arXiv subjects

Limei Liu

Publications and source records attributed to Limei Liu.

2 recordsLinked to original sources

arXiv2024

NTIRE 2024 Quality Assessment of AI-Generated Content Challenge

This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC.

cs.CV↗

arXiv2022

Highly scalable, wearable surface-enhanced Raman spectroscopy

The last two decades have witnessed a dramatic growth of wearable sensor technology, mainly represented by flexible, stretchable, on-skin electronic sensors that provide rich information of the wearer's health conditions and surroundings. A recent breakthrough in the field is the development of wearable chemical sensors based on surface-enhanced Raman spectroscopy (SERS) that can detect molecular fingerprints universally, sensitively, and noninvasively. However, while their sensing properties are excellent, these sensors are not scalable for widespread use beyond small-scale human health monitoring due to their cumbersome fabrication process and limited multifunctional sensing capabilities. Here we demonstrate a highly scalable, wearable SERS sensor based on an easy-to-fabricate, low-cost, ultrathin, flexible, stretchable, adhesive, and bio-integratable gold nanomesh. It can be fabricated in any shape and worn on virtually any surface for label-free, large-scale, in-situ sensing of diverse analytes from low to high concentrations (10 nM - 1 mM). To show the practical utility of the wearable SERS sensor, we test the sensor for the detection of sweat biomarkers, drugs of abuse, and microplastics. This wearable SERS sensor represents a significant step toward the generalizability and practicality of wearable sensing technology.

physics.optics↗