Research map / 3D vision / Depth and stereo
MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost
Taiga Yamane, Ryo Masumura, Satoshi Suzuki, Shota Orihashi
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 |
|---|---|---|---|
| increase past trajectory length K from 1 to 7 (ablation) | MVTrajecter · GMVD | MOTA: 74.2 -> 78.1 (IDF1 71.0 -> 77.2) | Improved |
| add trajectory motion cost (TMC) to motion baseline (ablation) | Motion baseline · GMVD | IDF1: 67.8 -> 71.8 | Improved |
| add trajectory appearance cost (TAC) to appearance baseline (ablation) | Appearance baseline · GMVD | IDF1: 64.7 -> 72.3 | Improved |
| combine TMC and TAC (ablation) | MVTrajecter · GMVD | MOTA: 74.2 -> 78.1 vs motion baseline + TMC | Improved |
| use attention instead of Kalman filter to predict motion (ablation) | MVTrajecter · GMVD | MOTA: 75.3 -> 78.1 | Improved |
| use attention-based appearance features instead of EarlyBird-style extraction (ablation) | MVTrajecter · GMVD | MOTA: 76.2 -> 78.1 | Improved |
| use MVTrajecter detections for baseline trackers | TrackTacular · GMVD | IDF1: 74.4 -> 75.6 | Improved |
| increase K from 5 to 7 (ablation) | MVTrajecter · GMVD | MOTP: 87.8 -> 87.7 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports MVTrajecter as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes (CVPR 2026 · better on 1 of 3 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
- Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes (CVPR 2026 · similarity 0.86)
- MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model (ECCV 2026 · similarity 0.85)
- Delving into the Trajectory Long-tail Distribution for Muti-object Tracking (CVPR 2024 · similarity 0.85)
- PathTrack: Fast Trajectory Annotation With Path Supervision (ICCV 2017 · similarity 0.84)
- MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (IJCV 2020 · similarity 0.84)
- MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping (ECCV 2024 · similarity 0.84)
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.
