A5100723207- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Robotics and Sensor-Based Localization
- Advanced Neural Network Applications
- Visual Attention and Saliency Detection
- Fire Detection and Safety Systems
- Human Pose and Action Recognition
- Bioenergy crop production and management
- Image Enhancement Techniques
- Gait Recognition and Analysis
- Image and Object Detection Techniques
- Remote Sensing and LiDAR Applications
- Cloud Computing and Resource Management
- Forest ecology and management
- Hand Gesture Recognition Systems
- Advanced Image Processing Techniques
- Image and Video Quality Assessment
- Interactive and Immersive Displays
- Metaheuristic Optimization Algorithms Research
- IoT and Edge/Fog Computing
- Machine Fault Diagnosis Techniques
- Advanced Measurement and Detection Methods
- Neural Networks and Reservoir Computing
Tsinghua University
2023-2025
Renmin University of China
2025
Yanshan University
2013-2024
Second Affiliated Hospital of Chongqing Medical University
2021-2024
Dalian Medical University
2021-2024
Army Medical University
2021-2024
University of Science and Technology Liaoning
2024
Chongqing Medical University
2021-2024
Henan University
2020
National University of Defense Technology
2020
Abstract The Honey Badger Algorithm (HBA) is a new swarm intelligence optimization algorithm by simulating the foraging behavior of honey badgers in nature. To further improve its convergence speed and accuracy, an improved HBA based on density factors with elementary functions mathematical spirals polar coordinate system was proposed. proposes six for attenuation states functions, introduces expressions diameters angles seven (Fibonacci spiral, Butterfly curve, Rose Cycloid, Archimedean...
To tackle the negative effect of arbitrary crowd distribution on counting task, in this article, we propose a novel RGB-D approach, including cross-modal cycle-attention fusion (CmCaF) model and fine-coarse (FC) supervision. In feature level, CmCaF combines RGB depth way so as to effectively. supervision design FC could optimize from both fine pixel-aware level coarse region-aware enhance its sensitivity whole instance location. Extensive evaluations benchmarks well illustrate feasibility...
The Amodal Instance Segmentation (AIS) task aims to infer the visible and occluded regions of an object instance. Existing AIS methods typically focus on directly predicting or leveraging prior knowledge guide predictions. However, these often ignore perception views, leading inaccurate results. To address this issue achieve high-quality AIS, we propose a boundary-aware Occlusion Perception Network (OPNet). OPNet consists three main components: Dynamic Feature Augmentation Pyramid (DFAP),...
Abstract Ever reports showed that PCNP is associated with human cancers including neuroblastoma and lung cancer. However, the role underlying molecular mechanism of in ovarian cancer have not been plenty elucidated. Herein, we first investigated expression tissues cells, effects proliferation, apoptosis, migration invasion, determined progression. The results indicated was significantly overexpressed related to poor prognosis patients. In addition, also detected promoted cells growth, as...
Two-dimensional (2D) ultrasound (US) images are widely used in minimally invasive prostate procedure for its noninvasive nature and convenience. However, the poor quality of US image makes it difficult to be as guiding utility. To improve limitation, we propose a multimodality guided navigation module that registers 2D with magnetic resonance imaging (MRI) based on high preoperative models. A 2-step spatial registration method is complete which combines manual alignment rapid mutual...
We analyze the connections between entanglement dynamics and classical trajectories in a semiclassical regime for two systems: A pair of coupled oscillators Jaynes-Cummings model. find that production depends on invariant tori such phenomenon is closely related to power spectra trajectories. Classical spectrum with larger number frequency components corresponds entanglement. introduce entropy describe distribution. It found there good correspondence entropies maximum von Neumann entropies.
Recent developments of crowd analysis and behaviour prediction have attracted much attention. Crowd counting, as the essential challenging task in analysis, is riddled with many issues, such large scale variations, serious occlusion, so on. In this study, a self‐attention‐based multi‐scale cascaded network called SAMC‐Net to estimate density map for especially high congested scene, proposed. The proposed consists two components: classification sub‐network estimation an end‐to‐end convolution...