Carl Vondrick

Ph.D. Student
Massachusetts Institute of Technology


About Me

I am a computer science Ph.D. student at MIT. My research focuses on problems in computer vision and machine learning. I aim to build intelligent systems by combining knowledge from humans with machines.

I work at CSAIL where I am advised by Antonio Torralba. Previously, I was at UC Irvine advised by Deva Ramanan. I have done summer internships at Google Maps and Google X.

Thank you to Google and the NSF for supporting my research!


Classifiers from Human Imagination How to learn biases from the human visual
system and plug them into a machine.

Project Page

Anticipating the Future By watching large amounts of unlabeled video,
we train models to anticipate human actions.

Learn More

Judging People's Actions Algorithms that estimate how well people perform
actions and offers suggestions to improve.

Learn More

Inferring Motivations of People Mining commonsense knowledge to predict
why people in images are performing actions.

Learn More

iHOG: Feature Visualization Tool Tool to visualize feature spaces
commonly used in object detection.

Code Examples Demo

vatic: Video Annotation Tool Interactive tool to efficiently annotate
massive videos on Mechanical Turk.

Project Page


Learning Visual Biases from Human Imagination
Carl Vondrick, Hamed Pirsiavash, Aude Oliva, Antonio Torralba
NIPS 2015
Paper Project Page Technology Review Vice Magazine

Where are they looking?
Adria Recasens*, Aditya Khosla*, Carl Vondrick, Antonio Torralba *equal contribution
NIPS 2015
Paper Project Page Demo

Anticipating the Future by Watching Unlabeled Video
Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
arXiv 2015
Paper Project Page

Do We Need More Training Data?
Xiangxin Zhu, Carl Vondrick, Charless C. Fowlkes, Deva Ramanan
IJCV 2015
Paper 10x Data

Visualizing Object Detection Features
Carl Vondrick, Aditya Khosla, Hamed Pirsiavash, Tomasz Malisiewicz, Antonio Torralba
IJCV 2015
Paper Project Page Slides MIT News

Inferring the Why in Images
Carl Vondrick*, Hamed Pirsiavash*, Antonio Torralba *equal contribution
arXiv 2014
Paper Project Page

Assessing the Quality of Actions
Hamed Pirsiavash, Carl Vondrick, Antonio Torralba
ECCV 2014
Paper Code + Data

HOGgles: Visualizing Object Detection Features
Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, Antonio Torralba
ICCV 2013
Paper Project Page Slides MIT News

Do We Need More Training Data or Better Models for Object Detection?
Xiangxin Zhu, Carl Vondrick, Deva Ramanan, Charless C. Fowlkes
BMVC 2012
Paper Slides 10x Data

Efficiently Scaling Up Crowdsourced Video Annotation
Carl Vondrick, Donald Patterson, Deva Ramanan
IJCV 2012
Paper Slides Data + Code

Video Annotation and Tracking with Active Learning
Carl Vondrick, Deva Ramanan
NIPS 2011
Paper Slides Code

A Large-scale Benchmark Dataset for Event Recognition
Sangmin Oh, et al.
CVPR 2011
Paper Slides Data

Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces
Carl Vondrick, Deva Ramanan, Donald Patterson
ECCV 2010
Journal Paper Conference Paper Data + Code


Visualizing Object Detection Features
Carl Vondrick
M.S. Thesis, MIT, 2013
Thesis Code

I'm normally not a praying man, but if you're up there, please save me, Superman. — Homer Simpson