Yufeng Wu

Engagement–Quality Mismatch in Robot-Assisted Total Knee Arthroplasty Short Videos on TikTok and Bilibili

K. L. Li, Wenfeng Su, Yifan Yang, H. T. Dai et autres

cn (code pays fourni par la source)

Robust Deep Video Watermarking Against Camera Recording Attacks via Temporal Distortion Modeling and Synchronization

Zhengdong Wang, Xin Liao, Yufeng Wu

cn (code pays fourni par la source)

AI-Assisted Knee Infrared Imaging Based Acupuncture for Treating Knee Osteoarthritis: A Randomized Controlled Study Protocol

Fengxi Qiu, Xianfei Xie, Weihong Zheng, Yufeng Wu et autres

Background: The variability in acupoint selection limits the standardization of acupuncture for knee osteoarthritis (KOA) and is one of the important factors affecting treatment efficacy. Recent advancements in artificial intelligence (AI) and infrared imaging provide opportunities to enhance the precision and standardization …

cn (code pays fourni par la source)

Interpretable machine learning model for low bone density screening in older adults using demographic and anthropometric data: findings from 2005 to 2020 NHANES

Weiyan Huang, Jiewei Peng, Yufeng Wu, Dawei Gao

BACKGROUND: Rising osteoporosis from low bone mineral density (BMD) due to an aging population presents a major health challenge. Timely risk identification is vital for prevention. Traditional Dual-energy X-ray absorptiometry (DXA) diagnostics are expensive and inaccessible to all. This study aimed to …

cn (code pays fourni par la source)

Sim-to-Real: An Unsupervised Noise Layer for Screen-Camera Watermarking Robustness

Yufeng Wu, Xin Liao, Baowei Wang, Han Fang et autres

Unauthorized screen capturing and dissemination pose severe security threats such as data leakage and information theft. Several studies propose robust watermarking methods to track the copyright of Screen-Camera (SC) images, facilitating post-hoc certification against infringement. These techniques typically employ heuristic mathematical modeling …

FasterCReW: Performance or Efficiency? A Lightweight Conditional Residual DNN-Based Watermarking Based on FasterNet

Baowei Wang, Yufeng Wu, Qi Ming Cui

Deep neural networks (DNNs) based watermarking algorithms have made significant strides in recent years. However, existing methods either demand substantial resources for image feature extraction during watermark embedding, sacrificing efficiency, or completely neglect image texture information, resulting in suboptimal performance. Moreover, current …

cn (code pays fourni par la source)

MCFN: Multi-scale Crossover Feed-forward Network for high performance watermarking

Yufeng Wu, Baowei Wang, Guiling Wang, Xin Liao

cn, us (code pays fourni par la source)

Embedding Guide: Improving Watermarking Robustness and Imperceptibility based on Attention and Edge Information

Baowei Wang, Xinyu Lv, Yufeng Wu, Changyu Dai et autres

In the past few years, there has been an increasing focus on deep learning-based watermarking techniques. Many existing methods do not impose constraints to guide the embedding of watermarking, which leads to random embedding positions and makes watermarks vulnerable to detection and …

cn (code pays fourni par la source)

Large Capacity Image Watermarking Model using SWT and Laplacian Pyramid

Baowei Wang, Fan Yang, Yufeng Wu, Changyu Dai et autres

Image watermarking algorithms have developed rapidly in recent years. Most of the Deep Neural Network(DNN)-based image watermarking algorithms embed only 30 bits or 64 bits messages in 128 × 128 images, while few algorithms embed large capacity messages. This is mainly because …

cn (code pays fourni par la source)

Learnable Color Image Zero-Watermarking Based on Feature Comparison

Baowei Wang, Changyu Dai, Yufeng Wu

cn (code pays fourni par la source)

QAIC: Quality-assured image crowdsourcing via blockchain and deep learning

Baowei Wang, Yi Yuan, Bin Li, Changyu Dai et autres

Recently, image crowdsourcing, a new trading mode, has been proposed to bridge the gap between the excess photos generated by intelligent devices and the great demand for images. However, traditional crowdsourcing methods often rely on centralized platforms, which risk data leakage and …

cn (code pays fourni par la source)

Enhancing Robustness and Imperceptibility of Blind Watermarking with Improved Message Processor

Yufeng Wu, Baowei Wang, Changyu Dai, Yi Yuan et autres

The current state-of-the-art(SOTA) blind watermark embedding method MBRS based on deep learning is less robust to Crop, and additional diffusion layers need to be added for optimization. However, the diffusion layer will make the model less robust to noise other than Crop. …

cn (code pays fourni par la source)