A5010700792- Face recognition and analysis
- Robotics and Sensor-Based Localization
- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Gait Recognition and Analysis
Beijing University of Posts and Telecommunications
2022-2023
Recently, Multi-Object Tracking (MOT) has attracted rising attention, and accordingly, remarkable progresses have been achieved. However, the existing methods tend to use various basic models (e.g, detector embedding model), different training or inference tricks, etc. As a result, construction of good baseline for fair comparison is essential. In this paper, classic tracker, i.e., DeepSORT, first revisited, then significantly improved from multiple perspectives such as object detection,...
As person parts are frequently misaligned between detected human boxes, an image representation that can handle this part misalignment is required. In work, we propose effective grouped attentive re-identification (GAReID) framework to learn part-aligned and background robust representations for (ReID). Specifically, the GAReID consists of high-order pooling (GHOP) (AHOP) layers, which generate foreground features, respectively. addition, a novel Kronecker product (GKP) proposed use both...