A5100757037- Face and Expression Recognition
- Advanced Image and Video Retrieval Techniques
- Tuberculosis Research and Epidemiology
- Advanced Neural Network Applications
- Biochemical and Molecular Research
- Antibiotic Resistance in Bacteria
- Image and Video Stabilization
- Infrared Target Detection Methodologies
- Visual Attention and Saliency Detection
- Image Retrieval and Classification Techniques
- RNA modifications and cancer
- Hand Gesture Recognition Systems
- Robotic Path Planning Algorithms
- Sparse and Compressive Sensing Techniques
- Advanced Data Compression Techniques
- Digital Imaging for Blood Diseases
- Aerospace Engineering and Energy Systems
- Glaucoma and retinal disorders
- DNA Repair Mechanisms
- Spectral Theory in Mathematical Physics
- Machine Learning and Data Classification
- Biomimetic flight and propulsion mechanisms
- Topic Modeling
- Industrial Vision Systems and Defect Detection
- Advanced Computing and Algorithms
Hangzhou Normal University
2025
Binzhou Technician College
2024
Xiamen University
2024
Institute of Automation
2017-2024
University of Chinese Academy of Sciences
2024
Shenzhen University
2023
Chinese Academy of Sciences
2013-2023
Guangzhou Institutes of Biomedicine and Health
2023
China Aerospace Science and Technology Corporation
2021
China Academy of Space Technology
2016-2019
Spiking Neural Networks (SNNs) are biologically inspired models that process visual inputs over multiple time steps. However, they often struggle with limited feature discrimination along the temporal dimension due to inherent spatiotemporal invariance. This limitation arises from redundant activation of certain regions and shared supervision for steps, constraining network’s ability adapt learn diverse features. To address this challenge, we propose a novel Temporal-Self-Erasing (TSE)...
Wave glider with webbed wings (WGWW) is an innovative unmanned surface vehicle, powered by wave energy and solar energy. Its supply conundrum has been thoroughly resolved “exploiting local resources” can achieve long-term large-scale ocean data acquisition for its outstanding endurance. Flexible (FWWs) are crucial constituents of WGWW, transforming into driving force through fluid–structure interaction (FSI) under their hyper-elastic deformation. It great significance to analyze the...
Hyperuricemia has seen a continuous increase in incidence and trend towards younger patients recent years, posing serious threat to human health highlighting the urgency of using technological means for disease risk prediction. Existing prediction models hyperuricemia typically include two major categories indicators: routine blood tests biochemical tests. The potential alone not yet been explored. Therefore, this paper proposes model that integrates Particle Swarm Optimization (PSO) with...
Abstract Fatty acid degradation protein D32 (FadD32), an enzyme required for mycolic biosynthesis and essential mycobacterial growth, has recently been identified as a valid promising target anti-tuberculosis drug development. Here we report the crystal structures of Mycobacterium smegmatis FadD32 in apo ATP-bound states at 2.4 Å 2.25 resolution, respectively. consists two globular domains connected by flexible linker. ATP binds cleft interface between N- C-terminal its binding induces...
Abstract DNA polymerase III (DNA pol III) is a multi-subunit replication machine responsible for the accurate and rapid of bacterial genomes, however, how it functions in Mycobacterium tuberculosis ( Mtb ) requires further investigation. We have reconstituted leading-strand process holoenzyme vitro investigated physical functional relationships between its key components. verify presence an αβ 2 ε polymerase-clamp-exonuclease replicase complex by biochemical methods protein-protein...
Convolutional neural networks are built upon simple but useful convolution modules. The traditional has a limitation on feature extraction and object localization due to its fixed scale geometric structure. Besides, the loss of spatial information also restricts networks' performance depth. To overcome these limitations, this paper proposes novel anisotropic by adding factor shape into convolution. augments receptive fields flexibly dynamically depending valid sizes objects. In addition, is...
The robust feature extraction method for face representation is an important issue in recognition. In this paper, we extract a new kind of through applying the idea local binary pattern (LBP) into resulted sub-images Gabor transform. feature, i.e. Gabor-LBP-Like (GLLBP), together with its extension methods (1) overcome drawback losing information after transform’s down-sampling; (2) are insensitive to noise, compared LBP extracted from original image; and (3) image variation, especially...
