Aditya Khosla

I am a third year computer science Ph.D. student at the Massachusetts Institute of Technology. I work at CSAIL with the Computer Vision Group where I am advised by Professor Antonio Torralba, and frequently collaborate with Professor Aude Oliva.

      Email: khosla@csail.mit.edu
      Office: 32-D428
      Curriculum vitae: pdf

I completed my M.S. in computer science at Stanford University with the Stanford Vision Lab where I was advised by Professor Fei-Fei Li. I completed my B.S. with honors in computer science, electrical engineering and economics at the California Institute of Technology where I was advised by Professor Tracey Ho. This academic year, I am being supported by a Facebook Fellowship. Thank you Facebook!


2011 - Present Summer 2013 Summer 2012 2009 - 2011 2005 - 2009

 

Recent News

 

Publications

(complete bibfile, Google Scholar page)

3D ShapeNets for 2.5D Object Recognition and Next-Best-View Prediction
Zhirong Wu, Shuran Song, Aditya Khosla, Xiaoou Tang and Jianxiong Xiao
arXiv:1406.5670, 2014 (under submission).
[paper] [bibtex] [arXiv]

FPM: Fine pose Parts-based Model with 3D CAD Models
Joseph J. Lim, Aditya Khosla and Antonio Torralba
To appear in European Conference on Computer Vision (ECCV), 2014.
[coming soon]

Looking Beyond the Visible Scene
Aditya Khosla, Byoungkwon An, Joseph J. Lim and Antonio Torralba
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
[paper] [bibtex] [project page]

What makes an image popular?
Aditya Khosla, Atish Das Sarma and Raffay Hamid
International World Wide Web Conference (WWW), 2014.
[paper] [bibtex] [slides] [demo/project page]

Integrating Randomization and Discrimination for Classifying Human-Object Interaction Activities
Aditya Khosla, Bangpeng Yao and Li Fei-Fei
Book chapter in Human-Centered Social Media Analytics, Springer, 2014.
[paper] [bibtex] [poster] [slides] [code]
PASCAL VOC Action Classification Winner 2011 & 2012!

Modifying the Memorability of Face Photographs
Aditya Khosla, Wilma A. Bainbridge, Antonio Torralba and Aude Oliva
International Conference on Computer Vision (ICCV), 2013.
[paper] [bibtex] [project page] [new york times]

HOGgles: Visualizing Object Detection Features
Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz and Antonio Torralba
International Conference on Computer Vision (ICCV), 2013.
Oral Presentation
[paper] [bibtex] [project page] [code] [demo] [mit news]

What makes a picture memorable?
Aude Oliva, Phillip Isola, Aditya Khosla and Wilma A. Bainbridge
SPIE Newsroom article, DOI: 10.1117/2.1201304.004806, 7 May 2013.
[paper] [newsroom] [bibtex]

Large-Scale Video Summarization Using Web-Image Priors
Aditya Khosla, Raffay Hamid, Chih-Jen Lin and Neel Sundaresan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
[paper] [bibtex] [project page]

Memorability of Image Regions
Aditya Khosla, Jianxiong Xiao, Antonio Torralba and Aude Oliva
Advances in Neural Information Processing Systems (NIPS), 2012.
[paper] [bibtex] [project page]

Image Memorability and Visual Inception
Aditya Khosla*, Jianxiong Xiao*, Phillip Isola, Antonio Torralba and Aude Oliva (* - indicates equal contribution)
SIGGRAPH Asia, 2012. (Invited paper)
[paper] [bibtex]

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.
[paper] [bibtex] [project page] [code]

Human Action Recognition by Learning Bases of Action Attributes and Parts
Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas J. Guibas, and Li Fei-Fei
International Conference on Computer Vision (ICCV), 2011.
Oral presentation
[paper] [extended paper] [bibtex] [slides] [video] [dataset]

Classifying Actions and Measuring Action Similarity by Modeling the Mutual Context of Objects
and Human Poses

Bangpeng Yao, Aditya Khosla, and Li Fei-Fei
International Conference on Machine Learning (ICML), 2011.
Oral presentation in the cross-conference track
[paper] [bibtex] [slides]

Multimodal Deep Learning
Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y. Ng
International Conference on Machine Learning (ICML), 2011.
Oral presentation
[paper] [bibtex] [poster] [slides]


Combining Randomization and Discrimination for Fine-Grained Image Categorization
Aditya Khosla*, Bangpeng Yao* and Li Fei-Fei (* - indicates equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
[paper] [bibtex] [poster] [slides] [code]
PASCAL VOC Action Classification Winner 2011 & 2012!

An Integrated Machine Learning Approach to Stroke Prediction
Aditya Khosla, Yu Cao, Cliff Chiung-Yu Lin, Hsu-Kuang Chiu, Junling Hu, and Honglak Lee
16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2010.
Oral presentation
[paper] [bibtex] [slides] [video] [code]

On combining information theoretic and cryptographic approaches to network coding security
against the pollution attack

Svitlana Vyetrenko, Aditya Khosla and Tracey Ho
Asilomar Conference on Signals, Systems and Computers (Asilomar), 2009.
[paper] [bibtex]

Towards Real-time Classification of Astronomical Transients
Mahabal, A.; Djorgovski, S. G.; Williams, R.; Drake, A.; Donalek, C.; Graham, M.; Moghaddam, B.;
Turmon, M.; Jewell, J.; Khosla, A.; Hensley, B.
International conference on Classification and Discovery in Large Astronomical Surveys (Class), 2008.
[paper] [bibtex]

Workshops

Novel Dataset for Fine-Grained Image Categorization
Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao and Li Fei-Fei
First Workshop on Fine-Grained Visual Categorization (FGVC), CVPR 2011.
[extended abstract] [bibtex] [poster] [dataset]