A5100419137- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Remote-Sensing Image Classification
- Infrared Target Detection Methodologies
- Video Surveillance and Tracking Methods
- Advanced Image Fusion Techniques
- Remote Sensing and Land Use
- Robotics and Sensor-Based Localization
- Advanced Measurement and Detection Methods
- Advanced SAR Imaging Techniques
- Image Enhancement Techniques
- Image Retrieval and Classification Techniques
- 3D Shape Modeling and Analysis
- Automated Road and Building Extraction
- Remote Sensing and LiDAR Applications
- Multimodal Machine Learning Applications
- Generative Adversarial Networks and Image Synthesis
- Domain Adaptation and Few-Shot Learning
- Higher Education and Teaching Methods
- Advanced Vision and Imaging
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Web Data Mining and Analysis
- Insect-Plant Interactions and Control
- 3D Surveying and Cultural Heritage
- Image Processing and 3D Reconstruction
Huazhong University of Science and Technology
2015-2025
Institute of Vegetables and Flowers
2022-2025
Chinese Academy of Agricultural Sciences
2021-2025
Hua Hong Semiconductor (China)
2024
Southwest Petroleum University
2022-2024
PLA Information Engineering University
2024
Xi'an Jiaotong University
2020-2023
Mudanjiang Normal University
2023
Nanjing University of Aeronautics and Astronautics
2023
Beijing University of Posts and Telecommunications
2022
Abstract BACKGROUND The whitefly Bemisia tabaci is a notorious agricultural pest known for its ability to cause significant crop damage through direct feeding and virus transmission. Its remarkable adaptability reproductive capacity are linked acquire integrate horizontally transferred genes (HTGs) into genome. These HTGs increase the physiological metabolic capacities of this pest, including cholesterol synthesis, which critical survival success. Among these genes, we identified...
The entorhinal cortex (EC) is one of the most vulnerable brain regions that attacked during early stage Alzheimer's disease (AD). Here, we report synaptic terminals pyramidal neurons in EC layer II (ECIIPN) directly innervate CA1 parvalbumin (PV) (CA1PV) and are selectively degenerated AD mice, which exhibit amyloid-β plaques similar to those observed patients. A loss ECIIPN–CA1PV synapses disables excitatory inhibitory balance circuit impairs spatial learning memory. Optogenetic activation...
Object detection that focuses on locating objects of interest and categorizing them has long played a critical role in the development remote sensing imagery. Following significant improvements Earth observation technologies, high-resolution (HRRS) images show additional detailed information more complex patterns. Some applications, such as urban monitoring, military reconnaissance, national security, have urgent needs terms identifying small-scale (small) weak-feature-response (weak)...
Abstract The recent discovery that various insects have acquired functional genes through horizontal gene transfer (HGT) has prompted numerous studies into this puzzling and fascinating phenomenon. So far, horizontally transferred are found to be functionally conserved largely retained their ancestral functions. It evidently not yet been considered may evolve can contribute divergence between species. Here, it is first showed the genomes of two widespread agriculturally important whiteflies...
Military-civilian attribute recognition of ships in synthetic aperture radar (SAR) imagery plays an important role marine surveillance. However, high-quality labeled data are hard to obtain for SAR ships, which hinder the development deep learning models. Considering that models directly transferred from optical images cannot achieve satisfactory performance applications due great discrepancy different modalities, we propose a two-stage transfer method by combining data-level and...
Self-supervised learning establishes a new paradigm of representations with much fewer or even no label annotations. Recently there has been remarkable progress on large-scale contrastive models which require substantial computing resources, yet such are not practically optimal for small-scale tasks. To fill the gap, we aim to study wearable-based activity recognition task. Specifically, conduct an in-depth from both algorithmic-level and task-level perspectives. For analysis, decompose into...
Aircraft detection in synthetic aperture radar (SAR) images is still a challenging research task because of the insufficient public data, difficulty multiscale target detection, and complexity background interference. In this article, we construct SAR aircraft dataset (SADD) with complex interference objects to facilitate detection. Then, propose scale expansion feature enhancement pyramid network as SADD baseline. It uses four-scale fusion method combine shallow position information deep...
Synaptic spine loss is one of the major preceding consequences stroke damages, but its underlying molecular mechanisms remain unknown. Here, we report that a direct interaction DAPK1 with Tau causes and subsequently neuronal death in mouse model stroke. We found phosphorylates protein at Ser262 (pS262) cortical neurons mice. Either genetic deletion kinase domain (KD) mice (DAPK1-KD−/−) or blocking DAPK1-Tau by systematic application membrane permeable peptide protects damages improves...
In this paper, an improved ant lion optimization (IALO) algorithm for parameter identification of hydraulic turbine governing system (HTGS) is proposed. the proposed algorithm, search space explored by first, and then domain searched particle swarm (PSO) in each iteration cycle. A chaotic mutation operation namely Logistics map introduced elite to break out local optimum. operation, a serial-parallel combined method developed increase diversity mutant population. When IALO applied HTGS,...
Sea-land segmentation is a key step in inshore ship detection and coast monitoring. Among the state-of-art approaches, semantic networks show great potential on this task, but there still room for improvement. In paper, we propose method based UNet sea-land segmentation. We replace its contraction part with ResNet which specializes handling complicated scenes, construct new network structure Res-UNet. After preliminary results are obtained, fully connected Conditional Random Field (CRF)...
Remote sensing image scene classification plays an important role in remote interpretation. Deep learning brings prosperity to the research this field, and numerous deep models are proposed order improve performance of classification. However, images different scenes vary a lot, showing similar or diverse textures simple complex contents. Using fixed convolutional neural network framework classify is performance-limited not practice-flexible. To address issue, article, we propose SEMSDNet...
Years of education are inversely related to the prevalence major depressive disorder (MDD), but relationship between clinical features MDD and educational status is poorly understood. We investigated this in 1970 Chinese women with recurrent identified a setting.Clinical demographic were obtained from Han DSM-IV depression 30 60 years age across China. Analysis linear, logistic multiple regression models used determine association level MDD.Subjects more likely have MDD, an odds ratio 1.14...
Two rare 7,8-seco-lignans (1, 2), three new lignan glycosides (3, 4a, 4b), and 10 known lignans (5–14) were isolated from the fruit of Schisandra glaucescens Diels. The absolute configurations 1 2 determined by comparing their experimental calculated electronic circular dichroism spectra. molecular structures compounds including configurations, using various spectroscopic methods hydrolysis reactions. antioxidant activities tested 2,2-diphenyl-1-picrylhydrazyl ferric reducing power assays....
Semantic segmentation is a fundamental task in remote sensing image interpretation, which aims to assign semantic label for every pixel the given image. Accurate still challenging due complex distributions of various ground objects. With development deep learning, series networks represented by fully convolutional network (FCN) has made remarkable progress on this problem, but accuracy far from expectations. This paper focuses importance class-specific features different land cover objects,...
Vehicle detection in infrared aerial images is vital for both military and civilian applications, as imaging remains effective under low-light conditions various adverse weather scenarios. However, the longer wavelengths of long-wave infrared, compared to visible light, make diffraction more noticeable, leading low-frequency degradation vehicle information. Thermal radiation from environment optical system leads higher noise images. Additionally, atmospheric transport models can degrade...