動画のカラー化によって創発する物体追跡
Tracking Emerges by Colorizing Videos
ラベルなし動画の時間的一貫性を利用し、グレースケール動画を参照フレームの色で彩色する学習を通じて、人手の教師なしで視覚的追跡モデルを獲得した研究。
著者: Carl Vondrick, Abhinav Shrivastava, Alireza Fathi, Sergio Guadarrama, Kevin Murphy
分類: cs.CV, cs.GR, cs.LG, cs.MM, cs.RO
原文アブストラクト
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.
