no code implementations • 26 Apr 2022 • Javier Morales, Nils Murrugarra-Llerena, Jose M. Saavedra
Sketch-based understanding is a critical component of human cognitive learning and is a primitive communication means between humans.
no code implementations • 22 Apr 2021 • Anibal Fuentes, Jose M. Saavedra
Architectures based on siamese networks with triplet loss have shown outstanding performance on the image-based similarity search problem.
no code implementations • 20 Apr 2021 • Pablo Torres, Jose M. Saavedra
We show that UMAP allows us to have feature vectors of 16 bytes improving precision by more than 35%.
no code implementations • 31 Mar 2021 • Andres Baloian, Nils Murrugarra-Llerena, Jose M. Saavedra
Visual attributes play an essential role in real applications based on image retrieval.
no code implementations • 29 Oct 2020 • Andre G. Hochuli, Alceu S. Britto Jr, David A. Saji, Jose M. Saavedra, Robert Sabourin, Luiz S. Oliveira
Over the last decades, most approaches proposed for handwritten digit string recognition (HDSR) have resorted to digit segmentation, which is dominated by heuristics, thereby imposing substantial constraints on the final performance.
no code implementations • 20 Jun 2019 • Ignacio Úbeda, Jose M. Saavedra, Stéphane Nicolas, Caroline Petitjean, Laurent Heutte
Pattern spotting consists of searching in a collection of historical document images for occurrences of a graphical object using an image query.