Research map / Detection and segmentation / Tracking
GMOT-40: A Benchmark for Generic Multiple Object Tracking
Hexin Bai, Wensheng Cheng, Peng Chu, Juehuan Liu, Kai Zhang, Haibin Ling
Check 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 |
|---|---|---|---|
| Replace one-shot detector detections with groundtruth detections (ablation) | DeepSORT · GMOT-40 | MOTA: 14.50% -> 80.60% | Improved |
| Replace one-shot detector detections with groundtruth detections (ablation) | DeepSORT · GMOT-40 | IDF1: 24.40% -> 79.30% | Improved |
| Replace one-shot detector detections with groundtruth detections (ablation) | IOU tracker · GMOT-40 | MOTA: 11.80% -> 75.90% | Improved |
| Replace one-shot detector detections with groundtruth detections (ablation) | IOU tracker · GMOT-40 | IDF1: 20.30% -> 79.00% | Improved |
| Replace one-shot detector detections with groundtruth detections (ablation) | MDP · GMOT-40 | MOTA: 19.80% -> 75.00% | Improved |
| Replace one-shot detector detections with groundtruth detections (ablation) | MDP · GMOT-40 | IDF1: 31.30% -> 72.50% | Improved |
| Replace one-shot detector detections with groundtruth detections (ablation) | FAMNet · GMOT-40 | MOTA: 18.00% -> 67.40% | Improved |
| Replace one-shot detector detections with groundtruth detections (ablation) | FAMNet · GMOT-40 | IDF1: 28.30% -> 70.50% | Improved |
| Use IOU-based association rather than appearance-dependent association | GMOT-40 association ablation · GMOT-40 | IDF1: DeepSORT 79.30%; IOU 79.00% | Mixed |
| Adapt GlobalTrack as a one-shot target candidate detector | GMOT-40 one-shot detection · GMOT-40 | AP50: 15.65% | Hurt |
Closest papers by meaning
- MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (IJCV 2020 · similarity 0.91)
- LaSOT: A High-quality Large-scale Single Object Tracking Benchmark (IJCV 2020 · similarity 0.90)
- Beyond MOT: Semantic Multi-Object Tracking (ECCV 2024 · similarity 0.89)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.88)
- Towards Generalizable Multi-Object Tracking (CVPR 2024 · similarity 0.88)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · similarity 0.88)
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.
