Research map / Learning theory and algorithms / Combinatorial and search optimization
Lifted Disjoint Paths with Application in Multiple Object Tracking
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 lifted long-range edges and optimize lifted disjoint paths | MOT17 tracking · MOT17 | MOTA: 53.5 to 60.5 | Helped |
| Add lifted long-range edges and optimize lifted disjoint paths | MOT17 tracking · MOT17 | IDF1: 52.3 to 65.6 | Helped |
| Increase the maximum edge time gap from 0.3s to 2s (ablation) | Lif_T assignment · MOT17 train | IDF1: 55.7 -> 64.3 | Helped |
| Increase the maximum edge time gap from 0.3s to 2s (ablation) | Lif_T assignment · MOT17 train | MOTA: 52.6 -> 52.8 | No clear effect |
| Add spatial interpolation on static-camera sequences (ablation) | MOT17 train Assignment · MOT17 train | MOTA: 52.8 -> 57.8 | Helped |
| Apply spatial interpolation to all sequences (ablation) | MOT17 train Assignment · MOT17 train | MOTA: 52.8 -> 59.5 | Helped |
| Apply spatial interpolation to moving-camera sequences (ablation) | MOT17 tracking · moving-camera sequences | tracking quality | Hurt |
| Add visual interpolation (ablation) | MOT17 train Assignment · MOT17 train | MOTA: 52.8 -> 59.6 | Helped |
| Add visual interpolation, visual extrapolation, and spatial interpolation (ablation) | MOT17 train Assignment · MOT17 train | MOTA: 52.8 -> 67.0 | Helped |
Closest papers by meaning
- Self-Supervised Multi-Object Tracking with Path Consistency (CVPR 2024 · similarity 0.84)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.84)
- Towards Generalizable Multi-Object Tracking (CVPR 2024 · similarity 0.84)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.83)
- ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association (CVPR 2024 · similarity 0.83)
- S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking (ICML 2025 · similarity 0.83)
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.