no code implementations • 19 Jul 2018 • Carlos Herranz-Perdiguero, Carolina Redondo-Cabrera, Roberto J. López-Sastre
While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately.
1 code implementation • 13 Apr 2018 • Carolina Redondo-Cabrera, Marcos Baptista-Ríos, Roberto J. López-Sastre
Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task.
no code implementations • 24 Jan 2018 • Daniel Oñoro-Rubio, Roberto J. López-Sastre, Carolina Redondo-Cabrera, Pedro Gil-Jiménez
Detecting objects and estimating their pose remains as one of the major challenges of the computer vision research community.
1 code implementation • 24 Jan 2018 • Carolina Redondo-Cabrera, Roberto J. López-Sastre
We here propose two Siamese architectures for Convolutional Neural Networks, and their corresponding novel loss functions, to learn from unlabeled videos, which jointly exploit the local temporal coherence between contiguous frames, and a global discriminative margin used to separate representations of different videos.