Christian WOLF is associate professor (Maitre de Conférences, HDR) at INSA de Lyon and LIRIS UMR 5205, a CNRS laboratory, since 2005. He is interested in computer vision and machine learning, especially in the visual analysis of complex scenes in motion: gesture and activity recognition and pose estimation. In his work he puts an emphasis on models of complex interactions, on structured models, graphical models and on deep learning. He received his MSc in computer science from Vienna University of Technology (TU Wien) in 2000, and a PhD in computer science from INSA de Lyon, France, in 2003. In 2012 he obtained the habilitation diploma, also from INSA de Lyon.
Funded Master position / Sujet Master 2 recherche en machine learning :
(French) : Apprentissage par Renforcement Profond (Deep Reinforcement Learning) appliqué à la perception active par une flotte de robots mobiles [PDF]
In the press:
- 05.04.2016: In the CNRS journal on automatic authentification of smartphone users with Deep Learning
- 11.03.2016: In "Industrie & Technologies" on AI and Deep Learning [direct link]
- 25.07.2015: In "Le monde" on Deep Learning [direct link][saved-pdf]
- 28.04.2011: In "Usine Nouvelle" on Kinect [pdf]
- 28.01.2011: In "Millenaire 3" on robotics [pdf]
- 10.03.2010: In "Le monde" on video surveillance [pdf]
Recent committee participations
- 50% premier cycle department (head of the 2nd year computer science program)
- 50% computer science department
- Read more...
Teaching: exchange France - Austria
Current and former PhD Students:
- Fabien Baradel (10/2016-); Deep Learning of invariant representations for activity recognition (co-supervised with Julien Mille (INSA Val de Loire)).
- Leo Vetter (10/2016-); Deep Learning and video indexing (co-supervised with Elöd Egyed-Zsigmond (LIRIS/INSA-Lyon)).
- Bastien Moysset (10/2014-); Document analysis by deep learning (co-supervised with Christopher Kermorvant (A2IA/Teklia)).
- Damien Fourure (10/2014-); Learning deep representations of videos (co-supervised with Alain Tremeau, Rémi Emonet, Elisa Fromont, Damien Muselet (all LHC,Saint-Etienne)).
- Emre Dogan (01/2013-); Joint recognition of human activities by multiple robots (co-supervised with Atilla Baskurt (LIRIS/INSA-Lyon) and Gönen Eren (Galatasaray University, Istanbul))
- Natalia Neverova (10/2012-04/2016); Deep Learning for Human Motion Analysis (co-supervised with Graham W. Taylor ( University of Guelph, Canada)); [pdf-thesis]; current position: post-doc at Facebook AI Research.
- Alaeddine Mihoub (1.10.2012-8.10.2015); Attention et communication homme-robot dans des tâches de co-manipulation
(co-supervised with Gerard Bailly (Gipsalab, Grenoble)); [pdf-thesis]; current position: post-doc at Orange Labs RD.
- Jiu Mingyuan (01.10.2010-03.04.2014); Spatial information and end-to-end training for visual recognition (co-supervised with Atilla Baskurt (LIRIS/INSA-Lyon)); [pdf-thesis]; current position: post-doc at ENS Lyon.
- Oya Celiktutan (01.01.2011-06.09.2013); Action recognition in videos (co-supervised with Bülent Sankur (Bogazici University, Istanbul)); current position: post-doc at Cambridge University, UK.
- Moez Baccouche (01.10.2009-15.07.2012);
Video indexation taking into account human behavior (co-supervised with Frank Mamalet (Orange Labs), Christophe Garcia and Atilla Baskurt (both LIRIS/INSA-Lyon)); [pdf-thesis]; current position: researcher at Orange Labs R&D.
- Vincent Vidal(01.10.2008-09.12.2011); Remeshing and mesh simplification with probabilistic graphical models (co-supervised with Florent Dupont (LIRIS/University Lyon 1)); current position: assistant professor (MCF) at LIRIS laboratory; [pdf-thesis]
- Anh-Phuong TA (01.02.2008-26.11.2010);
Inexact graph matching and it's application to objet detection and action recognition (co-supervised with Guillaume Lavoué and Atilla Baskurt (both LIRIS/INSA-Lyon)); [pdf-thesis]
- Maxime Meyer (02/2016-); on activity recognition in a mobile robotics environment using machine learning and knowledge transfer.
Former post-doctoral Students:
- Rizwan Khan (12/2013-11/2014); Semantic labelling of HD videos taken from occulometric eye-glasses
(co-supervised with J. Mille)
Ongoing research projects
French-Canadian project ANR/NSERC "DeepVision" has been accepted. It involves 4 partners: LIRIS/INSA-Lyon, LIP6/UPMC, University of Guelph, Simon Fraser University.
Investissements d'Avenir: "INTERABOT"; gesture and object recognition in mobile robotics environment (5/2012-5/2016).
ANR blanc "Solstice"; graphes and structured models for computer vision (2013 - 2017).
Completed research projects
Labex IMU "RIVIERE"; semantic labeling of HD videos acquire from portable eyetracking glasses (2013 - 2015).
BQR INSA "CROME"; Multi-view multi-robot scene understanding and fleet coordination (2014 - 2016).
ANR Canada (2007-2010) - Comportements Anormaux : Analyse, Détection, Alerte
ANR Madras (2008-2011) - 3D Models And Dynamic models Representation And Segmentation
ANR Sattic (2007-2011) - Strings and Trees for Thumbnail Images Classification.
LIRIS-VISION / Starling
Starling is a graphical tool to build simple computer-vision applications developed and maintained by the LIRIS research laboratory and its 3 computer vision teams
Upcoming conferences and journal special issues:
- C ICLR 2017
DL: 4.11.2016; Event: 24.4.-27.4.2017, Toulon, FR.
- C CVPR 2017
DL: 15.11.2016; Event: July 21-26, Honolulu/Hawai, US.
- J ACM Transactions on Multimedia Computing, Communications and Applications special issue on Representation, Analysis and Recognition of 3D Humans
- J ACM Transactions on Interactive Intelligent Systems Special Issue on Interactive Visual Analysis of Human and Crowd Behaviors
- IET Computer Vision special Issue on Deep Learning in Computer Vision
- C ICCV 2017
DL: 17.3.2017; Event: October 22-29, Venice, IT.
- C AVSS 2017
DL: 5.4.2017; Event: 30.8.-1.9.2017, Lecce, IT.
- C BMVC 2017
DL: 2.5.2017; Event: 4.9.-7.9.2017, London, UK.
Email: christian.wolf (at) insa-lyon.fr
Tel: +33 4 72 43 63 08
Université de Lyon, INSA de Lyon
LIRIS UMR 5205
Bât. Jules Verne
20, Avenue Albert Einstein
69621 Villeurbanne cedex, France
Map - how to come here
When your only tool is a hammer, every problem looks like a nail