Research map / Detection and segmentation / Tracking
Robust Multi-Object Tracking by Marginal Inference
Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu
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 Kalman filter motion cue to appearance matching (ablation) | MTracker · MOT17 train | IDF1: 71.9 -> 73.6 | Improved |
| add IoU matching after appearance and Kalman (ablation) | MTracker · MOT17 train | IDF1: 73.6 -> 74.8 | Improved |
| add IoU matching (ablation) | MTracker · MOT17 train | ID switches: 777 -> 499 | Improved |
| add marginal probability matching (ablation) | MTracker · MOT17 train | IDF1: 74.8 -> 75.7 | Improved |
| add marginal probability matching (ablation) | MTracker · MOT17 train | ID switches: 499 -> 449 | Improved |
| replace feature distance with marginal probability (FairMOT det and ReID) | MTracker · MOT17 train | IDF1: 58.0 -> 58.2 | Improved |
| replace feature distance with marginal probability (Scaled-YOLOv4 det, FairMOT ReID) | MTracker · MOT17 train | IDF1: 72.5 -> 73.6 | Improved |
| replace feature distance with marginal probability | MTracker · MOT20 train (FairMOT) | IDF1: 45.9 -> 46.7 | Improved |
| replace feature distance with marginal probability | MTracker · MOT17 train | MOTA: 71.5 -> 71.6 | No clear effect |
| use marginal inference instead of softmax probability | MTracker · MOT17 train | IDF1: 73.7 -> 75.7 | Improved |
| use marginal inference instead of bi-directional softmax | MTracker · MOT17 train | IDF1: 74.7 -> 75.7 | Improved |
| use marginal inference instead of bi-directional softmax | MTracker · MOT17 train | ID switches: 405 -> 449 | 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.
- FairMOT — FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (IJCV 2021) · better on 2 of 2 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
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.86)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.86)
- UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation (AAAI 2024 · similarity 0.86)
- Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking (AAAI 2024 · similarity 0.86)
- Self-Supervised Multi-Object Tracking with Path Consistency (CVPR 2024 · similarity 0.85)
- Sampling-Resilient Multi-Object Tracking (AAAI 2024 · similarity 0.85)
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.
