# Siamese Keypoint Prediction Network for Visual Object Tracking

arXiv: https://arxiv.org/abs/2006.04078 · HTML: https://mlsanity.com/paper/2006.04078/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2020.

## Built on by (most cited first, 4 of 4)

- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [Context-aware Visual Tracking with Joint Meta-updating](https://mlsanity.com/paper/2204.01513/) (2022)
- [Higher Performance Visual Tracking with Dual-Modal Localization](https://mlsanity.com/paper/2103.10089/) (2021)

## Abstract (arXiv)

Visual object tracking aims to estimate the location of an arbitrary target in a video sequence given its initial bounding box. By utilizing offline feature learning, the siamese paradigm has recently been the leading framework for high performance tracking. However, current existing siamese trackers either heavily rely on complicated anchor-based detection networks or lack the ability to resist to distractors. In this paper, we propose the Siamese keypoint prediction network (SiamKPN) to address these challenges. Upon a Siamese backbone for feature embedding, SiamKPN benefits from a cascade heatmap strategy for coarse-to-fine prediction modeling. In particular, the strategy is implemented by sequentially shrinking the coverage of the label heatmap along the cascade to apply loose-to-strict intermediate supervisions. During inference, we find the predicted heatmaps of successive stages to be gradually concentrated to the target and reduced to the distractors. SiamKPN performs well against state-of-the-art trackers for visual object tracking on four benchmark datasets including OTB-100, VOT2018, LaSOT and GOT-10k, while running at real-time speed.