Research map / Detection and segmentation / Tracking
Robust Object Tracking Based on Temporal and Spatial Deep Networks
Zhu Teng, Junliang Xing, Qiang Wang, Congyan Lang, Songhe Feng, Yi Jin
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 Temporal Net (ablation) | TSN tracker · VOT2014 | EAO: 0.26 -> 0.32 | Improved |
| add Temporal Net (ablation) | TSN tracker · VOT2014 | robustness (Rav, lower better): 1.36 -> 0.75 | Improved |
| add Spatial Net (ablation) | TSN tracker · VOT2014 | robustness (Rav, lower better): 1.35 -> 0.75 | Improved |
| add Spatial Net (ablation) | TSN tracker · VOT2014 | EAO: 0.30 -> 0.32 | Improved |
| add Spatial Net (ablation) | TSN tracker · VOT2014 | accuracy (Aav): 0.61 -> 0.64 | Improved |
| use L1 loss instead of L2 loss in Temporal Net (ablation) | TSN tracker · VOT2014 | EAO: 0.29 -> 0.32 | Improved |
| use L1 loss instead of L2 loss in Temporal Net (ablation) | TSN tracker · VOT2014 | accuracy (Aav): 0.62 -> 0.64 | No clear effect |
| use L1 loss instead of L2 loss in Temporal Net (ablation) | TSN tracker · VOT2014 | robustness (Rav, lower better): 1.07 -> 0.75 | Improved |
| compare TSN (no tracking pre-training) with MDNet pre-trained on tracking videos | TSN · OTB100 | AP: 0.909 -> 0.868 | Hurt |
| compare TSN with DeepSRDCF | TSN · OTB100 | AP: 0.851 -> 0.868 | Improved |
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 1 of 1 shared result
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
- Robust Visual Tracking via Hierarchical Convolutional Features (TPAMI 2018 · similarity 0.91)
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.91)
- Target-Aware Deep Tracking (CVPR 2019 · similarity 0.89)
- Object Tracking using Spatio-Temporal Networks for Future Prediction Location (ECCV 2020 · similarity 0.89)
- Release the Power of Online-Training for Robust Visual Tracking (AAAI 2020 · similarity 0.89)
- Learning Spatial-Aware Regressions for Visual Tracking (CVPR 2018 · similarity 0.89)
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.
