Cláudio R. Jung — accepted AI-conference papers

2021

Improving the Classification of Rare Chords With Unlabeled Data

Marcelo Bortolozzo, Rodrigo Schramm, Cláudio R. Jung

ICASSP 2021accepted

In this work, we explore techniques to improve performance for rare classes in the task of Automatic Chord Recognition (ACR). We first explored the use of the focal loss in the context of ACR, which was originally proposed to improve the classification of hard samples. In parallel, we adapted a self…

Cited by 0 Source ↗Scholar ↗

2019

On the Performance of DIBR Methods When Using Depth Maps from State-of-the-art Stereo Matching Algorithms

Adriano Q. de Oliveira, Thiago L. T. da Silveira, Marcelo Walter, Cláudio R. Jung

ICASSP 2019accepted

In this paper we compare the quality of synthesized views produced by four DIBR methods when fed by depth maps estimated by five state-of-the-art stereo matching algorithms. Also, we compute the correlation between four popular metrics for ranking stereo matching algorithms and two metrics commonly…

Cited by 0 Source ↗Scholar ↗