Antonio
Torralba


Associate Professor

Computer Science and Artificial Intelligence Laboratory
Dept. of Electrical Engineering and Computer Science
Massachusetts Institute of Technology

Office: 32-D432, 32 Vassar Street
             Cambridge, MA 02139

 

 

My research is in the areas of computer vision, machine learning and human visual perception. I am interested in scene and object recognition, among other things. Scene and object recognition are two related visual tasks generally studied separately. However, by devising systems that solve these tasks in an integrated fashion I believe it is possible to build more efficient and robust recognition systems.

 

News

Alyosha Efros and I are guest-editing an IJCV special issue on Big Visual Data
Submission Deadline: Extended to May 31st, 2013.

Check the LabelMe App for iPhone and iPad. The app connects with your account online and allows you to take pictures and label them on the device. You can then recover the images and anotations with the LabelMe matlab toolbox. Developed by Dolores Blanco, Aina Torralba, David Way and Antonio Torralba.


 

Lab members

Aditya Khosla (Grad. student)

Agata Lapedriza (Visiting professor, UOC)

Andrew Owens (Grad. student with Bill Freeman)

Carl Vondrick (Grad. student)

Hamed Pirsiavash (Post-doctoral Fellow)

Jianxiong Xiao (Grad. student)

Josep Marc Mingot Hidalgo (Visiting student, UPC)

Joseph J. Lim (Grad. student)

Tomasz Malisiewicz (Post-doctoral Fellow)

Zoya Gavrilov (Grad. Student)

Past students and visitors

Dolores Blanco Almazan (Visiting student, 2012), Biliana Kaneva (Graduated 2011), Jenny Yuen (Graduated 2011), Tilke Judd (Graduated 2011) Myung "Jin" Choi (Graduated 2011), James Hays (Post-doctoral Fellow), Hector J.Bernal (Visiting student), Gunhee Kim (Visiting student), Bryan C. Russell (Graduated 2008).

Databases

SUN Database. Scene UNderstanding Database. A database for scene recognition (900 scene categories) and multiclass object detection (>15000 fully segmented images).
Xiao et al, CVPR 2010. (pdf)

360-SUN Database. A database of 360 degrees panoramas organized along the SUN categories.
Xiao et al, CVPR 2012. (pdf)

LabelMe video: You can help us extending the LabelMe database to include also annotated videos by contributing short video clips. Visit our video collection challenge.
Jenny Yuen et al, ICCV 09. (pdf)

LabelMe: the open annotation tool: Help us building a large database of annotated images. Explore the online query tool, Matlab toolbox, Wordnet hierarchy, and the LabelMe gallery.
Bryan Russell, Antonio Torralba and William T. Freeman

80 Million tiny images: explore a dense sampling of the visual world
Antonio Torralba, Rob Fergus, William T. Freeman

Indoor Scene Recognition Database: 67 indoor scene categories
A. Quattoni, and A.Torralba.
CVPR 2009.

Resources

Scene Understanding Symposium (SUnS)
Aude Oliva, Thomas Serre, Antonio Torralba
2006, 2007, 2008, 2009, 2011.

Course on Recognizing and Learning Object Categories
Li Fei-Fei, Rob Fergus, Antonio Torralba
ICCV 2005, CVPR 2007.

The context challenge: How far can you go before having to run an object detector?


Gallery: A selection of some of the images that I like the most resulting from the research.



Code

Gist, scene recognition


A simple object detector with boosting


Eye movements and attention


LabelMe toolbox,
3D LabelMe toolbox,
Video LabelMe toolbox


SIFT Flow



Teaching

6.869 Advances in Computer Vision Fall 2012.

6.870 Grounding Object Recognition and Scene Understanding, Fall 2011.

6.869 Advances in Computer Vision, (updated class material), Spring 2011.

6.869 Advances in Computer Vision, Spring 2010.

6.870 Object Recognition and Scene Understanding, Fall 2008.

6.01 Introduction to EECS I, Spring 2008.

6.003 Signals and Systems, Fall 2007.

Publications

2012

Notes on image annotation
A. Barriuso and A. Torralba
arXiv:1210.3448 [cs.CV] (unreferred).

