Research map / Detection and segmentation / Tracking
Visual Tracking via Dynamic Graph Learning
Chenglong Li, Liang Lin, Wangmeng Zuo, Jin Tang, Ming–Hsuan Yang
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 patch weights to the object representation (ablation) | WPG · OTB100 | precision rate: 0.811 -> 0.894 | Improved |
| add patch weights to the object representation (ablation) | WPG · OTB100 | success rate: 0.597 -> 0.632 | Improved |
| add learned graph affinity matrix A (ablation) | WPG · OTB100 | precision rate: 0.870 -> 0.894 | Improved |
| add learned graph affinity matrix A (ablation) | WPG · OTB100 | success rate: 0.610 -> 0.632 | Improved |
| add sparse constraint on Z (ablation) | WPG · OTB100 | precision rate: 0.882 -> 0.894 | Improved |
| add sparse constraint on Z (ablation) | WPG · OTB100 | success rate: 0.626 -> 0.632 | Improved |
| add sample-specific sparse constraint on E (ablation) | WPG · OTB100 | precision rate: 0.873 -> 0.894 | Improved |
| add sample-specific sparse constraint on E (ablation) | WPG · OTB100 | success rate: 0.612 -> 0.632 | Improved |
| use non-negligible gamma instead of 1e-10 (ablation) | WPG · OTB100 | precision rate: 0.861 -> 0.894 | Improved |
| use non-negligible alpha instead of 1e-10 (ablation) | WPG · OTB100 | precision rate: 0.883 -> 0.894 | Improved |
| use non-negligible beta instead of 1e-10 (ablation) | WPG · OTB100 | precision rate: 0.878 -> 0.894 | Improved |
| use WPG dynamic graph instead of SOWP spatial-neighbor weights | patch-weight tracker · OTB100 | precision rate: 0.803 -> 0.894 | Improved |
Closest papers by meaning
- Learning Patch-Based Dynamic Graph for Visual Tracking (AAAI 2017 · similarity 0.98)
- Discriminative and Efficient Label Propagation on Complementary Graphs for Multi-Object Tracking (TPAMI 2016 · similarity 0.89)
- Unifying Short and Long-Term Tracking With Graph Hierarchies (CVPR 2023 · similarity 0.88)
- Struck: Structured Output Tracking with Kernels (TPAMI 2016 · similarity 0.87)
- Tracking by 3D Model Estimation of Unknown Objects in Videos (ICCV 2023 · similarity 0.87)
- Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking (AAAI 2024 · similarity 0.86)
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.
