BootsTAP: Bootstrapped Training for Tracking-Any-Point
Authors:
- 8 December 2024
- book chapter
- Published by Springer Nature
- p. 483-500
Abstract
No abstract availableKeywords
All Related Versions
This publication has 58 references indexed in Scilit:
- Track2Act: Predicting Point Tracks from Internet Videos Enables Generalizable Robot Manipulation2024
- CoTracker: It Is Better to Track Together2024
- Semi-supervised Learning of Optical Flow by Flow Supervisor2022
- Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories2022
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow2020
- Unsupervised Learning of Multi-Frame Optical Flow with Occlusions2018
- Tracking Emerges by Colorizing Videos2018
- Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness2016
- A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation2016
- Particle Video: Long-Range Motion Estimation Using Point TrajectoriesInternational Journal of Computer Vision, 2008