Research map / Architectures and efficiency / CNN design
Attentional Correlation Filter Network for Adaptive 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 |
|---|---|---|---|
| Add adaptive attention-based module selection to the correlation filter network (ablation) | ACFN · CVPR2013 | precision: 81.3% -> 86.0% | Helped |
| Add adaptive attention-based module selection to the correlation filter network (ablation) | ACFN · CVPR2013 | mean FPS: 6.9 -> 15.0 | Helped |
| Add the selection sub-network that chooses modules using predicted scores and estimated prediction errors (ablation) | CFN+predNet · CVPR2013 | precision: 82.3% -> 86.0% | Helped |
| Select modules according to dynamic changes rather than using simple/random selection (ablation) | Correlation filter network · CVPR2013 | precision: 79.4% -> 86.0% | Helped |
| Use a large variety of modules instead of a fixed subset of frequently selected modules (ablation) | Correlation filter network · CVPR2013 | precision: 78.4% -> 81.3% | Helped |
| Add adaptive module selection | ACFN · TPAMI2015 | precision at 20 pixels: 0.773 -> 0.802 | Helped |
| Add adaptive module selection | ACFN · VOT2014 | precision at 20 pixels: 0.604 -> 0.666 | Helped |
Closest papers by meaning
- Visual Tracking Using Attention-Modulated Disintegration and Integration (CVPR 2016 · similarity 0.90)
- Correlation-Aware Deep Tracking (CVPR 2022 · similarity 0.90)
- Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking (CVPR 2018 · similarity 0.90)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.88)
- Target-Aware Tracking with Long-Term Context Attention (AAAI 2023 · similarity 0.88)
- Recurrently Target-Attending Tracking (CVPR 2016 · similarity 0.88)
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.