Marianna Madry Postal address CVAP/ CSC/ KTH SE-100 44, Stockholm Sweden Office address Room 619 Teknikringen 14 Stockholm Phone +46 8 790 6353 Fax +46 8 723 0302 E-mail Research Teaching Publications I am a Ph.D. student at the Computer Vision and Active Perception Lab at the Royal Institute of Technology (KTH) in Stockholm, Sweden. My supervisors are Danica Kragic and Carl Henrik Ek. I am involved in the EU project GRASP that is directed towards the development of a cognitive system capable of performing grasping and manipulation tasks. Research Top My research lies between the field of computer vision and robotics. I am working on designing an object class recognition (categorization) system based on visual cues for use on robot equipped with object manipulation capabilities. I am particularly interested in topics such as: single and multi-view object representation; active object recognition and categorization; scene reconstruction. My current work focuses on a problem of categorization of household objects for task-constrained grasping based on both 2D (RGB images) and 3D (extracted point cloud) visual information. The main idea is to enable transfer of grasp knowledge between objects that share similar physical properties and functionality. More about this work can be found here. Teaching Top Currently, I am a teaching assistant for the undergraduate course: DD2423 Image Processing and Computer Vision. I am also involved in organizing the PhD-level course: FDD3315 Multiple View Geometry in Computer Vision. Publications Top Peer Reviewed Conference Papers M. Madry, D. Song, D. Kragic. From Object Categories to Grasp Transfer Using Probabilistic Reasoning. In IEEE International Conference on Robotics and Automation (ICRA 2012), May 2012. To appear R. Detry, C.H. Ek, M. Madry, J. Piater, D. Kragic. Generalizing Grasps Across Partly Similar Objects. In IEEE International Conference on Robotics and Automation (ICRA 2012), May 2012. To appear Monographies M. Madry-Pronobis. Automatic gender recognition based on audio-visual cues. Master's thesis, Sound and Image Processing Laboratory, School of Electrical Engineering, Royal Institute of Technology, Stockholm, Sweden, XR-EE-SIP 2009:006, May 2009. Technical Reports M. Pronobis and M. Magimai.-Doss. Integrating audio and vision for robust automatic gender recognition. IDIAP Technical Report, Idiap-RR-73-2008, Idiap, November 2008. M. Pronobis and M. Magimai.-Doss. Analysis of F0 and cepstral features for robust automatic gender recognition. IDIAP Technical Report, Idiap-RR-30-2009, Idiap, September 2009. Created by: Marianna Madry, Photo by: Kasia Sliwa Last modified: 23-01-2012 14:02