Research map / Detection and segmentation / Tracking
A General Recurrent Tracking Framework Without Real Data
Shuai Wang, Hao Sheng, Yang Zhang, Yubin Wu, Zhang Xiong
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 dummy nodes for missing detections (ablation) | naive MHT baseline · MOT17 train (ablation, Fair detections) | IDF1: 63.1 -> 78.3 | Improved |
| add dummy nodes for missing detections (ablation) | naive MHT baseline · MOT17 train (ablation, Fair detections) | MOTA: 78.4 -> 82.2 | Improved |
| replace manual scoring with RTU classifying correct and false nodes (ablation) | baseline + D · MOT17 train (ablation, Fair detections) | IDF1: 78.3 -> 80.6 | Improved |
| replace manual scoring with RTU classifying correct and false nodes (ablation) | baseline + D · MOT17 train (ablation, Fair detections) | MOTA: 82.2 -> 83.2 | Improved |
| plug RTU into MHT DAM | MHT DAM · MOT17 train (PCB features) | IDF1: 76.2 -> 79.4 | Improved |
| plug RTU into MLT | MLT · MOT17 train (PCB features) | IDF1: 77.8 -> 78.7 | Improved |
| plug RTU into DeepSORT | DeepSORT · MOT17 train (PCB features) | IDF1: 72.5 -> 76.3 | Improved |
| plug RTU into MHT DAM | MHT DAM · MOT17 train (Fair features) | IDF1: 79.4 -> 79.6 | Improved |
| plug RTU into MLT | MLT · MOT17 train (Fair features) | IDF1: 80.7 -> 82.2 | Improved |
| plug RTU into DeepSORT | DeepSORT · MOT17 train (Fair features) | IDF1: 75.6 -> 81.4 | Improved |
| plug RTU into DeepSORT | DeepSORT · MOT17 train (Fair features) | FN: 13690 -> 15130 | Hurt |
| plug RTU into DeepSORT | DeepSORT · MOT17 train (PCB features) | MOTA: 83.6 -> 83.7 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TubeTK — TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model (CVPR 2020) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Recurrently Target-Attending Tracking (CVPR 2016 · similarity 0.88)
- Towards Generalizable Multi-Object Tracking (CVPR 2024 · similarity 0.87)
- Online Multi-Target Tracking Using Recurrent Neural Networks (AAAI 2017 · similarity 0.87)
- Self-Supervised Multi-Object Tracking with Cross-input Consistency (NeurIPS 2021 · similarity 0.87)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.87)
- Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking (AAAI 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.
