# COMET: Context-Aware IoU-Guided Network for Small Object Tracking

arXiv: https://arxiv.org/abs/2006.02597 · HTML: https://mlsanity.com/paper/2006.02597/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2020.

## Built on by (most cited first, 10 of 10)

- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [The State of Aerial Surveillance: A Survey](https://mlsanity.com/paper/2201.03080/) (2022)
- [Focus-and-Detect: A Small Object Detection Framework for Aerial Images](https://mlsanity.com/paper/2203.12976/) (2022)
- [Tiny Object Tracking: A Large-scale Dataset and A Baseline](https://mlsanity.com/paper/2202.05659/) (2022)
- [CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search](https://mlsanity.com/paper/2107.03463/) (2021)
- [Person Recognition in Aerial Surveillance: A Decade Survey](https://mlsanity.com/paper/2511.17674/) (2025)
- [MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results](https://mlsanity.com/paper/2507.12832/) (2025)
- [maskGRU: Tracking Small Objects in the Presence of Large Background Motions](https://mlsanity.com/paper/2201.00467/) (2022)
- [Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos](https://mlsanity.com/paper/2412.10861/) (2024)
- [Physics-Guided Fusion for Robust 3D Tracking of Fast Moving Small Objects](https://mlsanity.com/paper/2510.20126/) (2025)

## Abstract (arXiv)

We consider the problem of tracking an unknown small target from aerial videos of medium to high altitudes. This is a challenging problem, which is even more pronounced in unavoidable scenarios of drastic camera motion and high density. To address this problem, we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-stream network and an offline reference proposal generation strategy. The proposed network fully exploits target-related information by multi-scale feature learning and attention modules. The proposed strategy introduces an efficient sampling strategy to generalize the network on the target and its parts without imposing extra computational complexity during online tracking. These strategies contribute considerably in handling significant occlusions and viewpoint changes. Empirically, COMET outperforms the state-of-the-arts in a range of aerial view datasets that focusing on tracking small objects. Specifically, COMET outperforms the celebrated ATOM tracker by an average margin of 6.2% (and 7%) in precision (and success) score on challenging benchmarks of UAVDT, VisDrone-2019, and Small-90.