mlsanityData to 14 Oct 2026

Tracking Emerges by Colorizing Videos

arXiv 1806.09594 ↗First posted 25 Jun 2018cs.CV cs.GR cs.LGcited by 166

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 166 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 56; 2022: 46; 2023: 37; 2024: 15; 2025: 10; 2026: 2.

166 papers.

Sort:

By area:

  1. 2023Emergent Correspondence from Image Diffusioncited by 446
  2. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 429
  3. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 276
  4. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 263
  5. 2023A Cookbook of Self-Supervised Learningcited by 250
  6. 2023Tracking Everything Everywhere All at Oncecited by 193
  7. 2021VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examplescited by 154
  8. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  9. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  10. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  11. 2024CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videoscited by 128
  12. 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 120
38 more
  1. 2021Broaden Your Views for Self-Supervised Video Learningcited by 108
  2. 2021Region Similarity Representation Learningcited by 96
  3. 2021Colorization Transformercited by 89
  4. 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
  5. 2021Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspectivecited by 81
  6. 2023Siamese Masked Autoencoderscited by 76
  7. 2023Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Datacited by 69
  8. 2023Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lecturescited by 68
  9. 2021Multiple Object Tracking with Correlation Learningcited by 67
  10. 2021Self-supervised Video Transformercited by 64
  11. 2024DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Videocited by 64
  12. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  13. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  14. 2021Joint Inductive and Transductive Learning for Video Object Segmentationcited by 61
  15. 2022Mix and Localize: Localizing Sound Sources in Mixturescited by 54
  16. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  17. 2021Learning the Predictability of the Futurecited by 49
  18. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  19. 2022Dissecting Self-Supervised Learning Methods for Surgical Computer Visioncited by 48
  20. 2024EmbedLLM: Learning Compact Representations of Large Language Modelscited by 48
  21. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
  22. 2023Towards In-context Scene Understandingcited by 47
  23. 2021Motion-aware Contrastive Video Representation Learning via Foreground-background Mergingcited by 45
  24. 2021The Emergence of Objectness: Learning Zero-Shot Segmentation from Videoscited by 45
  25. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  26. 2021Self-Supervised Pillar Motion Learning for Autonomous Drivingcited by 44
  27. 2021Representation Learning via Global Temporal Alignment and Cycle-Consistencycited by 44
  28. 2021Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outlierscited by 39
  29. 2022Learning Pixel Trajectories with Multiscale Contrastive Random Walkscited by 36
  30. 2023CLIP-S4: Language-Guided Self-Supervised Semantic Segmentationcited by 34
  31. 2021Group Collaborative Learning for Co-Salient Object Detectioncited by 32
  32. 2024Moving Object Segmentation: All You Need Is SAM (and Flow)cited by 30
  33. 2021Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimizationcited by 27
  34. 2021Dense Unsupervised Learning for Video Segmentationcited by 26
  35. 2022Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learningcited by 26
  36. 2021Self-Supervised Multi-Object Tracking with Cross-Input Consistencycited by 25
  37. 2021Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learningcited by 22
  38. 2022Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wildcited by 22

50 most cited of 166 All 166 (JSON)