Research map / Detection and segmentation / Tracking
SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation
Xiao Wang, Chenglong Li, Bin Luo, Jin Tang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 PSGN-generated diverse positive samples (ablation) | SINT · OTB-100 | precision | Improved |
| Add PSGN-generated diverse positive samples (ablation) | SINT · OTB-100 | success | Improved |
| Add HPTN-generated hard occluded samples to PSGN-generated training data (ablation) | SINT · OTB-100 | precision: 0.754 -> 0.768 | Improved |
| Add HPTN-generated hard occluded samples to PSGN-generated training data (ablation) | SINT · OTB-100 | success: 0.558 -> 0.574 | Improved |
| Choose occlusion regions randomly instead of using HPTN (ablation) | SINT with PSGN samples · OTB-100 | tracking performance | Hurt |
| Use adversarial-network-generated hard samples instead of SINT++ samples (ablation) | SINT · OTB-50 | precision: 83.7 vs 83.9 | Hurt |
| Use adversarial-network-generated hard samples instead of SINT++ samples (ablation) | SINT · OTB-100 | precision: 76.0 vs 76.8 | Hurt |
Later papers that compared with this method
3 later accepted papers report SINT as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Deep Meta Learning for Real-Time Target-Aware Visual Tracking (ICCV 2019 · better on 1 of 2 shared results)
- Long-term Tracking in the Wild: a Benchmark (ECCV 2018 · better on 3 of 3 shared results)
- Deep Reinforcement Learning with Iterative Shift for Visual Tracking (ECCV 2018 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- VITAL: VIsual Tracking via Adversarial Learning (CVPR 2018 · similarity 0.88)
- Ranking-Based Siamese Visual Tracking (CVPR 2022 · similarity 0.87)
- Efficient Adversarial Attacks for Visual Object Tracking (ECCV 2020 · similarity 0.87)
- Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking (CVPR 2021 · similarity 0.87)
- Unsupervised Deep Representation Learning for Real-Time Tracking (IJCV 2020 · similarity 0.87)
- Learning To Adversarially Blur Visual Object Tracking (ICCV 2021 · similarity 0.87)
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.
