R
Rémi Mégret
Researcher at University of Puerto Rico
Publications - 70
Citations - 1055
Rémi Mégret is an academic researcher from University of Puerto Rico. The author has contributed to research in topics: Wearable computer & Motion estimation. The author has an hindex of 17, co-authored 67 publications receiving 880 citations. Previous affiliations of Rémi Mégret include University of Puerto Rico at Mayagüez & University of Puerto Rico, Río Piedras.
Papers
More filters
Journal ArticleDOI
Continuous-Discrete Extended Kalman Filter on Matrix Lie Groups Using Concentrated Gaussian Distributions
TL;DR: The proposed new assumed density filter called continuous-discrete extended Kalman filter on Lie groups (CD-LG-EKF) significantly outperforms two constrained non-linear filters applied on the embedding space of the Lie group.
Journal ArticleDOI
Understanding important features of deep learning models for segmentation of high-resolution transmission electron microscopy images.
TL;DR: This work considers the case of studying coarsening dynamics in supported nanoparticles, which is important for understanding the degradation of industrial catalysts, and proposes methods for optimizing performance of image segmentation using convolutional neural networks.
Proceedings Article
Discrete Extended Kalman Filter on Lie groups
TL;DR: A new filter called Discrete Extended Kalman Filter on Lie Groups (D-LG-EKF) is proposed, which assumes that the posterior distribution of the state is a concentrated Gaussian distribution on Lie groups.
ReportDOI
A Survey of Spatio-Temporal Grouping Techniques
Rémi Mégret,Daniel DeMenthon +1 more
TL;DR: This work classifies spatio-temporal grouping techniques into three categories: (1) segmentation with spatial priority, (2) segmentations by trajectory grouping, and (3) joint spatial and temporal segmentation.
Journal ArticleDOI
Hierarchical Hidden Markov Model in Detecting Activities of Daily Living in Wearable Videos for Studies of Dementia
Svebor Karaman,Jenny Benois-Pineau,Vladislavs Dovgalecs,Rémi Mégret,Julien Pinquier,Régine André-Obrecht,Yann Gaëstel,Jean-François Dartigues +7 more
TL;DR: A video structuring approach that combines automatic motion based segmentation of the video and activity recognition by a hierarchical two-level Hidden Markov Model is introduced that defines a multi-modal description space over visual and audio features, including mid-level features such as motion, location, speech and noise detections.