Localizing 3D Cuboids in Single-view Images
J. Xiao, B. C. Russell, and A. Torralba
Advances in Neural Information Processing Systems 25 (NIPS2012).

Memorability of Image Regions
A. Khosla, J. Xiao, A. Torralba and A. Oliva
Advances in Neural Information Processing Systems 25 (NIPS2012).

Undoing the Damage of Dataset Bias
Aditya Khosla, Tinghui Zhou, Tomasz Malisiewicz, Alexei A. Efros, and Antonio Torralba
European Conference on Computer Vision (ECCV), 2012.

Multidimensional Spectral Hashing
Y. Weiss, Rob Fergus, and Antonio Torralba
European Conference on Computer Vision (ECCV), 2012.

Recognizing Scene Viewpoint using Panoramic Place Representation
J. Xiao, K. A. Ehinger, A. Oliva and A. Torralba
Proceedings of 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)
Project page and SUN360 database

Accidental pinhole and pinspeck cameras: revealing the scene outside the picture
A. Torralba and W. T. Freeman
Proceedings of 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)
Talk | Project page | paper.pdf

Context Models and Out-of-context Objects
Myung Jin Choi, Antonio Torralba, and Alan S. Willsky
Pattern Recognition Letters, Volume 33, Issue 7, 1 May 2012, Pages 853-862.
Project page and database of out of context objects

2011

Nonparametric Scene Parsing via Label Transfer
C. Liu, J. Yuen and A. Torralba
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol 33, No. 12, 2011.
Project page

Transfer Learning by Borrowing Examples for Multiclass Object Detection
J. J. Lim, R. Salakhutdinov, A. Torralba
NIPS, 2011, Granada, Spain
Project page

Understanding the intrinsic memorability of images
P. Isola, D. Parikh, A. Torralba, A. Oliva
NIPS, 2011, Granada, Spain
Project page

Learning to Learn with Compound Hierarchical-Deep Models
R. Salakhutdinov, J. Tenenbaum , A. Torralba
NIPS, 2011, Granada, Spain

Evaluation of Image Features Using a Photorealistic Virtual World
B. Kaneva, A. Torralba, W.T. Freeman
ICCV, 2011, Barcelona, Spain

What makes an image memorable?
P. Isola, J. Xiao, A. Torralba, A. Oliva
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
Project page

Learning to Share Visual Appearance for Multiclass Object Detection
R. Salakhutdinov, A. Torralba, J. Tenenbaum
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.

Unbiased Look at Dataset Bias
A. Torralba, A. Efros
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.

A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video
Sangmin Oh, Anthony Hoogs, A.G.Amitha Perera, Chia-Chih Chen, Jong Taek Lee, Jake Aggarwal, Hyungtae Lee, Larry Davis, Xiaoyang Wang, Eran Swears, Qiang Ji, Kishore Reddy, Mubarak Shah, Carl Vondrick, Hamed Pirsiavash, Deva Ramanan, Jenny Yuen, Antonio Torralba, Bi Song, Anesco Fong, Amit Roy-Chowdhury, Mita Desai
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.

Fixations on Low-Resolution Images
T. Judd, F. Durand, A. Torralba
Journal of Vision, April 25, 2011 vol. 11 no. 4 article 14.
Project page | Play fixations

Estimating scene typicality from human ratings and image features
Ehinger, K. A., Xiao, J., Torralba, A., & Oliva, A.
Proceedings of the 33rd Annual Conference of the Cognitive Science Society, Boston, MA: Cognitive Science Society 2011, in press.

SIFT Flow: Dense Correspondence across Scenes and Its Applications
Ce Liu, Jenny Yuen, Antonio Torralba
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 978-994, May 2011.
Project page

How little do we need for 3-D shape perception?
Nandakumar C., Torralba A., Malik J.
Perception 40(3) 257 – 271, 2011.

2010

A data-driven approach for event prediction
Jenny Yuen, Antonio Torralba
European Conference on Computer Vision (ECCV), 2010.

Semantic Label Sharing for Learning with Many Categories
Rob Fergus, Hector Bernal, Yair Weiss, Antonio Torralba
European Conference on Computer Vision (ECCV), 2010.

