Research map / Detection and segmentation / Tracking
Global Tracking via Ensemble of Local Trackers
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ensemble local tracking with temporal context | long-term tracking · TLP | AUC: 0.558 -> 0.570 | Helped |
| use ensemble local tracking with temporal context | long-term tracking · OxUvA testing set | MaxGM: 0.723 -> 0.768 | Helped |
| use ensemble local tracking with temporal context | long-term tracking · VOT2020-LT | F-score: 0.709 -> 0.693 | Hurt |
| use ensemble local tracking with temporal context | long-term tracking · LaSOTExtSub | AUC: 0.482 -> 0.450 | Hurt |
| use ensemble local tracking with temporal context | tracking · TrackingNet | AUC: 0.814 -> 0.825 | Helped |
| add temporal context transferring (ablation) | global tracking model · LaSOT | AUC: 0.653 -> 0.677 | Helped |
| use deformable local attention instead of global dense attention (ablation) | global tracking model · LaSOT | AUC: 0.623 -> 0.677 | Helped |
| use multiple deformable local trackers instead of one global tracker (ablation) | global tracking model · LaSOT | AUC: 0.619 -> 0.677 | Helped |
| reduce the ensemble to 5 local trackers (ablation) | Our model · LaSOT | AUC: 0.677 -> 0.670 | Hurt |
| increase the ensemble to 20 local trackers (ablation) | Our model · LaSOT | AUC: 0.677 -> 0.660 | Hurt |
| shorten memory to 1 (ablation) | Our model · LaSOT | AUC: 0.677 -> 0.672 | Hurt |
| shorten memory to 3 (ablation) | Our model · LaSOT | AUC: 0.677 -> 0.675 | Hurt |
Closest papers by meaning
- GlobalTrack: A Simple and Strong Baseline for Long-Term Tracking (AAAI 2020 · similarity 0.92)
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.88)
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels (NeurIPS 2025 · similarity 0.85)
- TGFormer: Transformer with Track Query Group for Multi-Object Tracking (AAAI 2025 · similarity 0.85)
- MambaLCT: Boosting Tracking via Long-term Context State Space Model (AAAI 2025 · similarity 0.85)
- Beyond Accuracy: Tracking more like Human via Visual Search (NeurIPS 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.