Research map / Detection and segmentation / Tracking
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters
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 adaptive spatial regularization (ablation) | Baseline tracker · OTB2015 | success: 0.620 -> 0.665 | Helped |
| Use multi-scale shallow features for scale estimation (ablation) | Baseline tracker · OTB2015 | success: 0.620 -> 0.659 | Helped |
| Add adaptive spatial regularization and multi-scale shallow-feature scale estimation (ablation) | Baseline tracker · OTB2015 | success: 0.620 -> 0.692 | Helped |
| Replace adaptive spatial regularization with the BACF constraint (ablation) | ASRCF · OTB2015 | success: 0.692 -> 0.663 | Hurt |
| Replace adaptive spatial regularization with the SRDCF constraint (ablation) | ASRCF · OTB2015 | success: 0.692 -> 0.639 | Hurt |
| Replace adaptive spatial regularization with the KCF constraint (ablation) | ASRCF · OTB2015 | success: 0.692 -> 0.555 | Hurt |
| Use ASRCF rather than ECO | Visual tracking · TC128 | success: 0.597 -> 0.603 | Helped |
| Use ASRCF rather than ECO | Visual tracking · OTB2015 | success: 0.687 -> 0.692 | Helped |
| Use ASRCF rather than LSART | Visual tracking · OTB2015 | precision: 0.923 -> 0.922 | Hurt |
| Use ASRCF rather than C-COT | Visual tracking · VOT2016 | EAO: 0.331 -> 0.391 | Helped |
| Use ASRCF rather than LSART | Visual tracking · VOT2017 | EAO: 0.323 -> 0.328 | Helped |
| Use ASRCF rather than MDNet | Visual tracking · LaSOT | success: 0.413 -> 0.359 | Hurt |
Closest papers by meaning
- Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking (CVPR 2018 · similarity 0.93)
- Robust Visual Tracking via Local-Global Correlation Filter (AAAI 2017 · similarity 0.89)
- Structural Correlation Filter for Robust Visual Tracking (CVPR 2016 · similarity 0.89)
- Context-Aware Correlation Filter Tracking (CVPR 2017 · similarity 0.88)
- Robust Estimation of Similarity Transformation for Visual Object Tracking (AAAI 2019 · similarity 0.88)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 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.