Research map / Detection and segmentation / Tracking
Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
Check 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 |
|---|---|---|---|
| Use interactions between tracklets instead of treating them independently (ablation) | ArTIST-C · MOT17 validation | IDF1: 62.0 -> 66.5 | Helped |
| Use interactions between tracklets instead of treating them independently (ablation) | ArTIST-C · MOT17 validation | IDs: 293 -> 231 | Helped |
| Add tracklet inpainting (ablation) | ArTIST-C · MOT17 validation | IDF1: 60.7 -> 66.5 | Helped |
| Add inpainted boxes to evaluation (ablation) | ArTIST-C with inpainting · MOT17 validation | FN: 22,004 -> 19,769 | Helped |
| Use multinomial sampling instead of greedy top-1 continuation (ablation) | ArTIST-C inpainting · MOT17 validation | IDF1: 62.5 -> 64.9 | Helped |
| Add tracklet rejection strategy to multinomial sampling (ablation) | ArTIST-C inpainting · MOT17 validation | IDF1: 64.9 -> 66.5 | Helped |
| Use a stochastic multi-modal motion model instead of no motion model (ablation) | ArTIST-C · MOT17 validation | IDF1: 60.7 -> 66.5 | Helped |
| Use a stochastic multi-modal motion model instead of a Kalman Filter (ablation) | ArTIST-C · MOT17 validation | IDF1: 61.9 -> 66.5 | Helped |
| Use a stochastic multi-modal motion model instead of deterministic CenterTrack offsets (ablation) | ArTIST-C · MOT17 validation | IDF1: 60.6 -> 66.5 | Helped |
| Refine public detection bounding boxes (ablation) | ArTIST-C · MOT17 validation | IDF1: 57.0 -> 66.5 | Helped |
Closest papers by meaning
- More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions (ICML 2025 · similarity 0.90)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.89)
- Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking (ICLR 2025 · similarity 0.88)
- Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking (AAAI 2024 · similarity 0.88)
- S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking (ICML 2025 · similarity 0.88)
- TGFormer: Transformer with Track Query Group for Multi-Object Tracking (AAAI 2025 · 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.