Tracking Emerges by Colorizing Videos

ECCV 2018  ·  Carl Vondrick, Abhinav Shrivastava, Alireza Fathi, Sergio Guadarrama, Kevin Murphy ·

We 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.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Skeleton Based Action Recognition JHMDB Pose Tracking ColorPointer PCK@0.1 45.2 # 2
Compare
PCK@0.2 69.6 # 2
Compare
PCK@0.3 80.8 # 2
Compare
PCK@0.4 87.5 # 2
Compare
PCK@0.5 91.4 # 2
Compare

Methods
Add Remove

Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy