Research map / Detection and segmentation / Tracking
Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking
Heng Fan, Haibin Ling
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the parallel verifier to the fDSST tracker | fDSST · OTB2015 | distance precision rate: 72 -> 84.9 | Improved |
| add the parallel verifier to the fDSST tracker | fDSST · OTB2015 | overlap success rate: 67.6 -> 77.6 | Improved |
| add the parallel verifier to the fDSST tracker | fDSST · TC128 | distance precision rate: 57.5% -> 74.1% | Improved |
| add the parallel verifier to the fDSST tracker | fDSST · TC128 | overlap success rate: 43.5% -> 54.4% | Improved |
| run tracking and verifying in two threads instead of one (ablation) | PTAV · OTB2013 | speed (fps): 16 -> 27 | Improved |
| run tracking and verifying in two threads instead of one (ablation) | PTAV · UAV20L | speed (fps): 15 -> 25 | Improved |
| use fDSST instead of KCF as the tracker (ablation) | PTAV · OTB2013 | distance precision rate: 80.4 -> 89.4 | Improved |
| use fDSST instead of KCF as the tracker (ablation) | PTAV · OTB2015 | overlap success rate: 57.9 -> 77.6 | Improved |
| use fDSST instead of KCF as the tracker (ablation) | PTAV · OTB2013 | speed (fps): 24 -> 27 | Improved |
| shorten verification interval from V=10 to V=5 (ablation) | PTAV · OTB2013 | distance precision rate and speed: DPR 89.4 -> 89.7, speed 27 -> 23 fps | Mixed |
| lengthen verification interval from V=10 to V=15 (ablation) | PTAV · OTB2013 | distance precision rate and speed: DPR 89.4 -> 87.9, speed 27 -> 29 fps | Mixed |
| PTAV versus deep tracker HCF on TC128 | PTAV · TC128 | distance precision rate: 70.5% -> 74.1% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Staple — Staple: Complementary Learners for Real-Time Tracking (CVPR 2016) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework (ICCV 2023 · similarity 0.87)
- UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization (ECCV 2026 · similarity 0.87)
- PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking (ICCV 2023 · similarity 0.86)
- Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook (TPAMI 2022 · similarity 0.86)
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (CVPR 2024 · similarity 0.85)
- DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
