Enhanced Spatio- Temporal Image Encoding for Online Human Activity Recognition

1 code implementation • International Conference on Machine Learning and Applications (ICMLA) 2023 • Nassim Mokhtari, Vincent Fer, Alexis Nédélec, Marlene Gilles, Pierre De Loor

It can be done using 3D skeleton data extracted from a RGB+D camera.

Human Activity Recognition Time Series +1

Improving Neural Architecture Search by Mixing a FireFly algorithm with a Training Free Evaluation

1 code implementation • International Joint Conference on Neural Networks (IJCNN) 2022 • Nassim Mokhtari, Alexis Nédélec, Marlène Gilles, Pierre De Loor

Neural Architecture Search (NAS) algorithms are used to automate the design of deep neural networks.

Neural Architecture Search valid

Human Activity Recognition: A Spatio-temporal Image Encoding of 3D Skeleton Data for Online Action Detection

1 code implementation • International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications VISIGRAPP 2020 • Nassim Mokhtari, Alexis Nédélec, Pierre De Loor

Human activity recognition (HAR) based on skeleton data that can be extracted from videos (Kinect for example) , or provided by a depth camera is a time series classification problem, where handling both spatial and temporal dependencies is a crucial task, in order to achieve a good recognition.

Human Activity Recognition Online Action Detection +2

Effects of Coupling in Human-Virtual Agent Body Interaction

no code implementations • 19 Sep 2014 • Elisabetta Bevacqua, Sankovic Igor, Maatalaoui Ayoub, A. Nédélec, Pierre De Loor

The experiment was based on a theatrical game involving the imitation of slow upper-body movements and the proposal of new movements by the user and virtual agent.

A Database of Full Body Virtual Interactions Annotated with Expressivity Scores

no code implementations • LREC 2014 • Demulier Virginie, Elisabetta Bevacqua, Florian Focone, Tom Giraud, Pamela Carreno, Brice Isableu, Sylvie Gibet, Pierre De Loor, Jean-Claude Martin

Recent technologies enable the exploitation of full body expressions in applications such as interactive arts but are still limited in terms of dyadic subtle interaction patterns.

Enaction-Based Artificial Intelligence: Toward Coevolution with Humans in the Loop

no code implementations • 26 Feb 2014 • Pierre De Loor, Kristen Manach, Jacques Tisseau

This article deals with the links between the enaction paradigm and artificial intelligence.