Integrated models of scenes and objects
Mauldin Auditorium (NSH 1305)
Refreshments 3:15 pm
Talk 3:30 pm
Human scene understanding is remarkable: with only a brief glance at an image, an abundance of information is available - spatial layout, scene category, identity of main objects in the scene, etc. In traditional computer vision, scene and object recognition are two related visual tasks generally studied separately. By devising systems that solve these tasks in an integrated fashion it is possible to build more efficient and robust recognition systems. We argue that multi-object recognition systems should be based on models which consider the relationships between different object categories during the training process. This approach provides several benefits. At the lowest level, significant computational savings can be achieved if different categories share a common set of features. More importantly, jointly trained recognition systems can use similarities between object categories to their advantage by learning features which lead to better generalization. This inter-category regularization is particularly important when few training examples are available, as is common in many vision domains. In complex, natural scenes, object recognition systems can be further improved by using contextual knowledge about the objects likely to be found in a given scene, and common spatial relationships between those objects. I will describe how scene information can be used early during the visual processing in order to provide a short cut for object detection and recognition.
is a research scientist at the computer science and artificial intelligence
laboratory at MIT. His main areas of research are human and computer vision.
After high school on the
For appointments, please contact Janice Brochetti (email@example.com)