Research map / Video / Video segmentation and tracking
Instance Segmentation as Tracking: A New Paradigm for Multi-Small-Object Tracking with Event Cameras
Nuo Chen, Shiman He, Boyang Li, Yingqian Wang, Chao Xiao, QianYin QianYin, Ruojing Li, Yihang Luo, Wei An, Miao Li
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 intra-packet association module (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA / IDF1: +8.13 MOTA, +16.62 IDF1 | Improved |
| add inter-packet association for online processing (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 60.84 -> 60.85 | No clear effect |
| add direction prediction to association modules (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 60.85 -> 64.48 | Improved |
| add direction prediction alone (ablation) | baseline · EV-UAV-Track test | MOTA: 52.71 -> 53.89 | Improved |
| use 1 ms instead of 50 ms voxel temporal resolution (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 45.7 -> 64.4 | Improved |
| use 800 ms instead of 100 ms time window (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 55.32 -> 64.48 | Improved |
| use 800 ms instead of 1200 ms time window (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 63.89 -> 64.48 | Improved |
| use K=15 neighbors instead of K=30 (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 60.89 -> 64.48 | Improved |
| use K=15 neighbors instead of K=5 (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 58.32 -> 64.48 | Improved |
| use relative location and direction features instead of adding all absolute and relative features (ablation) | Ev-ISNet · EV-UAV-Track test | MOTA: 58.22 -> 64.48 | Improved |
| use Ev-ISNet instead of HAIS on dense bee swarm | Ev-ISNet · Bee Swarm | MOTA: 23.1 -> 31.5 | Improved |
| use Ev-ISNet instead of best frame-based tracker (RVT + SORT) | Ev-ISNet · EV-UAV-Track test | MOTA: 37.08 -> 64.48 | Improved |
Closest papers by meaning
- M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection (NeurIPS 2026 · similarity 0.87)
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline (CVPR 2024 · similarity 0.87)
- MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking (NeurIPS 2025 · similarity 0.87)
- M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking (AAAI 2024 · similarity 0.86)
- TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (NeurIPS 2024 · similarity 0.86)
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · 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.
