Research map / Detection and segmentation / Tracking
Visual Tracking Using Attention-Modulated Disintegration and Integration
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 |
|---|---|---|---|
| use four AtCFs with Gaussian and polynomial kernels but exclude the linear kernel (ablation) | SCT · OOTB, all sequences | precision (20px): 83.6% -> 84.5% | Helped |
| remove attentional weight maps from the six-tracker framework (ablation) | SCT6 · OOTB, all sequences | precision (20px): 79.2% -> 83.6% | Hurt |
| replace PGDT with a general classification decision tree (ablation) | SCT6 · OOTB, all sequences | precision (20px): 79.1% -> 83.6% | Hurt |
| use PGDT instead of a general classification decision tree (ablation) | SCT6 · OOTB, all sequences | mean FPS: 22.90 -> 37.1 | Helped |
| combine multiple AtCF responses using the integration framework (ablation) | SCT · OOTB, all sequences | precision (20px) | Helped |
| weight correlation-filter features with attentional weight maps (ablation) | AtCF · OOTB, all sequences | precision | Helped |
Closest papers by meaning
- Attentional Correlation Filter Network for Adaptive Visual Tracking (CVPR 2017 · similarity 0.90)
- Deep Attentive Tracking via Reciprocative Learning (NeurIPS 2018 · similarity 0.88)
- Transformer Tracking (CVPR 2021 · similarity 0.87)
- Cross-modulated Attention Transformer for RGBT Tracking (AAAI 2025 · similarity 0.86)
- A Distractor-Aware Memory for Visual Object Tracking with SAM2 (CVPR 2025 · similarity 0.84)
- Beyond Accuracy: Tracking more like Human via Visual Search (NeurIPS 2024 · similarity 0.84)
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.