Antonio Torralba



  • Fellow
  • Learning in Machines & Brains


  • Massachusetts Institute of Technology
Department of Electrical Engineering and Computer Science


  • United States


PhD (Signal Image and Speech Processing), Institut national polytechnique de Grenoble
MSc, Institut national polytechnique de Grenoble


Antonio Torralba is a computer scientist who works in artificial intelligence (expert systems, machine learning, robotics).

His research interests span computer and human vision, computer graphics and machine learning, with a focus on the problem of visual scene understanding. His particular areas of interest include object detection and scene recognition, the role of context in visual perception, image and video annotation and applications of large image databases.


J. K. Aggarwal Prize from the International Association for Pattern Recognition, 2010

Best Student Paper Award, IEEE Conference on Computer Vision and Pattern Recognition, 2009

National Science Foundation Career Award, 2008

Relevant Publications

Zhou, B. et al. "Object Detectors Emerge in Deep Scene CNNs." ICLR, 2015.

Zhou, B. et al. "Learning Deep Features for Scene Recognition using Places Database." Advances in Neural Information Processing Systems 27 (NIPS), 2014.

Torralba, A., and W.T. Freeman. "Accidental pinhole and pinspeck cameras. Revealing the scene outside the picture." International Journal of Computer Vision (2014).

Xiao, J. et al. "SUN Database: Exploring a Large Collection of Scene Categories." International Journal of Computer Vision (2014).

Lim, J., A. Khosla, and A. Torralba. "FPM: Fine pose Parts-based Model with 3D CAD models." ECCV, 2014.