Modeling and Analysis of Dynamic Behaviors of Web Image Collections
K. Gunhee, E. Xing, A. Torralba
European Conference on Computer Vision (ECCV), 2010.
Project page

Matching and Predicting Street Level Images
B. Kaneva, J. Sivic, A. Torralba, S. Avidan, W. T. Freeman
Workshop for Vision on Cognitive Tasks, ECCV 2010.

Exploiting Hierarchical Context on a Large Database of Object Categories
Myung Jin Choi, Joseph Lim, Antonio Torralba, and Alan S. Willsky
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.
SUN Database, object annotations and precomputed detectors

SUN Database: Large Scale Scene Recognition from Abbey to Zoo
Jianxiong Xiao, James Hays, Krista Ehinger, Aude Oliva, and Antonio Torralba
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.
SUN Database, scene recognition benchmark

Part and Appearance Sharing: Recursive Compositional Models for Multi-View Multi-Object Detection
Leo Zhu, Yuanhao Chen, Antonio Torralba, William Freeman, and Alan Yuille
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010.

Using the forest to see the trees: object recognition in context
A. Torralba, K. Murphy, W. T. Freeman
Communications of the ACM, Research Highlights, 53(3): 107-114, 2010.

LabelMe: online image annotation and applications
A. Torralba, B. C. Russell, J. Yuen
Proceedings of the IEEE, Vol. 98, n. 8, pp. 1467 – 1484, August 2010.

Infinite Images: Creating and Exploring a Large Photorealistic Virtual Space
B. Kaneva, J. Sivic, A. Torralba, S. Avidan, W. T. Freeman
Proceedings of the IEEE, Vol. 98, n. 8, pp. 1391-1407, August 2010.

2009

Semi-supervised Learning in Gigantic Image Collections
R. Fergus, Y. Weiss, and A. Torralba
Advances in Neural Information Processing Systems, 2009.

Unsupervised Detection of Regions of Interest Using Iterative Link Analysis
G. Kim, and A. Torralba
Advances in Neural Information Processing Systems, 2009.
Project page

Nonparametric Bayesian Texture Learning and Synthesis
Long Zhu, Yuanhao Chen, William Freeman, and Antonio Torralba
Advances in Neural Information Processing Systems, 2009.

LabelMe video: building a video database with human annotations
J. Yuen, B. C. Russell, C. Liu, and A. Torralba
IEEE International Conference on Computer Vision (ICCV), 2009.

Learning to predict where humans look
T. Judd, K. Ehinger, F. Durand, and A. Torralba
IEEE International Conference on Computer Vision (ICCV), 2009.
Project page

Nonparametric scene parsing: label transfer via dense scene alignment
C. Liu, J. Yuen, A. Torralba
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.

Recognizing indoor scenes
A. Quattoni, and A.Torralba
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.

Building a database of 3D scenes from user annotations
B. C. Russell and A. Torralba
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.
Project website |

Modelling search for people in 900 scenes: a combined source model of eye guidance
K. Ehinger, B. Hidalgo-Sotelo, A. Torralba, and A. Oliva
Visual Cognition, Vol. 17, Issue 6 & 7 August 2009 , pages 945 - 978, 2009.
Project page

How many pixels make an image?
A. Torralba
Visual Neuroscience, volume 26, issue 01, pp. 123-131, 2009.

2008

Spectral Hashing
Y. Weiss, A. Torralba, R. Fergus
Advances in Neural Information Processing Systems, 2008.
Project page | LabelMe data and GIST

SIFT flow: dense correspondence across different scenes
C. Liu, J. Yuen, A. Torralba, J. Sivic, and W. T. Freeman
European Conference on Computer Vision (ECCV), 2008.
Project page

Small codes and large databases for recognition
A. Torralba, R. Fergus, Y. Weiss
IEEE Computer Vision and Pattern Recognition, June 2008.
Project page | code

Creating and exploring a large photorealistic virtual space
J. Sivic, B. Kaneva, A. Torralba, S. Avidan and W. T. Freeman
First IEEE Workshop on Internet Vision, associated with CVPR 2008.

