Visual Tracking
Visual Tracking is an essential and actively researched problem in the field of computer vision with various real-world applications such as robotic services, smart surveillance systems, autonomous driving, and human-computer interaction. It refers to the automatic estimation of the trajectory of an arbitrary target object, usually specified by a bounding box in the first frame, as it moves around in subsequent video frames.
Source: Learning Reinforced Attentional Representation for End-to-End Visual Tracking
Papers
Showing 1–10 of 525 papers
All datasetsTNL2KDAVISKineticsKubricRGB-StackingLaSOTOTB-100OTB-2013Second dialogue state tracking challengeTrackingNet
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | ARTrack-L | AUC | 60.3 | — | Unverified |
| 2 | UNINEXT-H | AUC | 59.3 | — | Unverified |
| 3 | JointNLT | AUC | 56.9 | — | Unverified |
| 4 | OSTrack | AUC | 55.9 | — | Unverified |
| 5 | TransT | AUC | 50.7 | — | Unverified |
| 6 | AdaSwitcher | AUC | 42 | — | Unverified |