Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1430 - 1438
• Main Authors: Danelljan, Martin, Hager, Gustav, Khan, Fahad Shahbaz, Felsberg, Michael
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Series: IEEE Conference on Computer Vision and Pattern Recognition
• Subjects: Computational modeling; Robustness; Target tracking; Training; Videos; Visualization

Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data, additional samples need to be extracted and labeled by the tracker i...