Research map / Detection and segmentation / Tracking
muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking
Congchao Wang, Yizhi Wang, Yinxue Wang, Chiung-Ting Wu, 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 SSP with muSSP (minimum-update shortest path tree, edge clipping, multi-path flipping, batch Dijkstra) | min-cost flow data association · MOT datasets, 39 experiments | running time: 4193 times faster than SSP on average | Improved |
| use muSSP instead of cs2 as min-cost flow subroutine in Frank-Wolfe QP | PETS S1.L1-2 quadratic programming · PETS S1.L1-2 | running time (s): 613.1 -> 20.3 | Improved |
| use FollowMe instead of SSP on graphs with many objects | baseline solver · CVPR19 seq04 | running time: 1.8h -> 2.4h | Hurt |
Closest papers by meaning
- Efficient Global MOT Under Minimum-Cost Circulation Framework (TPAMI 2020 · similarity 0.90)
- Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths (ICCV 2021 · similarity 0.87)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.86)
- DyGLIP: A Dynamic Graph Model With Link Prediction for Accurate Multi-Camera Multiple Object Tracking (CVPR 2021 · similarity 0.86)
- Learning a Neural Solver for Multiple Object Tracking (CVPR 2020 · similarity 0.86)
- Hybrid-SORT: Weak Cues Matter for Online 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.
