# SiamVGG: Visual Tracking using Deeper Siamese Networks

arXiv: https://arxiv.org/abs/1902.02804 · HTML: https://mlsanity.com/paper/1902.02804/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 6 of 6)

- [Bridging Gap between Image Pixels and Semantics via Supervision: A Survey](https://mlsanity.com/paper/2107.13757/) (2021)
- [Generative Target Update for Adaptive Siamese Tracking](https://mlsanity.com/paper/2202.09938/) (2022)
- [Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking](https://mlsanity.com/paper/2203.03181/) (2022)
- [Towards real-time and energy efficient Siamese tracking -- a hardware-software approach](https://mlsanity.com/paper/2205.10653/) (2022)
- [Deep MDP: A Modular Framework for Multi-Object Tracking](https://mlsanity.com/paper/2310.14294/) (2023)
- [An experimental evaluation of Siamese Neural Networks for robot localization using omnidirectional imaging in indoor environments](https://mlsanity.com/paper/2407.10536/) (2024)

## Abstract (arXiv)

Recently, we have seen a rapid development of Deep Neural Network (DNN) based visual tracking solutions. Some trackers combine the DNN-based solutions with Discriminative Correlation Filters (DCF) to extract semantic features and successfully deliver the state-of-the-art tracking accuracy. However, these solutions are highly compute-intensive, which require long processing time, resulting unsecured real-time performance. To deliver both high accuracy and reliable real-time performance, we propose a novel tracker called SiamVGGfootnotehttps://github.com/leeyeehoo/SiamVGG. It combines a Convolutional Neural Network (CNN) backbone and a cross-correlation operator, and takes advantage of the features from exemplary images for more accurate object tracking. The architecture of SiamVGG is customized from VGG-16 with the parameters shared by both exemplary images and desired input video frames. We demonstrate the proposed SiamVGG on OTB-2013/50/100 and VOT 2015/2016/2017 datasets with the state-of-the-art accuracy while maintaining a decent real-time performance of 50 FPS running on a GTX 1080Ti. Our design can achieve 2% higher Expected Average Overlap (EAO) compared to the ECO and C-COT in VOT2017 Challenge.