activity
20172024
most citedDomain-independent Extraction of Scientific Concepts from Research Articles

54 citations · 230 across the 42 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

6 papers · 2 filters

cs.CV2021

Extraction of Positional Player Data from Broadcast Soccer Videos

Jonas Theiner, Wolfgang Gritz, Eric Müller-Budack +3

Computer-aided support and analysis are becoming increasingly important in the modern world of sports. The scouting of potential prospective players, performance as well as match a…

cs.CV2021

A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games

Henrik Biermann, Jonas Theiner, Manuel Bassek +3

The automatic detection of events in complex sports games like soccer and handball using positional or video data is of large interest in research and industry. One requirement is…

cs.CV2021

Unsupervised Training Data Generation of Handwritten Formulas using Generative Adversarial Networks with Self-Attention

Matthias Springstein, Eric Müller-Budack, Ralph Ewerth

The recognition of handwritten mathematical expressions in images and video frames is a difficult and unsolved problem yet. Deep convectional neural networks are basically a promis…

cs.CV2021

Unsupervised Video Summarization via Multi-source Features

Hussain Kanafani, Junaid Ahmed Ghauri, Sherzod Hakimov +1

Video summarization aims at generating a compact yet representative visual summary that conveys the essence of the original video. The advantage of unsupervised approaches is that…

cs.CV2021

Supervised Video Summarization via Multiple Feature Sets with Parallel Attention

Junaid Ahmed Ghauri, Sherzod Hakimov, Ralph Ewerth

The assignment of importance scores to particular frames or (short) segments in a video is crucial for summarization, but also a difficult task. Previous work utilizes only one sou…

cs.CV2021

Interpretable Semantic Photo Geolocation

Jonas Theiner, Eric Mueller-Budack, Ralph Ewerth

Planet-scale photo geolocalization is the complex task of estimating the location depicted in an image solely based on its visual content. Due to the success of convolutional neura…