Research map / Detection and segmentation / Tracking
Online Multiple Object Tracking With Cross-Task Synergy
Song Guo, Jingya Wang, Xinchao Wang, Dacheng Tao
Check 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 target attention and distractor attention (ablation) | TADAM · MOT17 train (FRCNN public detections) | MOTA: 65.9 -> 67.0 | Improved |
| add target attention without distractor attention (ablation) | TADAM · MOT17 train (FRCNN public detections) | MOTA: 65.9 -> 66.7 | Improved |
| add distractor attention without target attention (ablation) | TADAM · MOT17 train (FRCNN public detections) | MOTA: 65.9 -> 66.4 | Improved |
| use adaptive weighting for target and distractor attention (ablation) | TADAM · MOT17 train (FRCNN public detections) | MOTA: 66.0 -> 67.0 | Improved |
| use identity-aware memory aggregation instead of previous-frame embeddings alone (ablation) | TADAM · MOT17 train (FRCNN public detections) | MOTA: 66.5 -> 67.0 | Improved |
| use target and distractor attention with memory aggregation | TADAM · MOT17 train, objects with occlusion level >90% | tracked ratio: around 25% tracked ratio against approximately 5% | Improved |
Closest papers by meaning
- Online Multi-Object Tracking with Dual Matching Attention Networks (ECCV 2018 · similarity 0.91)
- Towards Real-Time Multi-Object Tracking (ECCV 2020 · similarity 0.89)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.89)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.88)
- Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking (AAAI 2024 · similarity 0.86)
- More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions (ICML 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.