80 million tiny images: a large dataset for non-parametric object and scene recognition
A. Torralba, R. Fergus, W. T. Freeman
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.30(11), pp. 1958-1970, 2008.
Project page

Describing Visual Scenes Using Transformed Objects and Parts
E. Sudderth, A. Torralba, W. T. Freeman, and A. Willsky.
International Journal of Computer Vision, No. 1-3, May 2008, pp. 291-330.
Project page

LabelMe: a database and web-based tool for image annotation
B. Russell, A. Torralba, K. Murphy, W. T. Freeman
International Journal of Computer Vision, pages 157-173, Volume 77, Numbers 1-3, May, 2008.
Project page

2007

Sharing visual features for multiclass and multiview object detection
A. Torralba, K. P. Murphy and W. T. Freeman
IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 29, no. 5, pp. 854-869, May, 2007.
Code | bibtex

The role of context in object recognition
A. Oliva, A. Torralba
Trends in Cognitive Sciences, vol. 11(12), pp. 520-527. December 2007.

Object Recognition by Scene Alignment
B. C. Russell, A. Torralba, C. Liu, R. Fergus, W. T. Freeman.
Advances in Neural Information Processing Systems, 2007.
Project page

2006

Contextual Guidance of Attention in Natural scenes: The role of Global features on object search
A. Torralba, A. Oliva, M. Castelhano and J. M. Henderson
Psychological Review. Vol 113(4) 766-786, Oct, 2006.
Project page

Depth from Familiar Objects: A Hierarchical Model for 3D Scenes
E. Sudderth, A. Torralba, W. T. Freeman, and A. Wilsky
CVPR, June 2006.
Dataset

Hybrid images
A. Oliva, A. Torralba and P. Schyns
ACM Transactions on Graphics, ACM Siggraph, 25-3, pp. 527-530. 2006.

Random Lens Imaging
R. Fergus, A. Torralba, W. T. Freeman
MIT CSAIL Technical Report 2006-058, 2006.

Building the Gist of a Scene: The Role of Global Image Features in Recognition
A. Oliva, and A. Torralba
Visual Perception, Progress in Brain Research, vol 155. 2006.

Dataset Issues in Object Recognition
J. Ponce, T. L. Berg, M. Everingham, D. A. Forsyth, M. Hebert, S. Lazebnik, M. Marszalek, C. Schmid,
B. C. Russell, A. Torralba, C. K. I. Williams, J. Zhang, and A. Zisserman.
In Toward Category-Level Object Recognition. Springer-Verlag Lecture Notes in Computer Science, J. Ponce, M. Hebert, C. Schmid, and A. Zisserman (eds.), 2006.

Object detection and localization using local and global features
K. Murphy, A. Torralba, D. Eaton, W. T. Freeman
In Toward Category-Level Object Recognition. Springer-Verlag Lecture Notes in Computer Science, J. Ponce, M. Hebert, C. Schmid, and A. Zisserman (eds.), 2006.

Shared features for multiclass object detection
A. Torralba, K. P. Murphy, W. T. Freeman
In Toward Category-Level Object Recognition. Springer-Verlag Lecture Notes in Computer Science, J. Ponce, M. Hebert, C. Schmid, and A. Zisserman (eds.), 2006.

2005

Contextual Models for Object Detection using Boosted Random Fields
A. Torralba, K. P. Murphy and W. T. Freeman
Adv. in Neural Information Processing Systems 17 (NIPS), pp. 1401-1408, 2005.
pdf | bibtex

Describing Visual Scenes using Transformed Dirichlet Processes
E. Sudderth, A. Torralba, W. T. Freeman, and A. Wilsky
NIPS 2005.

Learning Hierarchical Models of Scenes, Objects, and Parts
E. Sudderth, A. Torralba, W. T. Freeman, and A. Wilsky
ICCV 2005.

Motion magnification
C. Liu, A. Torralba, W.T. Freeman, F. Durand and E.H. Adelson
ACM Trans. on Graphics, ACM Siggraph, 24-3, pp. 519-526, 2005.

Human Learning of Contextual Priors for Object Search: Where does the time go?
B. Hidalgo-Sotelo, A. Oliva, and A. Torralba
Proceedings of the 3rd Workshop on Attention and Performance in Computer Vision at the Int. CVPR, 2005.

