| Paper | Code | AJ | OA | delta_avg | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| Dense Optical Tracking: Connecting the Dots | ✓ Link | 0.772 | 0.933 | 0.877 | DOT (CoTracker + RAFT) | 2023-12-01 |
| Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking | ✓ Link | 0.748 | 0.909 | 0.852 | DiTracker (CoTracker3) (extra data) | 2025-12-23 |
| TAPNext++: What's Next for Tracking Any Point (TAP)? | ✓ Link | 0.734 | 0.951 | 0.848 | TAPNext++ (extra data) | 2026-04-12 |
| Online Dense Point Tracking with Streaming Memory | ✓ Link | 0.733 | 0.903 | 0.864 | SPOT | 2025-03-09 |
| TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video | ✓ Link | 0.723 | 0.908 | 0.841 | TAPTRv3 (online, ResNet-18) | 2024-11-27 |
| Track-On: Transformer-based Online Point Tracking with Memory | ✓ Link | 0.714 | 0.917 | 0.852 | Track-On | 2025-01-30 |
| TAPTR: Tracking Any Point with Transformers as Detection | ✓ Link | 0.608 | 0.87 | 0.762 | TAPTR | 2024-03-19 |
| TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement | ✓ Link | 0.562 | 0.893 | 0.7 | TAPIR (MOVi-E) | 2023-06-14 |