A5062882793- Photoacoustic and Ultrasonic Imaging
- Sparse and Compressive Sensing Techniques
- Image and Signal Denoising Methods
- Environmental Quality and Pollution
- Image Processing Techniques and Applications
- Optical Imaging and Spectroscopy Techniques
- Water Quality Monitoring and Analysis
- Neural Networks and Applications
- Video Surveillance and Tracking Methods
- Pluripotent Stem Cells Research
- Evaluation Methods in Various Fields
- Plant Toxicity and Pharmacological Properties
- Sesquiterpenes and Asteraceae Studies
- Remote-Sensing Image Classification
- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Fire Detection and Safety Systems
- Renal and related cancers
- CRISPR and Genetic Engineering
- Cognitive Computing and Networks
- IoT-based Smart Home Systems
- Homicide, Infanticide, and Child Abuse
- Mercury impact and mitigation studies
- Higher Education and Teaching Methods
- Spectroscopy Techniques in Biomedical and Chemical Research
Xidian University
2023-2025
Nanyang Technological University
2024-2025
82th Hospital of Pla
2023
China University of Petroleum, Beijing
2022
China Medical University
2022
Shantou Central Hospital
2019
Fujian Fisheries Research Institute
2012-2016
Hunan Police Academy
2005-2010
To acquire a snapshot spectral image, coded aperture imaging (CASSI) is proposed. A core problem of the CASSI system to recover reliable and fine underlying 3D cube from 2D measurement. By alternately solving data subproblem prior subproblem, deep unfolding methods achieve good performance. However, in used sensing matrix ill-suited for real degradation process due device errors caused by phase aberration, distortion; it important design suitable model jointly exploit both spatial priors. In...
In hyperspectral image (HSI) reconstruction tasks, due to the lack of ground truth in real imaging processes, models are usually trained and validated on simulation datasets then tested measurements captured by HSI systems. However, gap between process process, best model dataset may fail measurements. To obtain for real-world task, it is crucial design a suitable no-reference quality assessment metric reflect performance different models. this paper, we propose novel via ranking feature...
Reconstructing hyperspectral images (HSIs) from RGB is an effective technique to overcome the high cost of spectrometers. Recently, Transformers have shown potential in capturing long-range dependencies for spectral reconstruction. However, few Transformer models attempt simultaneously capture both spatial and correlations HSIs. Within this study, we introduce integrated spatial–spectral hybrid (SSHFormer) framework designed interplay between features HSIs, with aim incrementally enhancing...
This study assesses the outcomes of NTIRE 2023 Challenge on Non-Homogeneous Dehazing, wherein novel techniques were proposed and evaluated new image dataset called HD-NH-HAZE. The HD-NH-HAZE contains 50 high resolution pairs real-life outdoor images featuring nonhomogeneous hazy corresponding haze-free same scene. haze was simulated using a professional setup that replicated real-world conditions scenarios. competition had 246 participants 17 teams submitted solutions for final testing...
Despite deep learning's progress in semantic communication, traditional fixed-length encoding does not adequately address the variable complexity of content, often leading to loss critical nuances and reduced communication accuracy. Current methods also introduce unnecessary redundancy, compromising transmission efficiency. Addressing these challenges, our work introduces an innovative adaptive rate mechanism that captures intrinsic semantics images fine-tunes coding based on interconnection...
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development integration of advanced image sensors with novel algorithms in camera systems. However, scarcity high-quality data research rare opportunity in-depth exchange views from industry academia constrain intelligent (MIPI). Building achievements previous MIPI Workshops held at ECCV 2022 CVPR 2023, we introduce our third challenge including three tracks focusing algorithms. In...
The respiration and excretion rates of Meretrix meretrix at different salinities were studied 20°C in laboratory December 2008. 1) It was shown that the effects salinity on oxygen consumption rate(OR) ammonia rate(NR) are extremely significant(p<;0.05), when changes from 8.2 to 28.1. 2) At same time, trend ratio O/N shows first increased then decreased with raise salinity, moreover, O/ N largest is 11.38
Soft sensor is widely used in the industrial process to capture variables that are difficult measure. Multivariate statistical analysis has wildly applied soft sensor. However, most of modeling methods have disadvantages coping with simultaneously contains nonlinear and dynamic characteristics. Considering process's characteristics contained, we proposed an algorithm combines canonical variate (CVA) decision tree (DT), named CVA-DTR method, those In this features related time closely will be...
Using ICP-MS to detect Pb in the multi-phase mediumin artificial reef .The results showed that: of sediment is varied from0.138~0.470mg/Kg,mean0.273±0.106mg/Kg,Thesediment distribution decreased order: lower> middle> upper layer each station.Risk evaluation that potential ecological risk index low sediments; accumulate partial belong moderate pollution levels; enrichment factor light~pollution-free .Pb organisms rang from 0.004-0.519mg / Kg, mean 0.185 ± 0.170 mg Kgin area; BCF value...
In the Coded Aperture Snapshot Spectral Imaging (CASSI) system, deep unfolding networks (DUNs) have demonstrated excellent performance in recovering 3D hyperspectral images (HSIs) from 2D measurements. However, some noticeable gaps exist between imaging model used DUNs and real CASSI process, such as sensing error well photon dark current noise, compromising accuracy of solving data subproblem prior DUNs. To address this issue, we propose a Degradation Estimation Network (DEN) to correct by...
The key water chemistry indexes of Heishijiao mariculture area were measured in autumn from 2007 to 2009. relationship between these and safety aquatic products, red tide, marine environment pollution was preliminary analyzed. Results showed that N serious investigation N:P ratio far greater than 16:1. However, the oligotrophic overall condition.
Human ERF gene is a transcription factor involved in development, trophoblast differentiation, apoptosis, and cancer progress. To further understand the exact roles of these processes, here we report that establishment two knockout human embryonic stem cell (hESC) lines by CRISPR/Cas9 mediated targeting. These exhibited classical hESC morphology normal karyotype, highly expressed pluripotent markers, had differentiation potential vitro. provide good materials to craniosynostosis for studies.