Speaker: Dr. Sanja Fidler, University of Toronto
Title: Towards perceptual machines that see, communicate, and reason
Integrating multiple modalities is crucial in order to develop cognitive systems with full autonomy. A successful system needs to semantically parse the visual world, localize itself, and importantly, interact with humans in a natural way. To make this possible, we need holistic models that can capture dependencies across domains and tasks. In this talk, I’ll show how to go from pixels to objects, from objects to complete interpretations of the visual scene, and from the scene to the living environment. These visual representations can then be naturally connected with language. Finally, I’ll show how language can be exploited to link high level semantic concepts and visual perception.
Sanja Fidler is an Assistant Professor at the Department of Computer Science, University of Toronto. Previously she was a Research Assistant Professor at TTI-Chicago, a philanthropically endowed academic institute located in the campus of the University of Chicago. She was a postdoctoral fellow at University of Toronto during 2011-2012. She completed her PhD in computer science at University of Ljubljana in 2010, and was a visiting student at UC Berkeley in the final year of her PhD. She is serving as an Area Chair in the upcoming CVPR’16, EMNLP’16 and ACCV’16, and as a Program Chair of 3DV’16. Her main research interests are object recognition, 3D scene understanding, and combining vision and language.