Self-paced learning for long-term tracking
icon We address the problem of long-term object tracking, where the object may become occluded or leave-the-view. In this setting, we show that an accurate appearance model is considerably more effective than a strong motion model. We develop simple but effective algorithms that alternate between tracking and learning a good appearance model given a track. We show that it is crucial to learn from the “right” frames, and use the formalism of self-paced curriculum learning to automatically select such frames. We leverage techniques from object detection for learning accurate appearance-based templates, demonstrating the importance of using a large negative training set (typically not used for tracking). We describe both an offline algorithm (that processes frames in batch) and a linear-time online (i.e. causal) algorithm that approaches real-time performance. Our models significantly outperform prior art, reducing the average error on benchmark videos by a factor of 4.

Download: pdf

Text Reference

James Steven Supan\vc i\vc and Deva Ramanan. Self-paced learning for long-term tracking. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 2379–2386. IEEE, 2013.

BibTeX Reference

@inproceedings{SupancicR_CVPR_2013,
    author = "Supan{\vc}i{\vc}, James Steven and Ramanan, Deva",
    title = "Self-paced learning for long-term tracking",
    booktitle = "Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on",
    pages = "2379--2386",
    year = "2013",
    organization = "IEEE"
}