# Revisiting the details when evaluating a visual tracker

arXiv: https://arxiv.org/abs/2102.06733 · HTML: https://mlsanity.com/paper/2102.06733/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 25 Jan 2021.

## Builds on (most cited first, 7 of 7)

- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [ECO: Efficient Convolution Operators for Tracking](https://mlsanity.com/paper/1611.09224/) (2016)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [A Novel Performance Evaluation Methodology for Single-Target Trackers](https://mlsanity.com/paper/1503.01313/) (2015)
- [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)

## Abstract (arXiv)

Visual tracking algorithms are naturally adopted in various applications, there have been several benchmarks and many tracking algorithms, more expected to appear in the future. In this report, I focus on single object tracking and revisit the details of tracker evaluation based on widely used OTBciteotb benchmark by introducing a simpler, accurate, and extensible method for tracker evaluation and comparison. Experimental results suggest that there may not be an absolute winner among tracking algorithms. We have to perform detailed analysis to select suitable trackers for use cases.