Research map / Detection and segmentation / Tracking
Distractor-aware Siamese Networks for Visual Object Tracking
Zheng Zhu, Qiang Wang, Bo Li, Wei Wu, Junjie Yan, Weiming Hu
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 positive pairs from detection datasets (ImageNet Det, COCO) (ablation) | SiamRPN · VOT2016 | EAO: 0.344 -> 0.368 | Improved |
| add semantic negative pairs in training (ablation) | SiamRPN with detection data · VOT2016 | EAO: 0.368 -> 0.389 | Improved |
| add distractor-aware updating at inference (ablation) | SiamRPN with detection data and negatives · VOT2016 | EAO: 0.389 -> 0.411 | Improved |
| add positive pairs from detection datasets (ablation) | SiamRPN · UAV20L | AUC: 45.4 -> 47.2 | Improved |
| add semantic negative pairs in training (ablation) | SiamRPN with detection data · UAV20L | AUC: 47.2 -> 48.6 | Improved |
| add distractor-aware updating (ablation) | SiamRPN with detection and negatives · UAV20L | AUC: 48.6 -> 49.8 | Improved |
| add local-to-global long-term tracking module (ablation) | DaSiamRPN · UAV20L | AUC: 49.8 -> 61.7 | Improved |
| add all DaSiamRPN components to SiamRPN | SiamRPN · VOT2016 | EAO: 0.344 -> 0.411 | Improved |
| add distractor-aware design to SiamRPN, accounting for speed | SiamRPN · speed (Titan X) | FPS: 200 -> 160 | Hurt |
| add distractor-aware design to SiamRPN | SiamRPN · OTB2015 | DP (%): 85.0 -> 88.0 | Improved |
Closest papers by meaning
- Learning To Filter: Siamese Relation Network for Robust Tracking (CVPR 2021 · similarity 0.92)
- Discriminative and Robust Online Learning for Siamese Visual Tracking (AAAI 2020 · similarity 0.92)
- SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks (CVPR 2019 · similarity 0.92)
- SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking (CVPR 2020 · similarity 0.91)
- Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks (IJCV 2022 · similarity 0.91)
- Deformable Siamese Attention Networks for Visual Object Tracking (CVPR 2020 · similarity 0.91)
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.
