Localization-Aware Meta Tracker Guided With Adversarial Features
Deep learning has recently shown great potentials in learning powerful features for visual tracking. However, most deep learning-based trackers neglect localization accuracy in the evaluation process of candidates. What's more, they usually over-rely on the discriminative features in a single f...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Sprog: | English |
| Udgivet: |
IEEE
2019-01-01
|
| Serier: | IEEE Access |
| Fag: | |
| Online adgang: | https://ieeexplore.ieee.org/document/8769969/ |