Visual Object Tracking
Visual Object Tracking is an important research topic in computer vision, image understanding and pattern recognition. Given the initial state (centre location and scale) of a target in the first frame of a video sequence, the aim of Visual Object Tracking is to automatically obtain the states of the object in the subsequent video frames.
Papers
Showing 1–10 of 341 papers
All datasetsLaSOTGOT-10kTrackingNetLaSOT-extOTB-2015UAV123TNL2KVOT2017/18DiDiNeedForSpeedYouTube-VOS 2018AVisT
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SAMURAI-L | Average Overlap | 81.7 | — | Unverified |
| 2 | DAM4SAM | Average Overlap | 81.1 | — | Unverified |
| 3 | SPMTrack-G | Average Overlap | 81 | — | Unverified |
| 4 | MITS | Average Overlap | 80.4 | — | Unverified |
| 5 | MCITrack-L384 | Average Overlap | 80 | — | Unverified |
| 6 | SPMTrack-L | Average Overlap | 80 | — | Unverified |
| 7 | ARTrackV2-L | Average Overlap | 79.5 | — | Unverified |
| 8 | LoRAT-g-378 | Average Overlap | 78.9 | — | Unverified |
| 9 | ARTrack-L | Average Overlap | 78.5 | — | Unverified |
| 10 | ODTrack-L | Average Overlap | 78.2 | — | Unverified |