Research map / Detection and segmentation / Tracking
Drift-Resilient Temporal Priors for Visual Tracking
Yuqing Huang, Liting Lin, Weijun Zhuang, Zhenyu He, Xin Li
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 learned reliability gate instead of fixed threshold (ablation) | DTPTrack-B224 · LaSOT (ablation, B224) | AUC: 72.0 -> 74.3 | Improved |
| fix initial template confidence at 1.0 rather than gating it (ablation) | DTPTrack-B224 · LaSOT (ablation, B224) | AUC: 73.2 -> 74.3 | Improved |
| add learnable base prior tokens (ablation) | DTPTrack-B224 · LaSOT (ablation, B224) | AUC: 72.7 -> 74.3 | Improved |
| inject dedicated prior tokens instead of concatenating summaries (ablation) | DTPTrack-B224 · LaSOT (ablation, B224) | AUC: 73.4 -> 74.3 | Improved |
| add DTPTrack module to five-frame LoRATv2 backbone (ablation) | Extended LoRATv2 · LaSOT (ablation, B224) | AUC: 73.3 -> 74.3 | Improved |
| learned MLP-modulated priors vs momentum priors (ablation) | DTPTrack-B224 · LaSOT (ablation, B224) | AUC: 73.8 -> 74.3 | Improved |
| learned MLP-modulated priors vs optical-flow priors (ablation) | DTPTrack-B224 · LaSOT (ablation, B224) | AUC: 73.2 -> 74.3 | Improved |
| increase history from 2 to 5 frames (ablation) | DTPTrack-B224 · LaSOT (ablation, B224) | AUC: 72.0 -> 74.3 | Improved |
| plug DTPTrack into OSTrack-256 | OSTrack-256 · LaSOT | AUC: 69.1 -> 70.1 | Improved |
| plug DTPTrack into ODTrack-B | ODTrack-B · LaSOT | AUC: 73.2 -> 73.7 | Improved |
| plug DTPTrack into LoRAT-B224 | LoRAT-B224 · VastTrack | AUC: 38.7 -> 39.1 | Improved |
Closest papers by meaning
- DreamTrack: Dreaming the Future for Multimodal Visual Object Tracking (CVPR 2025 · similarity 0.86)
- ODTrack: Online Dense Temporal Token Learning for Visual Tracking (AAAI 2024 · similarity 0.86)
- Autoregressive Sequential Pretraining for Visual Tracking (CVPR 2025 · similarity 0.86)
- RTracker: Recoverable Tracking via PN Tree Structured Memory (CVPR 2024 · similarity 0.85)
- FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking (CVPR 2024 · similarity 0.85)
- HIPTrack: Visual Tracking with Historical Prompts (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.
