Research Field:

Machine learning and computer vision

Research Topics:

• computer vision
• machine learning
• action recognition

Biography

Daniel Weinland joined the Deutsche Telekom Laboratories as a senior research scientist in March 2010. From 2008-2009 he worked as a Postdoctoral Researcher at EPFL, Switzerland, in the Computer Vision Laboratory (CVLAB) and in the Audiovisual Communications Laboratory (LCAV). He received his PhD in mathematics and computer science from INPG, France, in 2008. From 2005–2008 he was working as a research scientist in the Perception team at INRIA Rhône-Alpes, France. Before coming to INRIA, he worked as a research assistant at the University of Mannheim, Germany, in the CVGPR-Group, where he also completed his diploma thesis. His research interests are centered around machine learning and computer vision. In particular he is interested in learning and recognizing human actions/gestures from video sequences.

Address

Quality and Usability Lab
Deutsche Telekom Laboratories
TU Berlin
Ernst-Reuter-Platz 7
D-10587 Berlin, Germany
Tel:  +49 30 8353 58478
Fax: +49 30 8353 58409

Email: <first name>.<last name>@telekom.de

homepage

• IXMAS Action Recognition Dataset (New Address!)
• New: IXMAS Action Recordings with Occlusions! (also contains person centered ROIs from original IXMAS data)
  

• Daniel Weinland, Remi Ronfard, Edmond Boyer
  A Survey of Vision-Based Methods for Action Representation, Segmentation and Recognition
  accepted for publication in Computer Vision and Image Understanding (CVIU) - 2010 (pdf)
• Daniel Weinland, Mustafa Özuysal, Pascal Fua
  Making Action Recognition Robust to Occlusions and Viewpoint Changes
  In Proceedings of the European Conference on Computer Vision (ECCV) - 2010 (pdf, bibtex)
• Daniel Weinland, Remi Ronfard, Edmond Boyer
  A Survey of Vision-Based Methods for Action Representation, Segmentation and Recognition
  INRIA-TechReport, 2010 (pdf, bibtex)
• Nicolas Padoy, Diana Mateus, Daniel Weinland, Marie-Odile Berger, Nassir Navab
  Workflow Monitoring based on Multi-view Reconstruction
  In Proceedings of the ICCV Workshop on Video-Oriented Object and Event Classification (VOEC) - 2009, Best Paper Award (pdf, bibtex)
  
• Daniel Weinland
  Action Representation and Recognition
  PhD Thesis, LJK-INPG Grenoble, October 2008 (pdf, bibtex)
• Daniel Weinland, Edmond Boyer
  Action Recognition using Exemplar-based Embedding
  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - 2008 (pdf, bibtex)
• Daniel Weinland, Edmond Boyer, Remi Ronfard
  Action Recognition from Arbitrary Views using 3D Exemplars
  In Proceedings of the IEEE International Conference on Computer Vision (ICCV) - 2007 (pdf, bibtex)
• Daniel Weinland, Remi Ronfard, Edmond Boyer
  Automatic Discovery of Action Taxonomies from Multiple Views
  In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - 2006 (pdf, bibtex)
• Daniel Weinland, Remi Ronfard, Edmond Boyer
  Free Viewpoint Action Recognition using Motion History Volumes
  Computer Vision and Image Understanding (CVIU), Volume 104, Number 2-3 - November/December 2006 (pdf, bibtex)
• Daniel Weinland, Remi Ronfard, Edmond Boyer
  Motion History Volumes for Free Viewpoint Action Recognition
  In Proceedings of the IEEE International Workshop on modeling People and Human Interaction (PHI'05) - 2005 (pdf, bibtex)
• Najah Hraiech, Daniel Weinland, Kamel Hamrouni
  An Active Contour Model Based on Splines and Separating Forces to Detect the Left Ventricle in Scintigraphic Images
  In Proceedings of the International Conference on Machine Intelligence (ACIDCA-ICMI'2005) - 2005 (pdf, bibtex)