Research map / Detection and segmentation / Tracking
Deep Attentive Tracking via Reciprocative Learning
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 reciprocative attention regularization to the classifier (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.944 | Helped |
| add reciprocative attention regularization to the classifier (ablation) | MDNet baseline · OTB-2013 | OS: 0.671 -> 0.704 | Helped |
| set attention regularization weight λ to 1 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.917 | Helped |
| set attention regularization weight λ to 2 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.936 | Helped |
| set attention regularization weight λ to 3 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.941 | Helped |
| set attention regularization weight λ to 4 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.940 | Helped |
| set attention regularization weight λ to 5 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.944 | Helped |
| set attention regularization weight λ to 6 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.938 | Helped |
| set attention regularization weight λ to 7 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.929 | Helped |
| set attention regularization weight λ to 8 rather than 0 (ablation) | MDNet baseline · OTB-2013 | DP: 0.911 -> 0.911 | No clear effect |
| set attention regularization weight λ to 1 rather than 0 (ablation) | MDNet baseline · OTB-2013 | OS: 0.671 -> 0.688 | Helped |
| set attention regularization weight λ to 2 rather than 0 (ablation) | MDNet baseline · OTB-2013 | OS: 0.671 -> 0.694 | Helped |
Closest papers by meaning
- Visual Tracking Using Attention-Modulated Disintegration and Integration (CVPR 2016 · similarity 0.88)
- Hierarchical Attentive Recurrent Tracking (NeurIPS 2017 · similarity 0.87)
- Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking (CVPR 2018 · similarity 0.86)
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.86)
- Recurrently Target-Attending Tracking (CVPR 2016 · similarity 0.86)
- Tracking objects that change in appearance with phase synchrony (ICLR 2025 · 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.