Research map / Detection and segmentation / Tracking
Discriminative and Efficient Label Propagation on Complementary Graphs for Multi-Object Tracking
Amit Kumar K.C., Laurent Jacques, Christophe De Vleeschouwer
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 appearance graphs (ablation) | Node-wise label propagation · TUD Stadtmitte | MOTA: 63.1 -> 79.5 | Improved |
| add appearance graphs (ablation) | Joint label propagation · TUD Stadtmitte | MOTA: 62.7 -> 79.2 | Improved |
| add appearance graphs (ablation) | Node-wise label propagation · TUD Crossing | MOTA: 62.3 -> 65.4 | Improved |
| add appearance graphs (ablation) | Node-wise label propagation · PETS 2009-S2/L1 | MOTA: 83.07 -> 91.04 | Improved |
| add color and digit appearance graphs (ablation) | Node-wise label propagation · APIDIS | MOTA: 81.4 -> 83.85 | Improved |
| add appearance graphs (ablation) | Incremental graph construction · TUD Stadtmitte | MOTA: 61.60 -> 77.20 | Improved |
| add appearance graphs (ablation) | Incremental graph construction · PETS | MOTA: 79.32 -> 86.56 | Improved |
| use node-wise instead of joint label optimization | Label propagation · PETS 2009-S2/L1 | MOTA: 91.04 -> 91.04 | No clear effect |
| use incremental instead of offline graph construction | Label propagation · TUD Stadtmitte | MOTA: 79.5 -> 77.20 | Hurt |
| increase connection window T_c beyond 100 frames (ablation) | Appearance graph · TUD Stadtmitte and PETS | MOTA | Mixed |
| increase observation window T_o beyond 50 frames (ablation) | Incremental label propagation · TUD Stadtmitte | MOTA | No clear effect |
| increase gamma (time scaling) (ablation) | Spatio-temporal graph · TUD Stadtmitte and PETS | MOTA | No clear effect |
Closest papers by meaning
- Learning Patch-Based Dynamic Graph for Visual Tracking (AAAI 2017 · similarity 0.89)
- ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking (ICCV 2023 · similarity 0.89)
- Learnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object Tracking (CVPR 2021 · similarity 0.89)
- Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking (AAAI 2024 · similarity 0.87)
- Self-Supervised Multi-Object Tracking with Path Consistency (CVPR 2024 · similarity 0.87)
- Multiple Object Tracking as ID Prediction (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.
