I am a research associate at the University of Adelaide. I was previously a postdoctoral researcher at Carnegie Mellon University with Martial Hebert. I have also been affiliated with the University of Bath (UK), the Intelligent and Interative Systems lab of the University of Innsbruck (Austria), and the University of Liège (Belgium) where I obtained my PhD in Computer Science (2013), advised by Justus Piater.
My long-term research interests cover the visual recognition of objects, and global scene understanding, to ultimately allow machines to interact with their environment through robotic applications.
My most recent work deals with the use of convolutional neural networks for computer vision, how to reparametrize them and encode vision-specific knowledge to facilitate their training. I previously worked on a variety of topics: motion estimation, video segmentation, recognition of dynamic textures in videos of natural scenes (see the OAK project), object recognition and 3D pose estimation from single images for robotic grasping.