-
Tracking Emerges by Colorizing Videos
AbstractWe use large amounts of unlabeled video to learn models for visual tracking without manual human supervision. We leverage the natural temporal coherency of color to create a model that learns to colorize gray-scale videos by copying colors from a reference frame. Quantitative and qualitative experiments suggest that this task causes the model to automatically learn to track visual regions. Although the model is trained without any ground-truth labels, our method learns to track well enough to outperform the latest methods based on optical flow. Moreover, our results suggest that failures to track are correlated with failures to colorize, indicating that advancing video colorization may further improve self-supervised visual tracking.
Related Material
[pdf] [arXiv][bibtex]@InProceedings{Vondrick_2018_ECCV,
author = {Vondrick, Carl and Shrivastava, Abhinav and Fathi, Alireza and Guadarrama, Sergio and Murphy, Kevin},
title = {Tracking Emerges by Colorizing Videos},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}
ECCV 2018 papers
The ECCV 2018 papers, provided here by the Computer Vision Foundation, are the author-created versions. The content of the papers is identical to the content of the officially published ECCV 2018 LNCS version of the papers as available on SpringerLink: https://link.springer.com/conference/eccv.
Intellectual property rights, copyright and all rights therein are retained by authors, by Springer as the publisher of the official ECCV 2018 proceedings or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.