Research map / Detection and segmentation / Tracking
Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking
ShiJie Sun, Naveed Akhtar, XiangYu Song, HuanSheng Song, Ajmal Mian, Mubarak Shah
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 |
|---|---|---|---|
| augment UA-DETRAC training set with 8 Omni-MOT videos (DMM-Net+) | DMM-Net · UA-DETRAC | PR-MOTA: 11.80% -> 12.20% | Improved |
| augment UA-DETRAC training set with 8 Omni-MOT videos | DMM-Net · UA-DETRAC | PR-ML: 15.20% -> 14.90% | Improved |
| augment UA-DETRAC training set with 8 Omni-MOT videos | DMM-Net · UA-DETRAC | PR-MT: 10.30% -> 10.80% | Improved |
| augment UA-DETRAC training set with 8 Omni-MOT videos | DMM-Net · UA-DETRAC | PR-IDS: 230.3 -> 228.2 | Improved |
| use joint detector-free tracking (DMM-Net) instead of tracking-by-detection with off-the-shelf detectors | MOT on UA-DETRAC · UA-DETRAC | overall speed (fps): 0.67 -> 123.25 | Improved |
| replace best baseline DCT + R-CNN with detector-free DMM-Net | MOT on UA-DETRAC · UA-DETRAC | PR-MOTA: 11.70% -> 11.80% | Improved |
| harder camera views (Camera_5 and Camera_8) versus easy ones (Camera_7) | DMM-Net · Omni-MOT test | MOTA: 80.9% -> 20.4% | Hurt |
Closest papers by meaning
- Deep Affinity Network for Multiple Object Tracking (TPAMI 2019 · similarity 0.91)
- MOTS: Multi-Object Tracking and Segmentation (CVPR 2019 · similarity 0.89)
- OVTrack: Open-Vocabulary Multiple Object Tracking (CVPR 2023 · similarity 0.88)
- More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions (ICML 2025 · similarity 0.87)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.87)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · 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.
