A5077944631- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Advanced Image Processing Techniques
- Catalytic Processes in Materials Science
- Mesoporous Materials and Catalysis
- EEG and Brain-Computer Interfaces
- Zeolite Catalysis and Synthesis
- Layered Double Hydroxides Synthesis and Applications
- Image Processing and 3D Reconstruction
- Wireless Power Transfer Systems
- Advanced Image and Video Retrieval Techniques
- Fluid Dynamics and Heat Transfer
- Topic Modeling
- Advanced Vision and Imaging
- Speech and dialogue systems
- Natural Language Processing Techniques
- Muscle activation and electromyography studies
- Icing and De-icing Technologies
- Neuroscience and Neural Engineering
- Surface Modification and Superhydrophobicity
- Infrared Target Detection Methodologies
- Polymer composites and self-healing
- Thermal Expansion and Ionic Conductivity
- Aerospace Engineering and Applications
- Visual Attention and Saliency Detection
Wuhan University
2024
Hefei University of Technology
2014-2024
Beijing Union University
2024
Henan Polytechnic University
2024
Southeast University
2024
Nanjing Tech University
2016-2022
University of Shanghai for Science and Technology
2021
Nanjing University
2002-2019
Shenyang University
2014
Dalian Polytechnic University
2008
Low-light image enhancement is important for high-quality display and other visual applications. However, it a challenging task as the expected to improve visibility of an while keeping its naturalness. Retinex-based methods have well been recognized representative technique this task, but they still following limitations. First, due less-effective decomposition or strong imaging noise, various artifacts can be brought into enhanced results. Second, although priori information explored...
The visual quality of photographs taken under imperfect lightness conditions can be degenerated by multiple factors, e.g., low lightness, imaging noise, color distortion, and so on. Current low-light image enhancement models focus on the improvement only, or simply deal with all degeneration factors as a whole, therefore leading to sub-optimal results. In this article, we propose decouple model into two sequential stages. first stage focuses improving scene visibility based pixel-wise...
Boron neutron capture therapy (BNCT) is emerging cancer radiotherapy requiring 10 B sensitizer. Although boronophenylalanine (BPA)-BNCT approved clinically in Japan, the low tumour selectivity and retentivity result long-time infusion of high doses. Based on our finding size-controllable mechanochemical synthesis boron-10 carbide nanoparticles ( 4 C NPs), 50 nm size NPs grafted with poly(glycerol), C(50)-PG, found to show superior enhance eradication efficacy at much lower dosage (5 mg [ B]...
The open set domain adaptation problem was rarely studied and its existing solutions are mostly based on learning a joint latent space which may encounter issues when the domains differ significantly from each other. This work is driven by question whether or not it beneficial to operate source images another image as close target possible. We propose address aligning sample at both feature pixel space. Our approach, called Open Set Translation Adaptation Network (Ostan), consists of two...
Superhydrophobic surfaces have been extensively utilized due to their high hydrophobicity and anti-icing properties. Inspired by the shape of a cross flower, research has circular arc curves Bessel design flower structure model. Using 3D modeling software for printing technology prepare biomimetic microstructures in structural design. The microstructure before after spray coating was detected using ultra depth field laser confocal microscopy. Ultra-Ever Dry as low surface energy substance...
Abstract Surface electromyography signal (sEMG) is the bio-electric accompanied by muscle contraction. For master–slave manipulation scenario such as patients with prosthetic hands, their upper limb sEMG signals can be collected and corresponded to patient's gesture intention. Therefore, using a slave manipulator that integrated recognition module, master side could control it make gestures meet needs of daily life. In this paper, carried out based on deep learning, realized. According...
LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain, where different learned additional represent diverse skills. Combining existing LoRAs address new tasks can enhance the reusability of LoRAs, particularly beneficial with limited annotated data. Most prior works on combination primarily rely task-level weights involved LoRA, making examples and tokens share same weights. However, in generative tasks, may necessitate skills manage....
This paper presents a new RF-DC rectifier with high power conversion efficiency (PCE) at 13.56MHz, utilizing novel controlled V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sub> compensation technique. Simulation results show the maximum PCE of single-stage, 3-stage, and 5-stage rectifiers are 65.7%, 56.2%, 50.5% low input -17.64dBm, -8.86dBm, -5.3dBm, respectively.
In this paper, we rethink the low-light image enhancement task and propose a physically explainable generative diffusion model for enhancement, termed as Diff-Retinex. We aim to integrate advantages of physical network. Furthermore, hope supplement even deduce information missing in through Therefore, Diff-Retinex formulates problem into Retinex decomposition conditional generation. decomposition, superiority attention Transformer meticulously design network (TDN) decompose illumination...
The front cover of this issue points to two main results which were achieved in the work by Yadong Xu et al. (article no. 1600474). First all, authors show ability near-field scanning microwave impedance microscope (MIM) map local electrical properties a rapid and nondestructive manner, will be helpful for characterization micro-nano structures or defects bulk crystals. Secondly, well-defined tellurium-rich secondary phase particles (Te-SP) embedded CdZnTe crystals observed first time...