Command Palette
Search for a command to run...
Carl Vondrick; Abhinav Shrivastava; Alireza Fathi; Sergio Guadarrama; Kevin Murphy
Abstract
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| skeleton-based-action-recognition-on-jhmdb | ColorPointer | PCK@0.1: 45.2 PCK@0.2: 69.6 PCK@0.3: 80.8 PCK@0.4: 87.5 PCK@0.5: 91.4 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.