# Unsupervised Lightweight Single Object Tracking with UHP-SOT++

arXiv: https://arxiv.org/abs/2111.07548 · HTML: https://mlsanity.com/paper/2111.07548/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 15 Nov 2021.

## Builds on (most cited first, 25 of 25)

- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [ECO: Efficient Convolution Operators for Tracking](https://mlsanity.com/paper/1611.09224/) (2016)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [Distractor-aware Siamese Networks for Visual Object Tracking](https://mlsanity.com/paper/1808.06048/) (2018)
- [Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art](https://mlsanity.com/paper/1704.05519/) (2017)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [End-to-end representation learning for Correlation Filter based tracking](https://mlsanity.com/paper/1704.06036/) (2017)
- [Learning to Track at 100 FPS with Deep Regression Networks](https://mlsanity.com/paper/1604.01802/) (2016)
- [Unsupervised Deep Tracking](https://mlsanity.com/paper/1904.01828/) (2019)
- [Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking](https://mlsanity.com/paper/1608.03773/) (2016)
- [Learning Spatially Regularized Correlation Filters for Visual Tracking](https://mlsanity.com/paper/1608.05571/) (2016)
- [Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking](https://mlsanity.com/paper/1803.08679/) (2018)
- [A Twofold Siamese Network for Real-Time Object Tracking](https://mlsanity.com/paper/1802.08817/) (2018)
- [Staple: Complementary Learners for Real-Time Tracking](https://mlsanity.com/paper/1512.01355/) (2015)
- [Siamese Instance Search for Tracking](https://mlsanity.com/paper/1605.05863/) (2016)
- [Discriminative Scale Space Tracking](https://mlsanity.com/paper/1609.06141/) (2016)
- [Discriminative Correlation Filter with Channel and Spatial Reliability](https://mlsanity.com/paper/1611.08461/) (2016)
- [CREST: Convolutional Residual Learning for Visual Tracking](https://mlsanity.com/paper/1708.00225/) (2017)
- [Unsupervised Deep Representation Learning for Real-Time Tracking](https://mlsanity.com/paper/2007.11984/) (2020)
- [Deep Attentive Tracking via Reciprocative Learning](https://mlsanity.com/paper/1810.03851/) (2018)
- [UHP-SOT: An Unsupervised High-Performance Single Object Tracker](https://mlsanity.com/paper/2110.01812/) (2021)

## Built on by (most cited first, 3 of 3)

- [GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences](https://mlsanity.com/paper/2207.07629/) (2022)
- [Acceleration of Subspace Learning Machine via Particle Swarm Optimization and Parallel Processing](https://mlsanity.com/paper/2208.07023/) (2022)
- [A Tiny Machine Learning Model for Point Cloud Object Classification](https://mlsanity.com/paper/2303.10898/) (2023)

## Abstract (arXiv)

An unsupervised, lightweight and high-performance single object tracker, called UHP-SOT, was proposed by Zhou et al. recently. As an extension, we present an enhanced version and name it UHP-SOT++ in this work. Built upon the foundation of the discriminative-correlation-filters-based (DCF-based) tracker, two new ingredients are introduced in UHP-SOT and UHP-SOT++: 1) background motion modeling and 2) object box trajectory modeling. The main difference between UHP-SOT and UHP-SOT++ is the fusion strategy of proposals from three models (i.e., DCF, background motion and object box trajectory models). An improved fusion strategy is adopted by UHP-SOT++ for more robust tracking performance against large-scale tracking datasets. Our second contribution lies in an extensive evaluation of the performance of state-of-the-art supervised and unsupervised methods by testing them on four SOT benchmark datasets - OTB2015, TC128, UAV123 and LaSOT. Experiments show that UHP-SOT++ outperforms all previous unsupervised methods and several deep-learning (DL) methods in tracking accuracy. Since UHP-SOT++ has extremely small model size, high tracking performance, and low computational complexity (operating at a rate of 20 FPS on an i5 CPU even without code optimization), it is an ideal solution in real-time object tracking on resource-limited platforms. Based on the experimental results, we compare pros and cons of supervised and unsupervised trackers and provide a new perspective to understand the performance gap between supervised and unsupervised methods, which is the third contribution of this work.