Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Probabilistic Regression for Visual Tracking
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 |
|---|---|---|---|
| Replace DiMP50 with PrDiMP50 | DiMP50 · TrackingNet test | Success (AUC): +1.8% in AUC | Helped |
| Replace DiMP50 with PrDiMP50 | DiMP50 · GOT10k test | AO: 2.3% | Helped |
| Use probabilistic regression instead of DiMP regression | DiMP50 · NFS | AUC | Helped |
| Use probabilistic regression instead of DiMP regression | DiMP50 · VOT2018 | EAO | Helped |
| Apply KL-divergence probabilistic regression to both BBR and TCR instead of R-L2 | DiMP-18 · OTB-100-NFS-UAV123 combined | AUC: $1.7\%$ in AUC | Helped |
| Use KL-divergence probabilistic regression for BBR instead of L2, retaining R-L2 for TCR (ablation) | DiMP-18 · OTB-100-NFS-UAV123 combined | AUC: an additional improvement of $0.8\%$ | Helped |
| Use probabilistic NLL for BBR instead of L2, retaining R-L2 for TCR (ablation) | DiMP-18 · OTB-100-NFS-UAV123 combined | AUC: $1.2\%$ gain | Helped |
| Use KL-divergence probabilistic regression for TCR instead of NLL, retaining Ours for BBR (ablation) | DiMP-18 · OTB-100-NFS-UAV123 combined | AUC: $2.3\%$ gain | Helped |
| Use NLL for TCR without modeling label uncertainty (ablation) | DiMP-18 · OTB-100-NFS-UAV123 combined | AUC | Hurt |
| Use R-L2 instead of KL-divergence probabilistic regression for TCR (ablation) | DiMP-18 · OTB-100-NFS-UAV123 combined | AUC: 65.8 vs. 65.5 | Helped |
| Increase label-distribution standard deviation too much (ablation) | PrDiMP · OTB-100-NFS-UAV123 combined | AUC | Hurt |
| Make label-distribution standard deviation too small (ablation) | PrDiMP · OTB-100-NFS-UAV123 combined | AUC | Hurt |
Closest papers by meaning
- UAST: Uncertainty-Aware Siamese Tracking (ICML 2022 · similarity 0.88)
- DeTrack: In-model Latent Denoising Learning for Visual Object Tracking (NeurIPS 2024 · similarity 0.87)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.86)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.86)
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.86)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 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.