Research map / Detection and segmentation / Tracking
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Yifu Zhang, Peize Sun, Yi Jiang, Dongdong Yu, Fucheng Weng, Zehuan Yuan, Ping Luo, Wenyu Liu, Xinggang Wang
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 second association of low-score boxes (BYTE) to SORT | SORT · MOT17 val (half) | MOTA: 74.6 -> 76.6 | Improved |
| add low-score association to SORT | SORT · MOT17 val (half) | IDs: 291 -> 159 | Improved |
| use IoU instead of Re-ID as similarity in second association (ablation) | BYTE · MOT17 val (half) | MOTA: 75.8 -> 76.6 | Improved |
| use Re-ID instead of IoU in first association on BDD100K (ablation) | BYTE · BDD100K val | mMOTA: 39.4 -> 45.5 | Improved |
| use Re-ID in first association instead of IoU (ablation) | BYTE · MOT17 val (half) | MOTA / IDF1: MOTA 76.6 -> 76.3, IDF1 79.3 -> 80.5 | Mixed |
| apply BYTE (Kalman) to CenterTrack | CenterTrack · MOT17 val (half) | IDF1: 64.2 -> 74.0 | Improved |
| apply BYTE to Chained-Tracker | CTracker · MOT17 val (half) | IDF1: 60.9 -> 66.7 | Improved |
| insert BYTE into original association of MOTR | MOTR · MOT17 val (half) | MOTA / IDF1: MOTA 64.7 -> 64.3, IDF1 67.2 -> 69.3 | Mixed |
| replace TraDes association with BYTE (Kalman only) | TraDes · MOT17 val (half) | MOTA / IDF1: MOTA 68.2 -> 67.9, IDF1 71.7 -> 72.0 | No clear effect |
| insert BYTE into FairMOT association | FairMOT · MOT17 val (half) | MOTA: 69.1 -> 70.4 | Improved |
| replace DeepSORT with BYTE on YOLOX-Nano | YOLOX-Nano detector · MOT17 val (half) | MOTA: 61.4 -> 64.4 | Improved |
| add tracklet interpolation (sigma 20) (ablation) | ByteTrack · MOT17 val (half) | MOTA: 76.6 -> 78.3 | Improved |
Later papers that compared with this method
38 later accepted papers report ByteTrack as a baseline in their results tables; 36 of them report a better number on most of the results they share with it.
- An HMM-Based Framework for Identity-Aware Long-Term Multi-Object Tracking From Sparse and Uncertain Identification: Use Case on Long-Term Tracking in Livestock (IJCV 2026 · better on 5 of 6 shared results)
- Mode-Conditioned Residual Calibration for Multi-Object Tracking (ECCV 2026 · better on 4 of 4 shared results)
- Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos (AAAI 2026 · better on 3 of 3 shared results)
- SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation (AAAI 2026 · better on 2 of 2 shared results)
- When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking (AAAI 2026 · better on 2 of 2 shared results)
- SOVTrack: Open-Vocabulary Multi-Object Tracking with Self-Supervised Pseudo Labeling and Feature Distillation (ECCV 2026 · better on 2 of 2 shared results)
- SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors (ECCV 2026 · better on 2 of 2 shared results)
- UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking (ICLR 2026 · better on 1 of 1 shared result)
30 more not listed.
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 0.90)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.89)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.89)
- UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation (AAAI 2024 · similarity 0.88)
- More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions (ICML 2025 · similarity 0.88)
- Sampling-Resilient Multi-Object Tracking (AAAI 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.
