4 papers
Improving the Classification of Rare Chords with Unlabeled Data
Marcelo Bortolozzo, Rodrigo Schramm, Claudio R. Jung
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 con…
Distilling Knowledge from Refinement in Multiple Instance Detection Networks
Luis Felipe Zeni, Claudio Jung
Weakly supervised object detection (WSOD) aims to tackle the object detection problem using only labeled image categories as supervision. A common approach used in WSOD to deal wit…
Superpixel Image Classification with Graph Attention Networks
Pedro H. C. Avelar, Anderson R. Tavares, Thiago L. T. da Silveira +2
This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regi…
Collective behavior recognition using compact descriptors
Gustavo Fuhr, Claudio Rosito Jung
This paper presents a novel hierarchical approach for collective behavior recognition based solely on ground-plane trajectories. In the first layer of our classifier, we introduce…