A5080535168- Advanced Image Fusion Techniques
- Video Surveillance and Tracking Methods
- Crystallization and Solubility Studies
- X-ray Diffraction in Crystallography
- Human Pose and Action Recognition
- Gait Recognition and Analysis
- Remote-Sensing Image Classification
- Polyoxometalates: Synthesis and Applications
- Image Enhancement Techniques
- Photoacoustic and Ultrasonic Imaging
- Image and Signal Denoising Methods
- Anesthesia and Neurotoxicity Research
- Metal-Organic Frameworks: Synthesis and Applications
- Advanced Image Processing Techniques
- Infrared Target Detection Methodologies
- Image Processing Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Face recognition and analysis
- Image Retrieval and Classification Techniques
- MicroRNA in disease regulation
- Anesthesia and Sedative Agents
- Medical Image Segmentation Techniques
- Video Analysis and Summarization
- Multimodal Machine Learning Applications
- Prenatal Screening and Diagnostics
Kunming University of Science and Technology
2016-2025
Linyi People's Hospital
2016-2025
China Academy of Engineering Physics
2022-2024
Sichuan University
2014-2024
West China Second University Hospital of Sichuan University
2004-2024
Nanjing University of Science and Technology
2010-2024
Shandong First Medical University
2011-2024
Yingkou Institute of Technology
2023-2024
Southern Medical University Shenzhen Hospital
2024
Wuhan University
2024
Introduction Diabetic nephropathy (DN), distinguished by detrimental changes in the renal glomeruli, is regarded as leading cause of death from end-stage disease among diabetics. Cellular senescence plays a paramount role, profoundly affecting onset and progression chronic kidney (CKD) acute injuries. This study was designed to delve deeply into pathological mechanisms between glomerulus-associated DN cellular senescence. Methods Glomerulus-associated datasets senescence-related genes were...
Infrared and visible image fusion has gained ever-increasing attention in recent years due to its great significance a variety of vision-based applications. However, existing methods suffer from some limitations terms the spatial resolutions both input source images output fused image, which prevents their practical usage extent. In this paper, we propose meta learning-based deep framework for infrared images. Unlike most methods, proposed can accept different generate arbitrary resolution...
Domain invariance and discrimination of learned features as two crucial factors affect the performance unsupervised domain adaptation (UDA) person re-identification (Re-ID). Person attributes (such "backpack", "boots", "handbag", etc) remaining unchanged across multiple domains have been used mid-level visual-semantic information in UDA Re-ID. As main challenges, both misalignment attribute-related regions images shift between source target learning domain-invariant (DIF). To address above...
Due to the importance of practical applications, unsupervised domain adaptation (UDA) person re-identification (re-ID) has attracted increasing attention. However, most existing methods often lack multi-view information reasoning and ignore discrepancy pedestrian images with same identity, which constrain further improvement recognition performance. So, this paper proposes a triple adversarial learning imaginative network (TAL-MIRN) for UDA re-ID, consists module (IRM) (TALM). IRM makes...
How to effectively preserve the fine-scale details of image when noises are suppressed is one great challenges faced by scholars in field noisy fusion. The traditional fusion method tends smooth structures excessively. To overcome oversmoothing issue, we develop a novel that can perform fusion, denoising, and preservation fine simultaneously. In this method, modeled as superposition coarse details. At same time, brand new strategy developed decompose input into components for further...
Thanks for the cross-modal retrieval techniques, visible-infrared (RGB-IR) person re-identification (Re-ID) is achieved by projecting them into a common space, allowing Re-ID in 24-hour surveillance systems. However, with respect to probe-to- gallery, almost all existing RGB-IR based methods focus on image-to-image matching, while video-to-video matching which contains much richer spatial- and temporal-information remains under-explored. In this paper, we primarily study video-based per-son...
A series of DyxEr(1–x)-polyoxometalates (POMs) were successfully synthesized and characterized well by various physicochemical analysis. The structurally isolated compounds exhibit three characteristic emissions at 480 nm (blue, 4F9/2 → 6H15/2 transition), 573 (yellow, 6H13/2 663 (red, 6H11/2 transition) whose luminescent color coordinates appear in the near-white area CIE 1931 chromaticity diagram. Time-resolved emission spectroscopy was used DyxEr(1–x)-POM to further authenticate energy...
Due to the domain shift between source dataset and target dataset, most of existing person re-identification (PRID) algorithms trained by a supervised learning framework often fail be well generalized another domain. To address this challenge, we propose self-supervised algorithm based on attribute-identity embedding, which can incrementally optimize model selecting unlabeled samples from Thus gap is bridged. Specifically, first develop an joint prediction dictionary for simultaneously...
Abstract Cell death after spinal cord ischemia/reperfusion (I/R) can occur through necrosis, apoptosis, and autophagy, resulting in changes to the immune environment. However, molecular mechanism of this regulation is not clear. Accumulating evidence indicates that microRNAs (miRs) play a crucial role pathogenesis I/R injury. Here, we hypothesized miR‐22‐3p may be involved injury by interacting with interferon regulatory factor (IRF) 5. Rat models were established 12‐min occlusion aortic...
Single image super-resolution (SISR) using deep convolutional neural networks (CNNs) achieves the state-of-the-art performance. Most existing SISR models mainly focus on pursuing high peak signal-to-noise ratio (PSNR) and neglect textures details. As a result, recovered images are often perceptually unpleasant. To address this issue, in paper, we propose texture detail-preserving network (TDPN), which focuses not only local region feature recovery but also preserving Specifically,...