A5100621288- Heat Transfer and Optimization
- Anomaly Detection Techniques and Applications
- Explainable Artificial Intelligence (XAI)
- Machine Learning in Healthcare
- Human Pose and Action Recognition
- Heat Transfer Mechanisms
- Refrigeration and Air Conditioning Technologies
- Fatigue and fracture mechanics
- High Entropy Alloys Studies
- Sports Analytics and Performance
- Aluminum Alloys Composites Properties
- Anaerobic Digestion and Biogas Production
- Bayesian Modeling and Causal Inference
- Heat Transfer and Boiling Studies
- High-Temperature Coating Behaviors
- Bioinformatics and Genomic Networks
- Membrane Separation and Gas Transport
- Multimodal Machine Learning Applications
- Advanced Theoretical and Applied Studies in Material Sciences and Geometry
- Resource-Constrained Project Scheduling
- Brake Systems and Friction Analysis
- Domain Adaptation and Few-Shot Learning
- Mechanical Failure Analysis and Simulation
- Phonocardiography and Auscultation Techniques
- Machine Learning and ELM
University of Auckland
2024-2025
North University of China
2025
Shanghai University of Traditional Chinese Medicine
2025
Yueyang Hospital
2025
Shandong University
2024
Shanghai Jiao Tong University
2021-2024
Inner Mongolia University
2024
Jiaozuo University
2024
Xinxiang Medical University
2024
Donghua University
2024
We introduce a new benchmark "Humans Interacting with Common Objects" (HICO) for recognizing human-object interactions (HOI). demonstrate the key features of HICO: diverse set common object categories, list well-defined, sense-based HOI and an exhaustive labeling co-occurring category in each image. perform in-depth analysis representative current approaches show that DNNs enjoy significant edge. In addition, we semantic knowledge can significantly improve recognition, especially uncommon categories.
To enhance the positioning accuracy of autonomous underwater vehicles (AUVs), a new adaptive filtering algorithm (RHAUKF) is proposed. The most widely used traditional Unscented Kalman Filter or Adaptive Robust UKF (ARUKF). Excessive noise interference may cause decrease in and highly likely to result divergence by means Filter, resulting an increase uncertainty factors during submersible mission execution. An estimation model for system noise, (UKF) was derived light maximum likelihood...
The application of Artificial Intelligence (AI) and Computer Vision (CV) in sports has generated significant interest enhancing viewer experience through graphical overlays predictive analytics, as well providing valuable insights to coaches. However, more efficient methods are needed that can be applied across different without incurring high data annotation or model training costs. A major limitation deep learning models on large datasets is the resource requirement for reproducing...
In many settings, it is important that a model be capable of providing reasons for its predictions (ıe, the must interpretable). However, model's reasoning may not conform with well-established knowledge. such cases, while interpretable, lacks credibility. this work, we formally define credibility in linear setting and focus on techniques learning models are both accurate credible. particular, propose regularization penalty, expert yielded estimates (EYE), incorporates knowledge about...
The global incidence of metabolic dysfunction-associated fatty liver disease (MAFLD) is increasing annually, which has become a major public-health concern. MAFLD typically associated with obesity, hyperlipemia, or syndrome. Dietary induction one the most common methods for preparing animal models MAFLD. However, there are phenotypic differences between methionine-choline-deficient diet (MCDD) and high fat (HFD) models. To explore in hepatic acid metabolism MCDD HFD induced MAFLD, we...
Abstract Rolling bearings play a vital role in ensuring the safe operation of rotating machinery. However, many application scenarios, collected data has low signal-to-noise ratio and samples with faults are rare, which affects generalization capability model, making it impossible to achieve accurate diagnosis. To solve this problem, selection time-frequency (TF) maps was considered paper through reinforcement learning. The TF built by four classical characterization methods such as...
Low-light video enhancement is a challenging task with broad applications. However, current research in this area limited by the lack of high-quality benchmark datasets. To address issue, we design camera system and collect low-light dataset multiple exposures cameras. Our provides dynamic pairs pronounced motion strict spatial alignment. achieve general enhancement, also propose novel Retinex-based method named Light Adjustable Network (LAN). LAN iteratively refines illumination adaptively...