Towards a Better Understanding of the Computer Vision Research Community in Africa

TL;DR

The paper investigates how Africa's computer vision research is represented in top-tier venues, quantifying equity gaps with a Scopus-based bibliometric framework. It builds three data sets—full (~63k), refined (~18k), and top-tier (~43k)—and applies a verification pipeline including affiliation-history to identify African-affiliated authors. Key findings reveal Africa accounts for about 0.06% of top-tier CV publications, with Northern and Southern Africa dominating while Eastern and Western Africa are catching up; international collaborations predominate and African authors often lead as first or last authors; Central Africa remains under-resourced. The study discusses ethical considerations, barriers faced by researchers, and proposes actionable steps (quantitative barrier surveys, CV syllabus committee, and bias analysis) to advance an equity-focused African CV ecosystem.

Abstract

Computer vision is a broad field of study that encompasses different tasks (e.g., object detection). Although computer vision is relevant to the African communities in various applications, yet computer vision research is under-explored in the continent and constructs only 0.06% of top-tier publications in the last ten years. In this paper, our goal is to have a better understanding of the computer vision research conducted in Africa and provide pointers on whether there is equity in research or not. We do this through an empirical analysis of the African computer vision publications that are Scopus indexed, where we collect around 63,000 publications over the period 2012-2022. We first study the opportunities available for African institutions to publish in top-tier computer vision venues. We show that African publishing trends in top-tier venues over the years do not exhibit consistent growth, unlike other continents such as North America or Asia. Moreover, we study all computer vision publications beyond top-tier venues in different African regions to find that mainly Northern and Southern Africa are publishing in computer vision with 68.5% and 15.9% of publications, resp. Nonetheless, we highlight that both Eastern and Western Africa are exhibiting a promising increase with the last two years closing the gap with Southern Africa. Additionally, we study the collaboration patterns in these publications to find that most of these exhibit international collaborations rather than African ones. We also show that most of these publications include an African author that is a key contributor as the first or last author. Finally, we present the most recurring keywords in computer vision publications per African region.

Figures (7)

• Figure 1: Our proposed pipeline for data collection, verification and analysis of the African Scopus indexed computer vision publications. The search query generation uses simple queries to retrieve all computer vision publications (i.e., full set) or generates queries based on the Top-50 keywords in computer vision as a publications sample (i.e., refined set). This is followed by data collection of the full, refined and top-tier publications sets and a verification phase on the refined and top-tier sets. Finally, we present three different types of analysis on the these data sources.
• Figure 2: Scopus-indexed computer vision publications per African region across the time interval 2012-2022. We use the logarithmic scale in (A, C). (A) The number of publications in the refined set. (B) The percentages of publications per region. (C) The number of publications in the full set. The two most publishing regions (Northern - Southern Africa) are highlighted in red. It shows consistent growth in Northern and Southern regions’ publications, and a recent increase in Eastern and Western Africa publications in 2016-2022. However, Central Africa is the most in need of improving the computer vision capacity, as it contributes less than 1% to the total publications.
• Figure 3: Top ten African countries publishing in computer vision from the refined set. Left: Number of annual publications in computer vision from the top ten African countries in logarithmic scale. Right: Total number of publications from the top ten African countries.
• Figure 4: Publications in top-tier venues (CVPR, ICCV, ECCV, ICML, NeurIPS, ICLR, MICCAI, TPAMI, IJCV) across all continents. Right: Number of researcher-publication pairs in top-tier venues per continent over the last ten years, with Africa highlighted in red. Left: The top African countries publishing in top-tier venues. SA: South Africa.
• Figure 5: Publications in the best computer vision venue (CVPR). Right: Number of researcher-publication pairs in top-tier venues per continent over the last ten years, Africa highlighted in red. Africa$\dagger$: indicates African authors not necessarily affiliated with African institutions and highlighted in blue. Left: The top African countries publishing in CVPR. SA: South Africa. Table Column I: The number of pairs having authors affiliated with African institutions, Table Column II: The number of pairs having African Authors not necessarily affiliated with African institutions.