Research map / Detection and segmentation / Tracking
Robust Visual Tracking Using Oblique Random Forests
Le Zhang, Jagannadan Varadarajan, Ponnuthurai Nagaratnam Suganthan, Narendra Ahuja, Pierre Moulin
Check 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 |
|---|---|---|---|
| use oblique rather than orthogonal splits (ablation) | Obli-RaF · OTB-51 overall | precision (20 pixels): 67.4 -> 80.0 | Improved |
| use oblique rather than orthogonal splits (ablation) | Obli-RaF · OTB-51 overall | success rate (AUC): 48.1 -> 58.0 | Improved |
| add Obli-RaF as a discriminative component to the ConvNet tracker | FCNT · OTB-51 OPE | precision (20 pixels): 0.864 -> 0.919 | Improved |
| add Obli-RaF as a discriminative component to the ConvNet tracker | FCNT · OTB-51 OPE | success rate (AUC): 0.606 -> 0.615 | Improved |
| add Obli-RaF as a discriminative component to the ConvNet tracker | FCNT · OTB-100 OPE | precision (20 pixels): 0.798 -> 0.851 | Improved |
| combine the ConvNet tracker with Obli-RaF | FCNT · OTB-100 OPE | success rate (AUC): 0.555 -> 0.565 | Hurt |
Closest papers by meaning
- ATOM: Accurate Tracking by Overlap Maximization (CVPR 2019 · similarity 0.86)
- Pushing the Envelope of Gradient Boosting Forests via Globally-Optimized Oblique Trees (CVPR 2022 · similarity 0.85)
- Probabilistic Regression for Visual Tracking (CVPR 2020 · similarity 0.85)
- Model Uncertainty Guides Visual Object Tracking (AAAI 2021 · similarity 0.85)
- Struck: Structured Output Tracking with Kernels (TPAMI 2016 · similarity 0.85)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.83)
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.
