no code implementations • 26 Jun 2023 • Leonardo de Melo Joao, Azael de Melo e Sousa, Bianca Martins dos Santos, Silvio Jamil Ferzoli Guimaraes, Jancarlo Ferreira Gomes, Ewa Kijak, Alexandre Xavier Falcao
State-of-the-art (SOTA) object detection methods have succeeded in several applications at the price of relying on heavyweight neural networks, which makes them inefficient and inviable for many applications with computational resource constraints.
no code implementations • 1 Dec 2021 • Leonardo de Melo Joao, Alexandre Xavier Falcao
ISESS estimates seeds for superpixel delineation from a given saliency map and defines superpixel queries in the foreground and background.
no code implementations • 30 Jun 2020 • Leonardo de Melo Joao, Felipe de Castro Belem, Alexandre Xavier Falcao
We compare ITSELF to two state-of-the-art saliency estimators on five metrics and six datasets, four of which are composed of natural-images, and two of biomedical-images.