Scene Discovery by Matrix Factorization

Google Tech Talks March, 24 2008 ABSTRACT What constitutes a scene? Defining a meaningful vocabulary for scene discovery is a challenging problem that has important consequences for object recognition. We consider scenes to depict correlated objects and present visual similarity. We introduce a max-margin factorization model that finds a low dimensional subspace with high discriminative power for correlated annotations. We postulate this space should allow us to discover a large number of scenes in unsupervised data; we show scene discrimination results on par with supervised approaches. This model also produces state of the art word prediction results including good annotation completion. Speaker: Ali Farhadi Ali Farhadi is a PhD student in the UIUC Computer Science Department working on computer vision and machine learning under David Forsyth. His interests include image segmentation, transfer learning, scene understanding and human activity recognition.