Research map / Detection and segmentation / Tracking
Efficient Global MOT Under Minimum-Cost Circulation Framework
Congchao Wang, Yizhi Wang, Guoqiang Yu
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 |
|---|---|---|---|
| replace min-cost flow with min-cost circulation (no search for object number) | global data association · 40 efficiency experiments | running time: 53 times faster than MCF | Improved |
| use CINDA instead of successive shortest path | global data association · 40 efficiency experiments | running time: 1,192 times faster than SSP | Improved |
| use CINDA instead of dynamic SSP | global data association · 40 efficiency experiments | running time: 592 times faster than dSSP | Improved |
| use CINDA instead of best competing method | global data association · 40 efficiency experiments | running time: 29 times faster than the best competing method | Improved |
| use CINDA instead of MCF | global data association · Embryo | running time: 5.8h -> 398.45 | Improved |
| use CINDA instead of SSP/dSSP | global data association · Embryo | running time: >1d -> 398.45 | Improved |
| use CINDA as Frank-Wolfe subroutine instead of MCF | quadratic programming identity inference · PETS09 S1.L1 | running time: 643.1 -> 27.5 | Improved |
| use CINDA instead of SSP | global data association · KITTI(DPM) seq00 affinity (c) | running time: 1.2h -> 0.52 | Improved |
| use CINDA instead of dSSP | global data association · PTC-Low | running time: 40.4 -> 0.05 | Improved |
| use CINDA instead of MCF | global data association · CVPR19 seq06 affinity (a) | running time: 799.2 -> 22.9 | Improved |
| use CINDA instead of MCF | global data association · KITTI(DPM) seq00 affinity (a) | running time: 11.8 -> 0.26 | Improved |
| longer history for identity inference enabled by fast solver | car tracking · KITTI-Car | MOT accuracy | Improved |
Closest papers by meaning
- muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking (NeurIPS 2019 · similarity 0.90)
- Learning of Global Objective for Network Flow in Multi-Object Tracking (CVPR 2022 · similarity 0.88)
- DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking (CVPR 2024 · similarity 0.87)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.87)
- Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking (AAAI 2024 · similarity 0.86)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.86)
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.
