Carl Vondrick

Ph.D. Student
Massachusetts Institute of Technology
Email: vondrick@mit.edu

ResumeGithubScholarCalendar

About Me

I am a Ph.D. student at MIT. My research studies computer vision and machine learning.

I work at CSAIL where I am advised by Antonio Torralba. Previously, I was at UC Irvine advised by Deva Ramanan. I have spent some summers at Google and Google X.

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

Projects

Leveraging Unlabeled Data and Weakly Labeled Data

There is an abundance of unlabeled data available to us that contain rich signals about the world. We hope to leverage this resource to expand the capabilities of visual models.

Anticipating Visual Representations with Unlabeled Video
Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
CVPR 2016
Paper Press: New York Times CNN Wired MIT News

Predicting Motivations of Actions by Leveraging Text
Carl Vondrick, Deniz Oktay, Hamed Pirsiavash, Antonio Torralba
CVPR 2016
Paper

Learning Aligned Cross-Modal Representations from Weakly Aligned Data
Lluis Castrejon*, Yusuf Aytar*, Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
CVPR 2016
Paper Project Page


Human Activity Understanding

The ability to understand what other people do is crucial in our everyday life. We are interested in developing visual models for machines to reason about people's activities.

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

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

See also: Anticipating Visual Representations with Unlabeled Video

See also: Predicting Motivations of Actions by Leveraging Text


Diagnosing Computer Vision Models

In order to improve upon computer vision models, it is instructive to first understand and diagnose their failures. We are interested in methods to analyze and visualize what computer vision models have learned.

Visualizing Object Detection Features
Carl Vondrick, Aditya Khosla, Hamed Pirsiavash, Tomasz Malisiewicz, Antonio Torralba
IJCV 2016
Paper Project Page Slides Press: MIT News

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

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

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


Efficient Video Annotation

Large labeled datasets have enabled significant advancements in image understanding. However, there has not been as much progress in video understanding, possibly because labeled video data is much more expensive to annotate. We seek to develop better methods to annotate video efficiently.

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
Paper Data + Code

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