Research map / Detection and segmentation / Tracking
Learning Background-Aware Correlation Filters for Visual Tracking
Hamed Kiani Galoogahi, Ashton Fagg, Simon Lucey
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 |
|---|---|---|---|
| learn the filter from real background patches instead of circular shifts (BACF vs SRDCF) | correlation filter, HOG · OTB100 | AUC: 62.98 vs 60.13 | Improved |
| learn from real background patches (BACF vs LCT) | correlation filter, HOG · OTB50 | AUC: 67.78 vs 62.48 | Improved |
| learn from real background patches (BACF vs SRDCF) | correlation filter, HOG · TC128 | AUC: 51.97 vs 51.66 | Improved |
| use BACF instead of SRDCF for speed | correlation filter, HOG · OTB avg (CPU) | FPS: 3.8 -> 35.3 | Improved |
| use BACF with HOG instead of CCOT deep features, average success | correlation filter · OTB avg | success rate (%): 77.8 -> 76.0 | Hurt |
| use BACF instead of CCOT, speed | correlation filter · OTB avg (CPU) | FPS: 0.2 -> 35.3 | Improved |
| use BACF instead of DeepSRDCF, average success | correlation filter · OTB avg | success rate (%): 72.9 -> 76.0 | Improved |
| use BACF instead of HCF, average success | correlation filter · OTB avg | success rate (%): 65.0 -> 76.0 | Improved |
| BACF vs CCOT per-sequence comparison on OTB100 | correlation filter · OTB100 | videos won: 37 videos BACF better, 41 CCOT better, 23 equal | Mixed |
| use BACF instead of SRDCF on VOT2015 accuracy | correlation filter · VOT2015 | accuracy: 0.56 -> 0.59 | Improved |
| use BACF instead of CCOT on VOT2015 robustness | correlation filter · VOT2015 | robustness: 0.82 -> 1.56 | Hurt |
| BACF vs MDNet deep tracker | BACF · OTB success rate | success rate (%): 87.3 -> 85.4 | Hurt |
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 4 of 5 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
- Context-Aware Correlation Filter Tracking (CVPR 2017 · similarity 0.92)
- Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking (IJCV 2018 · similarity 0.90)
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (ECCV 2016 · similarity 0.90)
- Correlation Tracking via Joint Discrimination and Reliability Learning (CVPR 2018 · similarity 0.90)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.89)
- ECO: Efficient Convolution Operators for Tracking (CVPR 2017 · 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.
