Research map / Detection and segmentation / Tracking
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking
Hamed Kiani Galoogahi, Ashton Fagg, Chen Huang, Deva Ramanan, 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 |
|---|---|---|---|
| divide the learning rate by 8 for 240 FPS video (ablation) | BACF · NfS (240 FPS) | success rate at IoU>0.50 (%): 48.8 -> 60.5 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | SRDCF · NfS (240 FPS) | success rate at IoU>0.50 (%): 48.2 -> 55.8 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | Staple · NfS (240 FPS) | success rate at IoU>0.50 (%): 51.1 -> 53.4 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | LCT · NfS (240 FPS) | success rate at IoU>0.50 (%): 34.5 -> 36.4 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | DSST · NfS (240 FPS) | success rate at IoU>0.50 (%): 44.0 -> 53.4 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | SAMF · NfS (240 FPS) | success rate at IoU>0.50 (%): 42.8 -> 51.7 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | KCF · NfS (240 FPS) | success rate at IoU>0.50 (%): 28.7 -> 34.8 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | CFLB · NfS (240 FPS) | success rate at IoU>0.50 (%): 18.3 -> 22.9 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | HCF · NfS (240 FPS) | success rate at IoU>0.50 (%): 33.0 -> 41.2 | Improved |
| divide the learning rate by 8 for 240 FPS video (ablation) | HDT · NfS (240 FPS) | success rate at IoU>0.50 (%): 57.7 -> 59.6 | Improved |
| track 240 FPS video instead of 30 FPS video with motion blur | BACF · NfS | AUC of success plot: 34.0 -> 49.5 | Improved |
| track 240 FPS video instead of 30 FPS video with motion blur | MDNet · NfS | AUC of success plot: 42.9 -> 47.3 | Improved |
Closest papers by meaning
- Beyond Standard Benchmarks: Parameterizing Performance Evaluation in Visual Object Tracking (ICCV 2017 · similarity 0.91)
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (ECCV 2018 · similarity 0.90)
- Long-term Tracking in the Wild: a Benchmark (ECCV 2018 · similarity 0.89)
- LaSOT: A High-quality Large-scale Single Object Tracking Benchmark (IJCV 2020 · similarity 0.89)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.88)
- A Distractor-Aware Memory for Visual Object Tracking with SAM2 (CVPR 2025 · 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.
