A5062275056- Anomaly Detection Techniques and Applications
- Human Pose and Action Recognition
- Image Enhancement Techniques
- Advanced Image Processing Techniques
- Context-Aware Activity Recognition Systems
- Underwater Acoustics Research
- Video Surveillance and Tracking Methods
- Complex Systems and Time Series Analysis
- Underwater Vehicles and Communication Systems
- Time Series Analysis and Forecasting
- Gait Recognition and Analysis
- Advanced Vision and Imaging
Nanjing University of Information Science and Technology
2023-2024
At present, 3D reconstruction technology is being gradually applied to underwater scenes and has become a hot research direction that vital human ocean exploration development. Due the rapid development of computer vision in recent years, optical image mainstream method. Therefore, this paper focuses on methods environment. However, due wide application sonar reconstruction, also introduces summarizes based acoustic optical–acoustic fusion methods. First, uses Citespace software visually...
Abstract Temporal Action Detection (TAD) aims to accurately capture each action interval in an untrimmed video and understand human actions. This paper comprehensively surveys the state-of-the-art techniques models used for TAD task. Firstly, it conducts comprehensive research on this field through Citespace introduce relevant dataset. Secondly, summarizes three types of methods, i.e., anchor-based, boundary-based, query-based, from design method level. Thirdly, supervised learning methods...
In action recognition, obtaining skeleton data from human poses is valuable. This process can help eliminate negative effects of environmental noise, including changes in background and lighting conditions. Although GCN learn unique features, it fails to fully utilize the prior knowledge body structure coordination relations between limbs. To address these issues, this paper proposes a Multi-level Topological Channel Attention Network algorithm: Firstly, Topology Module incorporates using...