Deep learning for automatic detection of soccer events from broadcasted video Soccer analytics is attracting increasing interest in academia and industry, thanks to the...

Service that uses optical character recognition (OCR) to identify text contained within images. This is a multi-lingual service and not restricted to Latin scripts. It works...

https://github.com/HPAI-BSC/Focus-Metric Implementation of the Focus metric. This metric is able to evaluate explainability methods and quantify their coherency to the task...

We provide a method to visualize the results of Boolean Matrix Factorization algorithms. Our method can also be used to visualize overlapping clusters in bipartite graphs. The...

This experiment is part the project "Streams of conspiratorial folklore" that investigates online media as a stream of performances, rather than as archives of documents. Our...

This experiment is part the project "Streams of conspiratorial folklore" that investigates online media as a stream of performances, rather than as archives of documents. Our...

This experiment is part the project "Streams of conspiratorial folklore" that investigates online media as a stream of performances, rather than as archives of documents. Our...

How-to guide that describes four recipes for visual media analysis, including key software tools that enable the analysis

The video tutorial discusses the case study of deepfakes to present how to perform Visual Media Analysis for Online Discourses. The tutorial includes: research questions;...

The video tutorial presents techniques for analysing meme collections with the computer vision network approach, including seven steps for network building and interpretation,...

The video tutorial discusses making meme collections, including the meme as a technical collection of objects, automated visual analysis, and meme collection distinctiveness.

The video tutorial introduces the concept of the "metapicture" for the visual media analysis of online discourses and explains various analysis techniques: Visual Similarity,...

The video tutorial discusses using computer vision techniques to study online images, including case studies, research methods, challenges faced, and lessons learned.

Just for platform reviewing

Instagram is currently the social media platform most associated with online images (and their analysis), but images from other platforms also can be collected and grouped,...

This dataset contains 360° video footage from a bottom-up street-view survey in Pristina, Kosovo divided into major neighborhoods.

Implements a method of transfer learning for feature extraction including both convolutional and fully connected layers of a neural network.

The MAMe dataset ia an image classification dataset with remarkable high resolution and variable shape properties. The goal of MAMe is to provide a tool for studying the...