Teaching computers to see — by learning to see like computers
September 18, 2013By translating images into the language spoken by object-recognition systems, then translating them back, researchers hope to explain the systems’ failures.
Oliva explores new ground in computational perception at CSAIL
November 8, 2011Neuroscientist looks forward to collaborative studies of visual perception in the brain and its computational applications.
How the brain recognizes objects
June 6, 2010A new computational model sheds light on the workings of the human visual system and could help advance artificial-intelligence research, too.
Seeing the forest for the trees
May 6, 2010Object recognition systems that break images into ever smaller parts should be much more efficient and may shed light on how the brain works.
Context is ev … well, something, anyway
March 4, 2010MIT research uses information about how frequently objects are seen together to refine the conclusions of object recognition systems.
October 12, 2009Researchers from MIT's CSAIL teach computers to recognize objects.