Research map / Detection and segmentation / Tracking
Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos
Jianbo Ma, Hui Luo, Qi Chen, Yuankai Qi, Yumei Sun, Amin Beheshti, Jianlin Zhang, Ming-Hsuan Yang
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 AMC matrix (ablation) | FairMOT baseline · VisDrone2019 | IDF1: 54.4 -> 60.5 | Improved |
| add MTC module (ablation) | FairMOT baseline · VisDrone2019 | IDF1: 54.4 -> 57.3 | Improved |
| add both AMC and MTC (ablation) | FairMOT baseline · VisDrone2019 | IDF1: 54.4 -> 61.4 | Improved |
| add both AMC and MTC (ablation) | FairMOT baseline · VisDrone2019 | IDs: 3847 -> 1063 | Improved |
| add both AMC and MTC (ablation) | FairMOT baseline · UAVDT | IDF1: 72.4 -> 74.7 | Improved |
| add MTC on top of AMC (ablation) | AMOT · VisDrone2019 | IDF1: 60.5 -> 61.4 | Improved |
| add MTC on top of AMC (ablation) | AMOT · UAVDT | MOTA: 54.9 -> 55.1 | No clear effect |
| add AMC and MTC (ablation) | AMOT · VisDrone2019 | FPS: 37.1 -> 36.4 | No clear effect |
| use both forward and backward distances in AMC (ablation) | AMC · VisDrone2019 | IDF1: 60.4 -> 60.5 | No clear effect |
| use both forward and backward distances in AMC (ablation) | AMC · UAVDT | IDF1: 73.3 -> 74.4 | Improved |
| plug AMC and MTC into STCMOT (ablation) | STCMOT · VisDrone2019 | IDF1: 52.7 -> 59.7 | Improved |
| plug AMC and MTC into UAVMOT (ablation) | UAVMOT · UAVDT | IDF1: 69.0 -> 69.7 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ByteTrack — ByteTrack: Multi-Object Tracking by Associating Every Detection Box (ECCV 2022) · better on 3 of 3 shared results
- MM-Tracker — MM-Tracker: Motion Mamba for UAV-platform Multiple Object Tracking (AAAI 2025) · better on 2 of 2 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
- Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions (CVPR 2026 · similarity 0.90)
- Visual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models (AAAI 2017 · similarity 0.89)
- UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation (AAAI 2024 · similarity 0.87)
- MM-Tracker: Motion Mamba for UAV-platform Multiple Object Tracking (AAAI 2025 · similarity 0.87)
- MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking (NeurIPS 2025 · similarity 0.86)
- Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking (ICML 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.
