# SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking

Source: [SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking](<https://www.sota2.com/research/paper/68fa6a711e209131cea281d3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:24:37.002Z

Authors: Ziang Cao, Changhong Fu, Junjie Ye, Bowen Li, Yiming Li

Published: 2021-06-16T14:28:57.000Z

## Abstract

Recently, the Siamese-based method has stood out from multitudinous tracking methods owing to its state-of-the-art (SOTA) performance. Nevertheless, due to various special challenges in UAV tracking, \\textit{e.g.}, severe occlusion and fast motion, most existing Siamese-based trackers hardly combine superior performance with high efficiency. To this concern, in this paper, a novel attentional Siamese tracker (SiamAPN++) is proposed for real-time UAV tracking. By virtue of the attention mechanism, we conduct a special attentional aggregation network (AAN) consisting of self-AAN and cross-AAN for raising the representation ability of features eventually. The former AAN aggregates and models the self-semantic interdependencies of the single feature map via spatial and channel dimensions. The latter aims to aggregate the cross-interdependencies of two different semantic features including the location information of anchors. In addition, the anchor proposal network based on dual features is proposed to raise its robustness of tracking objects with various scales. Experiments on two well-known authoritative benchmarks are conducted, where SiamAPN++ outperforms its baseline SiamAPN and other SOTA trackers. Besides, real-world tests onboard a typical embedded platform demonstrate that SiamAPN++ achieves promising tracking results with real-time speed.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Tracking on DarkSOT (test)](<https://www.sota2.com/research/sota/object-tracking-on-darksot-test.md>): Object Tracking; DarkSOT (test); SAUC: 32.2.

- [Object Tracking on UAVDark135 (test)](<https://www.sota2.com/research/sota/object-tracking-on-uavdark135-test.md>): Object Tracking; UAVDark135 (test); SAUC: 34.1.

- [Nighttime UAV Tracking on DarkTrack 2021](<https://www.sota2.com/research/sota/nighttime-uav-tracking-on-darktrack-2021.md>): Nighttime UAV Tracking; DarkTrack 2021; Precision: 48.3.

- [Nighttime UAV Tracking on NAT 2021 (test)](<https://www.sota2.com/research/sota/nighttime-uav-tracking-on-nat-2021-test.md>): Nighttime UAV Tracking; NAT 2021 (test); Precision: 60.8.

- [Nighttime UAV Tracking on UAVDark135](<https://www.sota2.com/research/sota/nighttime-uav-tracking-on-uavdark135.md>): Nighttime UAV Tracking; UAVDark135; Precision: 42.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.08816>)

[PDF](<https://arxiv.org/pdf/2106.08816.pdf>)
