Research map / Detection and segmentation / Tracking
Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking
Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler
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 channel group selection (keep 5% of channels) to a DCF with deep features (ablation) | DCF with ResNet50 features · OTB2015 | AUC: 55.49% -> 63.07% | Improved |
| add spatial group selection to a DCF with hand-crafted features (ablation) | DCF with CN, IC, HOG · OTB2015 | AUC: selection ratios 5%~40% | Improved |
| add channel group selection to a DCF with hand-crafted features (ablation) | DCF with CN, IC, HOG · OTB2015 | AUC: maintains performance when compressed to 60% | No clear effect |
| add spatial group selection to a DCF with deep features (ablation) | DCF with ResNet50 · OTB2015 | AUC | No clear effect |
| add channel selection term R_C (BaseLine_CS) (ablation) | BaseLine DCF · OTB2013 | DP and AUC: DP by 10.1%, AUC by 10.6% | Improved |
| add spatial selection term R_S (BaseLine_SS) (ablation) | BaseLine DCF · OTB2013 | DP and AUC: DP by 6.1%, AUC by 6.7% | Improved |
| add low-rank temporal smoothness term R_T (BaseLine_LR) (ablation) | BaseLine DCF · OTB2013 | DP and AUC | Improved |
| combine all three terms (BaseLine_ALL = GFS-DCF) (ablation) | BaseLine DCF · OTB2013 | DP and AUC | Improved |
| vary lambda1, lambda2 in [0.01, 100] and lambda3 in [10, 100] (ablation) | GFS-DCF · OTB2015 | DP and AUC: stable for lambda1, lambda2 in [0.01, 100], lambda3 in [10, 100] | No clear effect |
| use GFS-DCF instead of ECO | OTB2015 tracking · OTB2015 | OP/CLE: by 4.1%/4.5 pixels | Improved |
| use GFS-DCF instead of C-COT | OTB2015 tracking · OTB2015 | OP/CLE: by 6.7%/3.7 pixels | 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.
- VITAL — VITAL: VIsual Tracking via Adversarial Learning (CVPR 2018) · better on 3 of 4 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
- Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters (IJCV 2021 · similarity 0.94)
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (ECCV 2016 · similarity 0.91)
- Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook (TPAMI 2022 · similarity 0.91)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.91)
- ECO: Efficient Convolution Operators for Tracking (CVPR 2017 · similarity 0.90)
- Discriminative Correlation Filter Tracker with Channel and Spatial Reliability (IJCV 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.
