Research map / Detection and segmentation / Tracking
SemTrack: A Large-scale Dataset for Semantic Tracking in the Wild
Pengfei Wang, Xiaofei Hui, Jing Wu, Zile Yang, Kian Eng Ong, Xinge Zhao, Beijia Lu, Dezhao Huang, Evan Ling, Weiling Chen, Keng Teck Ma, Minhoe Hur and 1 more
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 |
|---|---|---|---|
| use YOLOX-X detector with ByteTrack tracker instead of other detector/tracker pairs (ablation) | SemTracker · SemTrack test subset | ST-mAP: 1.241 -> 4.625 | Improved |
| replace DeepSort or Sort with ByteTrack (ablation) | SemTracker YOLOX-X · SemTrack test subset | Track-mAP: 2.039 -> 5.875 | Improved |
| increase detector size YOLOX-M to YOLOX-X with Sort tracker (ablation) | SemTracker · SemTrack test subset | ST-mAP: 1.043 -> 1.241 | Mixed |
| provide ground-truth first-frame box and class instead of detector (ablation) | SemTracker ByteTrack · SemTrack test subset | ST-mAP: 4.625 -> 4.792 | Improved |
| add meta-learning to SemTracker (ablation) | SemTracker · SemTrack test subset | ST-mAP: 4.625 -> 8.668 | Improved |
| add reweighting for data imbalance (ablation) | SemTracker · SemTrack test subset | ST-mAP: 4.625 -> 4.714 | No clear effect |
| add focal loss (ablation) | SemTracker · SemTrack test subset | ST-mAP: 4.625 -> 6.869 | Improved |
| add GCLLoss (ablation) | SemTracker · SemTrack test subset | ST-mAP: 4.625 -> 8.211 | Improved |
Closest papers by meaning
- Beyond MOT: Semantic Multi-Object Tracking (ECCV 2024 · similarity 0.89)
- SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking (CVPR 2025 · similarity 0.86)
- Tracking by Natural Language Specification (CVPR 2017 · similarity 0.86)
- Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation (CVPR 2026 · similarity 0.86)
- ODTrack: Online Dense Temporal Token Learning for Visual Tracking (AAAI 2024 · similarity 0.85)
- Less Is More: Token Context-Aware Learning for Object Tracking (AAAI 2025 · similarity 0.85)
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.
