PI
Core/Dual

Antonio Torralba

Professor

Phone

324-0900

Room

32/ -D462

Antonio Torralba is an Assistant Professor of Electrical Engineering and Computer Science and a member of the Computer Science and Artificial Intelligence Lab. He is a Telecommunication Engineer by the Technical University of Catalonia (Spain) since 1995. He received his Ph.D. from Grenoble Institute of Technology (France) in 2000. His research interests span computer and human vision, computer graphics and machine learning. His particular areas of interest include object and scene recognition, large image databases, applied machine learning, and the role of context in visual perception.

Projects

Project

Understanding Health Habits from Social Media Pictures

Group

Human-Computer Interaction
We focus on learning combined modalities (cooking recipes and food images), analyzing differences in how a machine would objectively label an image compared to how a human subjectively does, and estimating the population health level from social media images.

Amaia Salvador

Enes Kocabey

Mustafa Camurcu

+3

Ingmar Weber

Leads

Ingmar Weber

Research Areas

Project

VirtualHome: Representing Activities as Programs

Group

Human-Computer Interaction
We aim to create a virtual environment where agents learn to perform human tasks by executing programs. Furthermore, we aim to develop models that can generate such programs from video or text, enabling agents to understand and imitate such activities.
Torralba

Sanja Fidler

Kevin Ra

+4

Project

Neural Physics Engine

We've developed an object-based neural network architecture for learning predictive models of intuitive physics that extrapolates to variable object count and variable scene configurations with only spatially and temporally local computation.
Torralba
Tenenbaum

Leads

 8 More

Groups

News

Learning words from pictures

Speech recognition systems, such as those that convert speech to text on cellphones, are generally the result of machine learning. A computer pores through thousands or even millions of audio files and their transcriptions, and learns which acoustic features correspond to which typed words.But transcribing recordings is costly, time-consuming work, which has limited speech recognition to a small subset of languages spoken in wealthy nations.