Revisiting the details when evaluating a visual tracker
Not on the map. Why?
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.
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
7 of 10 references.
References · 7
- 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 568
- 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
- 2016ECO: Efficient Convolution Operators for Trackingcited by 239
- 2015Learning Multi-Domain Convolutional Neural Networks for Visual Trackingcited by 209
- 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
- 2017End-to-end representation learning for Correlation Filter based trackingcited by 90
- 2016Learning to Track at 100 FPS with Deep Regression Networkscited by 89
Built on by
Not cited yet.