Research map / Detection and segmentation / Tracking
Learning Regression and Verification Networks for Robust Long-term Tracking
Yunhua Zhang, Lijun Wang, Dong Wang, Jinqing Qi, Huchuan Lu
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 verification network to regression network (ablation) | regression tracker · VOT2018 LTB35 | F-score: 0.525 -> 0.610 | Improved |
| add concatenation of template feature in fusion (ablation) | object-aware fusion · VOT2018 LTB35 | F-score: 0.582 -> 0.610 | Improved |
| add multiplication of search and template features in fusion (ablation) | object-aware fusion · VOT2018 LTB35 | F-score: 0.442 -> 0.610 | Improved |
| use separate parameters for template and search branches instead of Siamese sharing (ablation) | regression network · VOT2018 LTB35 | F-score: 0.497 -> 0.610 | Improved |
| add verification network (precision) (ablation) | regression tracker · VOT2018 LTB35 | precision: 0.563 -> 0.634 | Improved |
| add verification network (recall) (ablation) | regression tracker · VOT2018 LTB35 | recall: 0.493 -> 0.588 | Improved |
| combine regression and verification scores with image-wide re-detection | DaSiam_LT-style tracker · VOT2018 LTB35 | re-detection success: 0% -> 100% | Improved |
| use fixed regression network plus online verification instead of SiamFC with random re-detection | SiamFC+R · OxUvA | MaxGM: 0.454 -> 0.544 | Improved |
Closest papers by meaning
- Effective Local and Global Search for Fast Long-Term Tracking (TPAMI 2022 · similarity 0.90)
- GlobalTrack: A Simple and Strong Baseline for Long-Term Tracking (AAAI 2020 · similarity 0.88)
- Probabilistic Regression for Visual Tracking (CVPR 2020 · similarity 0.87)
- Robust Object Tracking Based on Temporal and Spatial Deep Networks (ICCV 2017 · similarity 0.87)
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (ECCV 2018 · similarity 0.87)
- High-Performance Long-Term Tracking With Meta-Updater (CVPR 2020 · 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.
