On November 9th, 2017, I will defend my Ph.D. thesis in Computer Science (Computer Vision) from the INRIA and from the University of Nice Sophia-Antipolis, France. The topic of my Ph.D. is “Human Action Recognition in Videos with Local Representation”. All the research involved in my thesis was conducted at INRIA under the supervision of Francois Bremond.

The jury of my Ph.D. defense is:

  • Frederic Precioso, Professor, University of Nice Sophia-Antipolis, president,
  • Matthieu Cord, Professor, Pierre and Marie Curie University, reviewer,
  • Leonid Sigal, Professor, University of British Columbia, reviewer,
  • Jean-Marc Odobez, Professor, IDIAP, examinator,
  • Francois Bremond, Research Director, INRIA (STARS), advisor.


Action Recognition based on a mixture of RGB and Depth based skeleton
In AVSS, 2017.

Groups Re-identification with Temporal Context
In ICMR, 2017.

PDF Bibtex

Modeling Spatial Layout of Features for Real World Scenario RGB-D Action Recognition
In AVSS, 2016.

PDF Bibtex

A Hybrid Framework for Online Recognition of Activities of Daily Living In Real-World Settings
In AVSS, 2016.


Second-order temporal concept composites for complex activity understanding
In AVSS, 2016.

PDF Bibtex

Generating Unsupervised Models for Online Long-Term Daily Living Activity Recognition
In ACPR, 2015.

PDF Bibtex

Minimizing Hallucination in Histogram of Oriented Gradients
In AVSS, 2015.

PDF Bibtex

3D Trajectories for Action Recognition
In ICIP, 2014.

PDF Bibtex

Representing Visual Appearance by Video Brownian Covariance Descriptor for Human Action Recognition
In AVSS, 2014.

PDF Bibtex

Distributed standalone mobile data providers for BirdWatch system
NAKOM (ISBN: 978-83-89529-82-4), 2011.


The demo shows real-time action detection framework for daily-living patient monitoring.