MediaEval 2018 AcousticBrainz genre task: A baseline combining deep feature embeddings across datasets
MediaEval 2018 AcousticBrainz genre task: A baseline combining deep feature embeddings across datasets
Citació
- Oramas S, Bogdanov D, Porter A. MediaEval 2018 AcousticBrainz genre task: a baseline combining deep feature embeddings across datasets. In: Larson M, Arora P, Demarty CH, Riegler M, Bischke B, Dellandrea E, Lux M, Porter A, Jones GJF. MediaEval 2018 Multimedia Benchmark Workshop Working Notes Proceedings of the MediaEval 2018 Workshop. 2018 Oct 29-31; Sophia Antipolis, France. Aachen: CEUR; 2018. [3] p.
Enllaç permanent
Descripció
Dades relacionades
Resum
In this paper we present a baseline approach for the MediaEval 2018 AcousticBrainz Genre Task that takes advantage of stacking multiple feature embeddings learned on individual genre datasets by simple deep learning architectures. Although we employ basic neural networks, the combination of their deep feature embeddings provides a significant gain in performance compared to each individual network.Descripció
Comunicació presentada al MediaEval 2018 Workshop celebrat a Sophia Antipolis (França) del 29 al 31 d'octubre de 2018.