J
Jefersson A. dos Santos
Researcher at Universidade Federal de Minas Gerais
Publications - 132
Citations - 3382
Jefersson A. dos Santos is an academic researcher from Universidade Federal de Minas Gerais. The author has contributed to research in topics: Segmentation & Contextual image classification. The author has an hindex of 20, co-authored 120 publications receiving 2539 citations. Previous affiliations of Jefersson A. dos Santos include State University of Campinas.
Papers
More filters
Journal ArticleDOI
Towards better exploiting convolutional neural networks for remote sensing scene classification
TL;DR: An analysis of three possible strategies for exploiting the power of existing convolutional neural networks (ConvNets or CNNs) in different scenarios from the ones they were trained: full training, fine tuning, and using ConvNets as feature extractors points that fine tuning tends to be the best performing strategy.
Proceedings ArticleDOI
Do deep features generalize from everyday objects to remote sensing and aerial scenes domains
TL;DR: ConvNets trained for recognizing everyday objects for the classification of aerial and remote sensing images obtained the best results for aerial images, while for remote sensing, they performed well but were outperformed by low-level color descriptors, such as BIC.
Proceedings ArticleDOI
SkeleMotion: A New Representation of Skeleton Joint Sequences based on Motion Information for 3D Action Recognition
Carlos Caetano,Jessica Sena,Francois Bremond,Jefersson A. dos Santos,William Robson Schwartz +4 more
TL;DR: A novel skeleton image representation to be used as input of Convolutional Neural Networks (CNNs), named SkeleMotion, is introduced, which encodes the temporal dynamics by explicitly computing the magnitude and orientation values of the skeleton joints.
Journal ArticleDOI
Dynamic Multicontext Segmentation of Remote Sensing Images Based on Convolutional Networks
Keiller Nogueira,Mauro Dalla Mura,Jocelyn Chanussot,William Robson Schwartz,Jefersson A. dos Santos +4 more
TL;DR: A novel technique to perform semantic segmentation of remote sensing images that exploits a multicontext paradigm without increasing the number of parameters while defining, in training time, the best patch size is proposed.
Journal ArticleDOI
Dynamic Multi-Scale Segmentation of Remote Sensing Images based on Convolutional Networks
Keiller Nogueira,Mauro Dalla Mura,Jocelyn Chanussot,William Robson Schwartz,Jefersson A. dos Santos +4 more
TL;DR: In this paper, a dilated network with distinct patch sizes is proposed to capture multi-context characteristics from heterogeneous contexts, and the network provides a score for each patch size, helping in the definition of the best patch size for the current scenario.