A5004573172- Blockchain Technology Applications and Security
- Advanced Measurement and Detection Methods
- Diabetic Foot Ulcer Assessment and Management
- Vehicle License Plate Recognition
- Human Pose and Action Recognition
- Digital Imaging for Blood Diseases
- Video Analysis and Summarization
- Dental Radiography and Imaging
- Complex Network Analysis Techniques
- Anatomy and Medical Technology
- Video Surveillance and Tracking Methods
- Digital Image Processing Techniques
- Advanced X-ray and CT Imaging
- Spam and Phishing Detection
- Advanced Vision and Imaging
- Handwritten Text Recognition Techniques
University of Electronic Science and Technology of China
2025
Fudan University
2023
Institute of Forensic Science
2020
Controlling the movements of dynamic objects and camera within generated videos is a meaningful yet challenging task. Due to lack datasets with comprehensive motion annotations, existing algorithms can not simultaneously control motions both objects, resulting in limited controllability over contents. To address this issue facilitate research field, we introduce Synthetic Dataset for Free-Form Motion Control (SynFMC). The proposed SynFMC dataset includes diverse environments covers various...
There are two main methods of structural health monitoring. Among them, the traditional structure monitoring technology is mainly artificial, which has some problems such as inflexibility, large error, high cost and difficult to adapt change natural environment. The method based on machine vision characteristics flexible measuring point, accuracy, fast speed no contact. A variety technologies, image acquisition, processing, three-dimensional deep learning have made great progress, their...
The UPDRS III scale plays a critical role in diagnosing the progression of Parkinson's disease. Current methods often involve doctors guiding patients through specific actions on scale, recording their performance, and assigning scores. However, this approach has several drawbacks, including lengthy time required for doctorpatient communication, high costs traveling to hospitals follow-up visits, reliance subjective judgments from doctors, which lack standardized criteria. With advancements...
In recent years, with the popularity of Internet, a large number copyright infringement cases continue to emerge. Especially in cartoon industry, due difficulty replicating original works, incidents are more frequent. Therefore, this article aims prevent character and designs implements detection method based on improved YOLOv5s SIFT algorithms. response weak recognition ability model for small-sized objects, algorithm is by introducing multi-scale prediction, adding new categories,...
Objective To discuss the application of artificial intelligence automatic diatom identification system in practical cases, to provide reference for quantitative analysis using and validate deep learning model incorporated into system. Methods Organs from 10 corpses water were collected digested with nitric acid; then smears digitally scanned a digital slide scanner diatoms tested qualitatively quantitatively by Results The area under curve （AUC） receiver operator characteristic （ROC） system,...
Objective To evaluate the influence of factors such as selection equipment, focal length and reconstruction quality in software on results single camera photogrammetry provide reference for forensic application photogrammetry. Methods The 19 skulls were measured by traditional measurement method differences between two methods within group with same equipment but different analyzed. One skull one corpse selected research objects. According to conditions photogrammetric software, experimental...
The phishing scam is a major kind of fraudulence in blockchain. And it has become an urgent issue to discern and prevent the fraudulent behaviors. However, large-scale dynamic nature transaction network imposes great challenges on identification analysis. While there have been many sophisticated machine learning approaches providing predictive capability terms detecting such cases, they usually offer little insight into essence those behaviors occasion when activities happen. Motivated by...