# External Labeling Techniques: A Taxonomy and Survey

arXiv: https://arxiv.org/abs/1902.01454 · HTML: https://mlsanity.com/paper/1902.01454/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2019.

## Built on by (most cited first, 2 of 2)

- [Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement](https://mlsanity.com/paper/2303.01388/) (2023)
- [Adaptive 3D UI Placement in Mixed Reality Using Deep Reinforcement Learning](https://mlsanity.com/paper/2504.21731/) (2025)

## Abstract (arXiv)

External labeling is frequently used for annotating features in graphical displays and visualizations, such as technical illustrations, anatomical drawings, or maps, with textual information. Such a labeling connects features within an illustration by thin leader lines with their labels, which are placed in the empty space surrounding the image. Over the last twenty years, a large body of literature in diverse areas of computer science has been published that investigates many different aspects, models, and algorithms for automatically placing external labels for a given set of features. This state-of-the-art report introduces a first unified taxonomy for categorizing the different results in the literature and then presents a comprehensive survey of the state of the art, a sketch of the most relevant algorithmic techniques for external labeling algorithms, as well as a list of open research challenges in this multidisciplinary research field.