Research map / Detection and segmentation / Tracking
Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking
Read the paperCheck 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 general attention to SiamFC (ablation) | Siamese tracker · OTB-2013 | AUC: +0.4% | Helped |
| Add residual attention to general attention (ablation) | GenAtt · OTB-2013 | AUC: +4.9% | Helped |
| Add channel attention to SiamFC (ablation) | Siamese tracker · OTB-2013 | AUC: almost 4% | Helped |
| Add general, residual, and channel attention (ablation) | SiamFC · OTB-2013 | AUC: +6.3% | Helped |
| Use RASNet instead of CREST | OTB-2015 tracking · OTB-2015 | AUC: +1.9% | Helped |
| Use RASNet instead of SiamFC | OTB-2015 tracking · OTB-2015 | AUC: 6% | Helped |
| Use RASNet instead of CFNet | OTB-2015 tracking · OTB-2015 | AUC: 7.5% | Helped |
Closest papers by meaning
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking (CVPR 2019 · similarity 0.91)
- Deformable Siamese Attention Networks for Visual Object Tracking (CVPR 2020 · similarity 0.91)
- Attentional Correlation Filter Network for Adaptive Visual Tracking (CVPR 2017 · similarity 0.90)
- Discriminative and Robust Online Learning for Siamese Visual Tracking (AAAI 2020 · similarity 0.90)
- Correlation-Aware Deep Tracking (CVPR 2022 · similarity 0.90)
- High Performance Visual Tracking With Siamese Region Proposal Network (CVPR 2018 · similarity 0.89)
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.