Research map / Detection and segmentation / Tracking
STAR: Spatial-Temporal Tracklet Matching for Multi-Object Tracking
Xuewei Bai, Yongcai Wang, Deying Li, Haodi Ping, LI Chunxu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes STAR, a spatial-temporal tracklet graph matching paradigm for tracking-by-detection multi-object tracking that associates objects with tracklets to handle viewpoint changes and occlusions.
Problem
Tracking-by-detection multi-object tracking relies on motion and appearance features, which become inconsistent with historical tracklets under viewpoint variation and occlusion.
Approach
Replaces per-object tracklet association with a spatial-temporal tracklet graph matching paradigm, so that association uses graph structure over tracklets rather than only motion and appearance features.
Closest papers by meaning
- Learnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object Tracking (CVPR 2021 · similarity 0.89)
- Spatial-Temporal Relation Networks for Multi-Object Tracking (ICCV 2019 · similarity 0.88)
- Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking (AAAI 2024 · similarity 0.86)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.86)
- Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking (ICLR 2025 · similarity 0.86)
- TGFormer: Transformer with Track Query Group for Multi-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.
