CP-JKU achieves first place in `emotion and theme recognition in music challenge, MediaEval 19
MediaEval is a benchmarking that offers challenges in multimedia retrieval, access and exploration to allow researchers working in computer science and other multimedia related field an opportunity to work on tasks that are related to human and social aspects of multimedia. MediaEval aims is to promote reproducible research that makes multimedia a positive force for society.
Emotion and theme recognition is a popular task in music information retrieval that is relevant for music search and recommendation systems. The goal of the task is to automatically recognize the emotions and themes conveyed in a music recording using machine learning algorithms.
The team of the Institute of Computational Perception, namely Khaled Koutini, Shreyan Chowdhury, Verena Haunschmid, Hamid Eghbal-zadeh, Gerhard Widmer, won the challenge by developing the highest performing models to detect emotion and themes in music.