Research map / Detection and segmentation / Tracking
VITAL: VIsual Tracking via Adversarial Learning
Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, Wangmeng Zuo, Chunhua Shen, Rynson W.H. Lau, Ming-Hsuan Yang
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 random feature masks instead of adversarially learned masks (ablation) | VITAL classifier · OTB-2013 | tracking performance | Hurt |
| add adversarial learning to diversify positive samples (ablation) | baseline tracker · OTB-2013 | tracking performance | Improved |
| add cost-sensitive loss (ablation) | tracker with adversarial learning · OTB-2013 | tracking performance | Improved |
Later papers that compared with this method
4 later accepted papers report VITAL as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Correlation-Guided Attention for Corner Detection Based Visual Tracking (CVPR 2020 · better on 1 of 1 shared result)
- POST: POlicy-Based Switch Tracking (AAAI 2020 · better on 0 of 1 shared result)
- Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking (ICCV 2019 · better on 3 of 4 shared results)
- Graph Convolutional Tracking (CVPR 2019 · better on 0 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Staple — Staple: Complementary Learners for Real-Time Tracking (CVPR 2016) · better on 3 of 3 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
- SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation (CVPR 2018 · similarity 0.88)
- Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking (CVPR 2016 · similarity 0.87)
- Deep Object Tracking with Shrinkage Loss (TPAMI 2020 · similarity 0.87)
- Robust Visual Tracking via Hierarchical Convolutional Features (TPAMI 2018 · similarity 0.86)
- Efficient Adversarial Attacks for Visual Object Tracking (ECCV 2020 · similarity 0.86)
- Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks (ECCV 2024 · 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.
