Research map / Detection and segmentation / Tracking
FusionTrack: Collaborative Multi-Object Tracking with Arbitrary Multi-UAVs
Xiaohe Li, Pengfei Li, Kaixin Zhang, Jiahao Li, Zide Fan
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 cross-frame fusion (ablation) | FusionTrack base · MDMOT | CVMA/CVIDF1: 76.5/66.8 -> 78.8/72.2 | Improved |
| add cross-view fusion (ablation) | FusionTrack with cross-frame fusion · MDMOT | CVMA/CVIDF1: 78.8/72.2 -> 79.5/74.3 | Improved |
| add reconstruction loss (ablation) | FusionTrack · MDMOT | CVMA/CVIDF1: 79.5/74.3 -> 81.8/75.5 | Improved |
| add sliding-window voting to VHC (ablation) | FusionTrack inference · MDMOT | CVMA/CVIDF1: 77.1/72.3 -> 79.2/74.1 | Improved |
| add neighborhood filtering to VHC + SWV (ablation) | FusionTrack inference · MDMOT | CVMA/CVIDF1: 79.2/74.1 -> 81.8/75.5 | Improved |
| replace Hungarian matching with VHC (ablation) | FusionTrack inference (SWV + NFM) · MDMOT | CVMA/CVIDF1: 78.5/73.3 -> 81.8/75.5 | Improved |
| replace GMT with FusionTrack | GMT · MDMOT | CVMA/CVIDF1: 79.9/73.8 -> 81.8/75.5 | Improved |
| replace GMT with FusionTrack | GMT · DIVOTrack | CVIDF1: 73.2 -> 77.5 | Improved |
| replace GMT with FusionTrack | GMT · CAMPUS | CVMA: 66.4 -> 68.6 | Improved |
| FusionTrack vs HybridSORT on single-view tracking | HybridSORT · MDMOT (single-view) | MOTA: 89.81 -> 88.75 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- HybridSORT — Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking (AAAI 2024) · better on 0 of 3 shared results
- MOTR — MOTR: End-to-End Multiple-Object Tracking with TRansformer (ECCV 2022) · better on 1 of 1 shared result
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
- Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos (AAAI 2026 · similarity 0.89)
- MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking (CVPR 2025 · similarity 0.88)
- MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking (NeurIPS 2025 · similarity 0.88)
- Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking (ICML 2024 · similarity 0.88)
- M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking (AAAI 2024 · similarity 0.86)
- ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association (CVPR 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.
