Section: New Results

Introduction

This year Stars has proposed new results related to its three main research axes : perception for activity recognition, semantic activity recognition and software engineering for activity recognition.

Perception for Activity Recognition

Participants : Piotr Bilinski, François Brémond, Etienne Corvée, Antitza Dancheva, Furqan Muhammad Khan, Michal Koperski, Thi Lan Anh Nguyen, Javier Ortiz, Remi Trichet, Jana Trojanova, Ujjwal Ujjval.

The new results for perception for activity recognition are:

• Exploring Depth Information for Head Detection with Depth Images (see 6.2)

• Modeling Spatial Layout of Features for Real World Scenario RGB-D Action Recognition (see 6.3)

• Multi-Object Tracking of Pedestrian Driven by Context (see 6.4)

• Pedestrian detection: Training set optimization (see 6.5)

• Pedestrian Detection on Crossroads (see 6.6)

• Automated Healthcare: Facial-expression-analysis for Alzheimer's patients in Musical Mnemotherapy (see 6.7)

• Hybrid Approaches for Gender estimation (see 6.8)

• Unsupervised Metric Learning for Multi-shot Person Re-identification (see 6.9)

Semantic Activity Recognition

Participants : François Brémond, Carlos Fernando Crispim Junior, Michal Koperski, Farhood Negin, Thanh Hung Nguyen, Philippe Robert.

For this research axis, the contributions are :

• Semi-supervised Understanding of Complex Activities in Large-scale Datasets (see 6.10)

• On the Study of the Visual Behavioral Roots of Alzheimer's disease (see 6.11)

• Uncertainty Modeling with Ontological Models and Probabilistic Logic Programming (see 6.12)

• A Hybrid Framework for Online Recognition of Activities of Daily Living In Real-World Settings (see 6.13)

• Praxis and Gesture Recognition (see 6.14)

Software Engineering for Activity Recognition

Participants : Sabine Moisan, Annie Ressouche, Jean-Paul Rigault, Ines Sarray, Daniel Gaffé, Rachid Guerchouche, Matias Marin, Etienne Corvée, Julien Badie, Manikandan Bakthavatchalam, Vasanth Bathrinarayanan, Ghada Balhoul, Anais Ducoffe, Jean Yves Tigli, François Brémond.

The contributions for this research axis are:

• Scenario Recognition (see 6.15)

• The clem Workflow (see 6.16)

• Safe Composition in Middleware for Internet of Things (see 6.17)

• Verification of Temporal Properties of Neuronal Archetype (see 6.18)

• Dynamic Reconfiguration of Feature Models (see 6.19)

• Setup and management of SafEE devices (see 6.20)

• Brick & Mortar Cookies (see 6.21)