Related papers: Flickr Africa: Examining Geo-Diversity in Large-Sc…
Modern machine learning systems such as image classifiers rely heavily on large scale data sets for training. Such data sets are costly to create, thus in practice a small number of freely available, open source data sets are widely used.…
In our generation, there is an undoubted rise in the use of social media and specifically photo and video sharing platforms. These sites have proved their ability to yield rich data sets through the users' interaction which can be used to…
An untested assumption behind the crowdsourced descriptions of the images in the Flickr30K dataset (Young et al., 2014) is that they "focus only on the information that can be obtained from the image alone" (Hodosh et al., 2013, p. 859).…
People's behavior on online social networks, which store geo-tagged information showing where people were or are at the moment, can provide information about their offline life as well. In this paper we present one possible research…
Social media images provide valuable insights for modeling, mapping, and understanding human interactions with natural and cultural heritage. However, categorizing these images into semantically meaningful groups remains highly complex due…
The dynamics of attention in social media tend to obey power laws. Attention concentrates on a relatively small number of popular items and neglecting the vast majority of content produced by the crowd. Although popularity can be an…
Online social networks contain a constantly increasing amount of images - most of them focusing on people. Due to cultural and climate factors, fashion trends and physical appearance of individuals differ from city to city. In this paper we…
Visual-Language Models (VLMs) have shown remarkable performance across various tasks, particularly in recognizing geographic information from images. However, VLMs still show regional biases in this task. To systematically evaluate these…
In centralized countries, not only population, media and economic power are concentrated, but people give more attention to central locations. While this is not inherently bad, this behavior extends to micro-blogging platforms: central…
The unprecedented photorealistic results achieved by recent text-to-image generative systems and their increasing use as plug-and-play content creation solutions make it crucial to understand their potential biases. In this work, we…
Geotagged data can be used to describe regions in the world and discover local themes. However, not all data produced within a region is necessarily specifically descriptive of that area. To surface the content that is characteristic for a…
Recent availability of geo-localized data capturing individual human activity together with the statistical data on international migration opened up unprecedented opportunities for a study on global mobility. In this paper we consider it…
Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped…
Advances in Artificial Intelligence are challenged by the biases rooted in the datasets used to train the models. In image geolocation estimation, models are mostly trained using data from specific geographic regions, notably the Western…
The number of people who decide to share their photographs publicly increases every day, consequently making available new almost real-time insights of human behavior while traveling. Rather than having this statistic once a month or…
Despite significant efforts to democratize artificial intelligence (AI), computer vision which is a sub-field of AI, still lags in Africa. A significant factor to this, is the limited access to computing resources, datasets, and…
Recent discussion about the increase in international research collaboration suggests a comprehensive global network centred around a group of core countries and driven by generic socio-economic factors where the global system influences…
Poverty maps are essential tools for governments and NGOs to track socioeconomic changes and adequately allocate infrastructure and services in places in need. Sensor and online crowd-sourced data combined with machine learning methods have…
Today's geo-location estimation approaches are able to infer the location of a target image using its visual content alone. These approaches exploit visual matching techniques, applied to a large collection of background images with known…
We study cultural and socioeconomic diversity in contrastive vision-language models (VLMs). Using a broad range of benchmark datasets and evaluation metrics, we bring to attention several important findings. First, the common filtering of…