Contextual Influences on Saliency
A. Torralba
Neurobiology of Attention, Eds. L. Itti, G. Rees and J. Tsotsos. Pages 586-593. Academic Press / Elsevier. 2005

An Ensemble Prior of Image Structure for Cross-modal Inference
S. Ravela, A. Torralba, W. T. Freeman
ICCV 2005

2004

Sharing features: efficient boosting procedures for multiclass object detection
A. Torralba, K. P. Murphy and W. T. Freeman
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). pp 762-769, 2004.

Specular reflections and the perception of shape
R. W. Fleming, A. Torralba and E. H. Adelson
Journal of Vision. Volume 4, Number 9, Article 10, Pages 798-820. 2004.

Saliency, objects and scenes: global scene factors in attention and object detection
A. Torralba, A. Oliva, M. Castelhano and J. M. Henderson
Vision Sciences Society Annual Meeting, Sarasota. 2004.

2003

Statistics of natural image categories
A. Torralba and A. Oliva
Network: computation in neural systems, Vol. 14, 391-412. 2003.

Depth estimation from image structure
A. Torralba, A. Oliva
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24(9): 1226-1238. 2003.

Contextual priming for object detection
A. Torralba
International Journal of Computer Vision, Vol. 53(2), 169-191, 2003.

Context-based vision system for place and object recognition
A. Torralba, K. P. Murphy, W. T. Freeman and M. A. Rubin
IEEE Intl. Conference on Computer Vision (ICCV), Nice, France, October 2003.
Code and datasets

Using the forest to see the trees: a graphical model relating features, objects and scenes
P. Murphy, A. Torralba and W. T. Freeman
Adv. in Neural Information Processing Systems 16 (NIPS), Vancouver, BC, MIT Press, 2003.

Modeling global scene factors in attention
A. Torralba
Journal of Optical Society of America A. Special Issue on Bayesian and Statistical Approaches to Vision. Vol. 20(7): 1407-1418, 2003.

Top-down control of visual attention in object detection
A. Oliva, A. Torralba, M. S. Castelhano and J. M. Henderson
Proceedings of the IEEE International Conference on Image Processing. Vol. I, pages 253-256; September 14-17, in Barcelona, Spain, 2003.

Properties and applications of shape recipes
A. Torralba and W. T. Freeman
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, June, 2003.

2002

Scene-Centered Description from Spatial Envelope Properties
A. Oliva, A. Torralba
In Proc. 2nd Workshop on Biologically Motivated Computer Vision (BMCV'02), Tubingen, Germany. 2002.

Shape Recipes: Scene Representations that Refer to the Image
W. T. Freeman, A. Torralba
Adv. in Neural Information Processing Systems 15 (NIPS), MIT Press.

2001

Contextual modulation of target saliency
A. Torralba
Adv. in Neural Information Processing Systems 14 (NIPS), MIT Press, 2001.

Statistical context priming for object detection
A. Torralba, P. Sinha
Proceedings of the International Conference on Computer Vision (ICCV), pp. 763-770, Vancouver, Canada, 2001.

Modeling the shape of the scene: a holistic representation of the spatial envelope
A. Oliva, A. Torralba
International Journal of Computer Vision, Vol. 42(3): 145-175, 2001.
Code | Datasets | LabelMe

Global depth perception from familiar scene structure
A. Torralba, A. Oliva
AI-Memo 2001-036, CBCL Memo 213, 2001.

Indoor scene recognition
A. Torralba, P. Sinha
AI Memo 2001-015, CBCL Memo 202, 2001

Detecting faces in impoverished images
A. Torralba, P. Sinha
AI Memo 2001-028, CBCL Memo 208, 2001.

Shape from sheen. Three dimensional shape perception
R. W. Fleming, A. Torralba, and E. H. Adelson
(Eds.) Zaidi, Q., Springer

An efficient neuromorphic analog network for motion estimation
A. Torralba, J. Hérault
IEEE Transactions on Circuits and Systems-I. Special Issue on Bio-Inspired Processors and CNNs for Vision. Vol. 46(2): 269-280, 1999.

Semantic organization of scenes using discriminant structural templates
A. Torralba, A. Oliva
Proceedings of the International Conference on Computer Vision, pp. 1253-1258, Korfu, Grece, 1999.