Yanyan Wei
A5003728286- Image Enhancement Techniques
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Advanced Image Fusion Techniques
- Image and Signal Denoising Methods
- Advanced Optical Sensing Technologies
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Image Processing Techniques and Applications
- Anomaly Detection Techniques and Applications
- Fire Detection and Safety Systems
- Speech and Audio Processing
- Advanced X-ray and CT Imaging
- Speech Recognition and Synthesis
- Computer Graphics and Visualization Techniques
- Advanced Image and Video Retrieval Techniques
- Hand Gesture Recognition Systems
- Human Motion and Animation
- Geochemistry and Geologic Mapping
- Visual Attention and Saliency Detection
- Artificial Immune Systems Applications
- Space Science and Extraterrestrial Life
- Bioactive natural compounds
- Gait Recognition and Analysis
Hefei University of Technology
2019-2025
China Geological Survey
2024
Zhengzhou University
2023
National University of Defense Technology
2022
Beijing HuiLongGuan Hospital
2022
Peking University
2022
University Town of Shenzhen
2021
Harbin Institute of Technology
2021
Institute of Software
2020
Xinjiang Industry Technical College
2016
Single Image Deraining (SID) is a relatively new and still challenging topic in emerging vision applications, most of the recently emerged deraining methods use supervised manner depending on ground-truth (i.e., using paired data). However, practice it rather common to encounter unpaired images real task. In such cases, how remove rain streaks an unsupervised way will be task due lack constraints between hence suffering from low-quality restoration results. this paper, we therefore explore...
This paper reviews the NTIRE 2023 challenge on image denoising (σ = 50) with a focus proposed solutions and results. The aim is to obtain network design capable produce high-quality results best performance measured by PSNR for denoising. Independent additive white Gaussian noise (AWGN) assumed level 50. had 225 registered participants, 16 teams made valid submissions. They gauge state-of-the-art
This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing proposed solutions and results. The task of (SR) is to generate a high-resolution (HR) output from corresponding low-resolution (LR) input by leveraging prior information paired LR-HR images. aim obtain network design/solution capable produce high-quality results with best performance (e.g., PSNR). We want explore how high we can achieve regardless computational cost model size FLOPs) data. track was measure...
This work reviews the results of NTIRE 2023 Challenge on Image Shadow Removal. The described set solutions were proposed for a novel dataset, which captures wide range object-light interactions. It consists 1200 roughly pixel aligned pairs real shadow free and affected images, captured in controlled environment. data was white-box setup, using professional equipment lights acquisition sensors. challenge had number 144 participants registered, out 19 teams compared final ranking. extend...
This paper summarizes the 2nd NTIRE challenge on stereo image super-resolution (SR) with a focus new solutions and results. The task of is to super-resolve low-resolution pair high-resolution one magnification factor ×4. Compared single SR, major this lies in how exploit additional information another viewpoint maintain consistency has 3 tracks, including track distortion (e.g., PSNR) bicubic degradation, perceptual quality LPIPS) as well real degradations. In total, 175, 93, 103...
Video anomaly detection has always been a hot topic and attracting an increasing amount of attention. Much the existing methods on video depend processing entire rather than considering only significant context. This paper proposes novel method named COVAD, which mainly focuses region interest in instead video. Our proposed COVAD is based auto-encoded convolutional neural network coordinated attention mechanism, can effectively capture meaningful objects dependencies between different...
Single image deraining task is still a very challenging due to its ill-posed nature in reality. Recently, researchers have tried fix this issue by training the CNN-based end-to-end models, but they cannot extract negative rain streaks from rainy images precisely, which usually leads an over de-rained or under result. To handle issue, paper proposes new coarse-to-fine single framework termed Multi-stream Hybrid Deraining Network (shortly, MH-DerainNet). obtain during process more accurately,...
Although supervised single image deraining (SID) have obtained impressive results, they still cannot obtain satisfactory results on real images for the weak generalization of rain removal capacity. In this paper, we mainly discuss semi-supervised SID and propose a new GAN-based network called Semi-DerainGAN, which can use both synthetic data in uniform based two unsupervised processes. For task, streak learner termed SSRML sharing same parameters processes is derived, makes contribute more...
Data-driven single image deraining (SID) models have achieved greater progress by simulations, but there is still a large gap between current performance and practical high-level applications, since semantic information usually neglected in studies. Although few studies jointly considered tasks (e.g., segmentation) to enable the model learn more information, are two obvious shortcomings. First, they require segmentation labels for training, limiting their operations on other datasets without...
Repetitive Action Counting (RAC) is a critical and challenging task in video analysis, aiming to count the number of repeated actions videos accurately. Existing methods typically generate Temporal Self-similarity Matrix (TSM) as an intermediate representation predict repetitive actions. While this simplifies process, it often overlooks variable lengths between action cycles phenomenon motion interruptions. The period inconsistency problem caused by change interruption resulting from pause...
Synchronous Rain streaks and Raindrops Removal (SR^3) is a hard challenging task, since rain raindrops are two wildly divergent real-world phenomena with different optical properties mathematical distributions. As such, most existing data-driven deep Singe Image Deraining (SID) methods only focus on one of them. Although there few SR^3 methods, they still suffer from blur textures unknown noise in reality due to weak robustness generalization ability. In this paper, we will propose new...
Inflammation and oxidative stress are the major leading hypothetical causes of schizophrenia. Unconjugated bilirubin (UCB) is an efficient endogenous plasma antioxidant. closely linked to stress. The relationship between UCB inflammatory markers should be paid close attention in schizophrenia acute stage. In this paper, combined were evaluated for their capability predicting stage find easy effective indicator identify schizophrenia.A total 6,937 patients 6,404 healthy controls (HCs)...
Stereo image dehazing aims to restore haze-free images by leveraging the complementary information contained in binocular images. Current methods primarily focus on designing image-level modules and pipelines utilize between left right-view However, these cross-view interactions overlook regional differences haze concentration stereo disparity maps. Consequently, we propose a Progressive Image Dehazing Network via Cross-view Region Interaction, termed PSIDNet, which fully considers internal...
Removing the rain streaks from single image is still a challenging task, since shapes and directions of in synthetic datasets are very different real images. Although supervised deep deraining networks have obtained impressive results on datasets, they cannot obtain satisfactory images due to weak generalization removal capacity, i.e., pre-trained models usually handle new that may lead over-derained/under-derained results. In this paper, we propose semi-supervised GAN-based network termed...
We introduce a new strategy towards the cyclohexene oxidation reaction, which is driven by molecular oxygen with cobalt(<sc>ii</sc>)/amine acid complex as catalyst without any solvents.
Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent the increasing demand for computational photography imaging on mobile platforms. However, lack of high-quality data research rare opportunity in-depth exchange views from industry academia constrain development intelligent (MIPI). With success 1st MIPI Workshop@ECCV 2022, we introduce second challenge including four tracks focusing algorithms. In this paper, summarize review Nighttime...
This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task this challenge is to super-resolve an input image with magnification factor x4 based pairs low corresponding high-resolution images. primary objective develop networks that optimize various aspects such as runtime, parameters, FLOPs, while still maintaining peak signal-to-noise ratio (PSNR) approximately 26.90 dB...