Research map / Detection and segmentation / Tracking
Release the Power of Online-Training for Robust 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 sample squeezing with neighbour proximity (ablation) | MDNet · OTB-2013 | AUC: 0.682 -> 0.685 | Helped |
| use Euclid distance for squeezing instead of neighbour proximity (ablation) | MDNet squeezing · OTB-2013 | AUC: 0.685 -> 0.680 | Hurt |
| add data augmentation to initial training (ablation) | MDNet · OTB-2013 | AUC: 0.682 -> 0.660 | Hurt |
| add statistic-based losses without squeezing (ablation) | MDNet · OTB-2013 | AUC: 0.682 -> 0.690 | Helped |
| add squeezing to statistic-based losses (ablation) | MDNet + SLoss · OTB-2013 | AUC: 0.690 -> 0.702 | Helped |
| add intra-class variance loss (ablation) | MDNet + squeezing · OTB-2013 | AUC: 0.685 -> 0.691 | Helped |
| add inter-class distance loss (ablation) | MDNet + squeezing + IV · OTB-2013 | AUC: 0.691 -> 0.702 | Helped |
| apply squeezing and statistic-based losses to DAT (ablation) | DAT · OTB-2013 | AUC: 0.704 -> 0.705 | No clear effect |
| apply squeezing and statistic-based losses to DAT (ablation) | DAT · OTB-2013 | DP: 0.944 -> 0.952 | Helped |
Closest papers by meaning
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.90)
- STCT: Sequentially Training Convolutional Networks for Visual Tracking (CVPR 2016 · similarity 0.90)
- Discriminative and Robust Online Learning for Siamese Visual Tracking (AAAI 2020 · similarity 0.89)
- Target-Aware Deep Tracking (CVPR 2019 · similarity 0.88)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.87)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.86)
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.