et autres

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge ($\sigma=50$), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising performance, quantitatively evaluated using PSNR, without constraints on …

bg, it, gr (code pays fourni par la source)

CSR-YOLOv11: Detection Algorithms for Diseases of Soybeans, Tomatoes and Strawberries

Shan Tan, Xiaopeng Yi, Lixia Huang, J. F. Wu et autres

To address the challenges of low accuracy, susceptibility to background interference, and difficulty in detecting target diseases in existing algorithms for strawberry, tomato, and soybean disease detection in agricultural settings, this study proposes an improved disease detection model, CSR-YOLOv11, based on YOLOv11. …

cn (code pays fourni par la source)