Research map / Detection and segmentation / Tracking
Large Margin Object Tracking With Circulant Feature Maps
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 |
|---|---|---|---|
| add multimodal target detection (ablation) | LMCF · OTB-13 OPE | precision: 0.809 -> 0.839 | Helped |
| add multimodal target detection (ablation) | LMCF · OTB-13 OPE | success: 0.606 -> 0.624 | Helped |
| add multimodal target detection (ablation) | LMCF · OTB-13 TRE | precision: 0.815 -> 0.829 | Helped |
| add multimodal target detection (ablation) | LMCF · OTB-13 SRE | success: 0.549 -> 0.552 | Helped |
| add high-confidence update (ablation) | LMCF · OTB-13 OPE | precision: 0.813 -> 0.839 | Helped |
| add high-confidence update (ablation) | LMCF · OTB-13 OPE | success: 0.605 -> 0.624 | Helped |
| add high-confidence update (ablation) | LMCF · OTB-13 | mean FPS: 46.45 -> 85.23 | Helped |
| add multimodal detection and high-confidence update (ablation) | LMCF · OTB-13 OPE | precision: 0.799 -> 0.839 | Helped |
| use deep CNN features instead of conventional features (ablation) | LMCF · OTB-13 OPE | precision: 0.839 -> 0.892 | Helped |
| use deep CNN features instead of conventional features (ablation) | LMCF · OTB-13 | mean FPS: 85.23 -> 8.11 | Hurt |
| use LMCF rather than Struck | object tracking on OTB-13 and OTB-15 · OTB-13 and OTB-15 | average AUC: +15% | Helped |
| use multimodal detection and confidence-gated updating (ablation) | LMCF · OTB-13 | tracking performance | Helped |
Closest papers by meaning
- Object Tracking via Dual Linear Structured SVM and Explicit Feature Map (CVPR 2016 · similarity 0.87)
- Learning Spatial-Aware Regressions for Visual Tracking (CVPR 2018 · similarity 0.84)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.83)
- MVLM: Template-Free Tracking via Vision-Language Margin Confidence and Memory-Gated Tracking (CVPR 2026 · similarity 0.82)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.82)
- DeTrack: In-model Latent Denoising Learning for Visual Object Tracking (NeurIPS 2024 · similarity 0.82)
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.