Color constancy is one of the fundamental tasks in computer vision. Many supervised methods, including recently proposed Convolutional Neural Networks (CNN)-based have been proved to work well on this problem, but they often require a sufficient number labeled data. However, it expensive and time-consuming collect large training images with accurately measured illumination. In order reduce dependence leverage unlabeled ones without illumination, we propose novel semi-supervised framework...
In this paper, a novel feature extraction method based on an improved color local binary pattern (LBP) is proposed for face recognition. Firstly, in given neighborhood of every pixel, we choose some sampling points from three channels simultaneously and the numbers channel may be different. Secondly, use new rule to select threshold which does not always locate geometrical center neighborhood. Thirdly, order excavate potential method, [Formula: see text]-uniform LBP obtain code each pixel....
In this paper, we propose two self-adapting patch strategies, which are obtained by employing the integral projection technique on images’ edge images, while images recovered two-dimensional discrete wavelet transform. The strategies equipped with advantage of considering single image’s unique properties and maintaining integrity some particular local information. Combining binary pattern feature extraction classifier forward backward greedy algorithms under strong sparse constraint, new...
Detection of ship targets in the sea area is an important field remote sensing image target detection. As ships and surrounding areas are very different texture, that makes it a possible solution to detect using texture feature. Aiming at detection targets, novel algorithm large scene optical proposed this paper. This based on conspicuity multi-scale fractal dimension feature background, then realized by method visual saliency model. In paper, accuracy small or medium-sized window...
Abstract The Yellow River Delta wetland is a habitat for wintering waterfowl, where mallard ( Anas platyrhynchos ) and tundra bean goose Anser fabalis are commonly observed. Although the intestinal flora plays pivotal role in maintaining host health promoting nutrient absorption, it remains unclear whether same overwintering challenging feeding conditions specifically affect composition diversity of both species. Here, high-throughput sequencing was used to compare bacterial communities from...
With the rise of "Metaverse" and "Web 3.0", Non-Fungible Token (NFT) has emerged as a kind pivotal digital asset, garnering significant attention.By end March 2024, more than 1.7 billion NFTs have been minted across various blockchain platforms.To effectively locate desired NFT, conducting searches within vast array is essential.The challenge in NFT retrieval heightened due to high degree similarity among different NFTs, regarding regional semantic aspects.In this paper, we will introduce...
Abstract PRMT1 is the predominant type I protein arginine methyltransferase responsible for generating monomethylarginine and asymmetric dimethylarginine (MMA ADMA) in various substrates. It regulates numerous biological processes, including RNA metabolism, mRNA splicing, DNA damage repair, chromatin dynamics. The crystal structure of rat has been previously reported as a homodimer; however, higher-order oligomeric species human have observed vivo, their structural basis remains elusive. In...
Dimensionality reduction is a problem of fundamental importance in both machine learning and data mining. In this paper, we develop new approach that can process labeled datasets accurately reduce their dimensionalities. The based on objective contains information from the global local structures set. An iterative used to compute directions along which be optimized. Experiments benchmark sets show dataset effectively captured by it thus able provide more accurate results for dimensionality...
For modern sport training, critical posture recognition of athletes can be helpful for athlete training. This paper proposes convolutional neural networks using a two-stage evaluation mechanism to recognize four postures weightlifter, that is, force releasing, knee flexion, extension and highest point. Using the proposed classify images extract image features. Meanwhile, is adopted calculate scores features, based on calculated scores, accurately recognized. Experimental results show...
Abstract The ability of RNA-binding proteins (RBPs) to form complexes with other biomolecules underpins a broad range functions and remarkable structural properties. Understanding the precise spatiotemporal dynamics RBPs their interacting partners in steady state upon perturbation is key deciphering these aspects. Here, we present coRIC ( co mpartmentalized R NA Interactome C apture) map, an experimental resource analytical pipeline study subcellular through multimodal dataset integration...
A new method to evaluate the quality of color images is proposed in this paper, i.e. DSF (definition, error sensitivity and objective fidelity), which would combine definition, fidelity through utilizing vision properties human eyes redundant information fully. For existence redundancy structural similarity between three different frames, definition be evaluated by way based on 3D SIT (submatrix integration transform), components image integrated into one model can exploited well. The...