A5100343530- Visual Attention and Saliency Detection
- Advanced Image and Video Retrieval Techniques
- Nanoparticle-Based Drug Delivery
- Multimodal Machine Learning Applications
- Recommender Systems and Techniques
- Advanced Neural Network Applications
- Human Mobility and Location-Based Analysis
- Topic Modeling
- Research in Cotton Cultivation
- Advanced Multi-Objective Optimization Algorithms
- Cardiovascular Health and Risk Factors
- Human Pose and Action Recognition
- Image Retrieval and Classification Techniques
- Image Processing Techniques and Applications
- Educational Technology and Assessment
- Luminescence Properties of Advanced Materials
- Perovskite Materials and Applications
- Systemic Lupus Erythematosus Research
- Domain Adaptation and Few-Shot Learning
- Advanced Vision and Imaging
- Luminescence and Fluorescent Materials
- Heat Transfer and Optimization
- Clinical Laboratory Practices and Quality Control
- biodegradable polymer synthesis and properties
- Renal Diseases and Glomerulopathies
Second Affiliated Hospital of Xi'an Jiaotong University
2018-2024
Xi'an Jiaotong University
2015-2024
Tencent (China)
2022-2024
Shenzhen University
2024
Macao Polytechnic University
2022
Chinese Academy of Meteorological Sciences
2022
Zhengzhou University
2022
Nanchang Institute of Technology
2022
University of Chinese Academy of Sciences
2020
Institute of Computing Technology
2020
Next POI recommendation has been studied extensively in recent years. The goal is to recommend next for users at specific time given users' historical check-in data. Therefore, it crucial model both general taste and sequential behaviors. Moreover, different show dependencies on the two parts. However, most existing methods learn same users. Besides, locations categories of POIs contain information about preference. current researchers always treat them as factors or believe that determine...
Abstract Long blood circulation in vivo remains a challenge to dual‐drug‐loaded nanocarriers for synergistic chemotherapy. Herein, novel strategy prepare lollipop‐like nanoparticles (DOX–PDA–gossypol NPs) is developed based on the self‐assembly of gossypol, doxorubicin (DOX), and polydopamine (PDA) via π–π stacking. Dopamine polymerizes PDA fills gaps between gossypol DOX molecules form super compact long‐circulating nanoparticles. The DOX–PDA–gossypol NPs show suitable particle size 59.6 ±...
Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task rare, polysemous, and ambiguous words frequently appear images, e.g., names places, products, sports teams. To overcome difficulty, only resorting to pre-trained word embedding models far from enough. A desired model should utilize the rich information multiple modalities help understand meaning scene texts, prominent text on a bottle most likely be brand. Following...
Next POI recommendation has been studied extensively in recent years. The goal is to recommend next for users at specific time given users' historical check-in data. Therefore, it crucial model general taste and sequential behavior. Moreover, the context information such as category also important capture user preference. To this end, we propose a long- short-term preference learning (LSPL) considering information. In long-term module, learn contextual features of POIs leverage attention...
Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks. The progresses are highly relevant to the architecture design, then it is worthwhile propose Architecture Search (TAS) search for better ViTs automatically. However, current TAS methods time-consuming and existing zero-cost proxies CNN do not generalize well ViT space according our experimental observations. In this paper, first time, we investigate how conduct a training-free manner devise...
The progression of proteinuric kidney diseases is associated with podocyte loss but the mechanisms underlying this process remain unclear. Podocytes re-enter cell cycle to repair double-stranded DNA (dsDNA) breaks. However, unsuccessful can result in podocytes crossing G1/S checkpoint and undergoing abortive cytokinesis. In study, we identified Pfn1 as indispensable maintaining glomerular integrity - its tissue-specific mouse results severe proteinuria failure. Our suggest that phenotype due...
The double-layered nanoparticles encapsulating the chiral drug (−)-gossypol possess tumor-targeting ability, a sustained release profile, and evident tumor-inhibition effects.
This paper presents a new image retargeting method based on seam searching and pixel fusion. First, the importance map of original image, which is represented by saliency every pixel, generated. Second, all pixels in are divided into W (width image) groups with help searching. Then, it performs inter-row coherence filtering to maintain spatial coherence, directly utilizes filtered generate scaling map. Finally, after fusion map, can be retargeted effectively. Experimental results show that...
Novel ratiometric fluorescent short single-stranded DNA (ssDNA) nanothermometers (ssDNA FT) were developed using the fluorescence resonance energy transfer (FRET) effect of ssDNA's end labeled fluorophores. An optimal ssDNA sequence and associated FT determined through combined MD simulation temperature-related FRET analysis. Their properties thermo-responsivities analyzed spectra. The influences ssDNA' length, composition labels for temperature sensing investigated. Results revealed...
Traditional image resizing methods, such as uniform scaling and content-aware retargeting, are designed to preserve the visually salient contents of an while it. In this paper, we propose a novel approach called recognition-oriented retargeting. Its goal is distinctive local features for recognition instead traditional visual saliency during resizing. Moreover, also apply our matching retrieval applications verify its performance. Meanwhile, using these able solve some challenging problems...
To improve the computed tomography (CT) imaging ability and toxicity of gold nanoparticles (AuNPs), hydrophilic dopamine (DPA)-coated nanoparticle (AuNP) (MSA AuNPs@DPA) aggregates (42 ± 2.65 nm) were obtained by assembling MSA AuNPs@DPA (5-6 with use polyethyleneimine (PEI). They rapidly degraded into PEI in blood. The acute test showed that maximum tolerated doses larger than 4.8 4.6 g kg-1, respectively, which are much higher those commonly used citric acid-stabilized AuNPs (CA AuNPs)...
Abstract With the development of digital technology, dance movement recognition and correction has become a hot research topic. This study focuses on system that incorporates human skeletal information aims to improve movements’ accuracy efficiency. develops combines lean information. can recognize correct movements accurately by improving spatio-temporal graph convolutional network (ST-GCN). The employs representation skeleton spatial convolution technique, enhances system’s capability...
Point of interest (POI) recommendation is a popular personalized location-based service. This paper proposes Geographic Personal Matrix Factorization (GPMF) model that makes effective use geographic information from the perspective relationship between POIs and users. considers role multiple perspectives based on locational among users, distributional users POIs, proximity clustering POIs. The GPMF mines influence different objects carries out unique modeling through cosine similarity,...