Research map / Detection and segmentation / Tracking
Multiple Planar Object Tracking
Zhicheng Zhang, Shengzhe Liu, Jufeng 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 occlusion reasoning module (occlusion localization plus two-stream attention) (ablation) | PRTrack · MPOT-3K val | success rate S0.8: 75.82 -> 80.44 | Improved |
| add shifted sampling vertex encoder (ablation) | PRTrack · MPOT-3K val | success rate S0.8: 76.38 -> 80.58 | Improved |
| add memory pool reuse gate (ablation) | PRTrack · MPOT-3K val | success rate S0.8: 80.44 -> 80.58 | Improved |
| add factorized homography (ablation) | PRTrack · MPOT-3K val | success rate S0.8: 79.24 -> 80.58 | Improved |
| use occlusion-indicator fusion instead of concatenation or attention-only fusion (ablation) | PRTrack · MPOT-3K val | success rate S0.8: 77.53 / 78.99 -> 80.58 | Improved |
| use PRTrack over best prior tracker HDN | planar object tracking · MPOT-3K test, overall | success rate S0.8: 76.40 -> 82.51 | Improved |
| use PRTrack versus Gracker on tracking distance in moving-objects scenes | planar object tracking · MPOT-3K test, moving objects | tracking distance D: 04.11 (Gracker) vs 05.46 | Hurt |
| use deep-learning planar trackers instead of generic object trackers | MPOT-3K baselines · MPOT-3K test | success rate S0.8 | Improved |
| apply PRTrack without fine-tuning to single planar object datasets | PRTrack · POT210 and POT280 | precision | No clear effect |
Closest papers by meaning
- PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking (ICCV 2023 · similarity 0.89)
- LaSOT: A High-quality Large-scale Single Object Tracking Benchmark (IJCV 2020 · similarity 0.88)
- Learning To Track With Object Permanence (ICCV 2021 · similarity 0.87)
- GMOT-40: A Benchmark for Generic Multiple Object Tracking (CVPR 2021 · similarity 0.87)
- M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking (AAAI 2024 · similarity 0.87)
- MITracker: Multi-View Integration for Visual Object Tracking (CVPR 2025 · 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.
