James Hays
Computer Science Department
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh, PA 15213-3891
Tel. (401) 829 3921

Email
jhhays@cs.cmu.edu

Webpage
http://www.cs.cmu.edu/~jhhays/

Research Interests
My current research involves using Internet scale data to improve image understanding and manipulation. My interests span computer graphics and computer vision, including image completion, texture analysis and synthesis, animation, place recognition, and object recognition. I'm also interested in the connections between human and machine vision.

Education

Carnegie Mellon University, Pittsburgh, Pennsylvania
    Ph.D. in Computer Science, expected May 2009.

Georgia Institute of Technology, Atlanta, Georgia
    B.S. in Computer Science with Highest honors, Spring 2003.

Research Experience
Carnegie Mellon University, Pittsburgh, Pennsylvania
    Fall 2003 to present
    Member of Graphics lab
    Advised by Alexei Efros Fall 2006 to present.
    Advised by Yanxi Liu Fall 2003 to Summer 2006.

Ecole Normale Supérieure, Paris, France
    Spring 2008.
    Visiting researcher with Willow group.
    Hosted by Jean Ponce and Andrew Zisserman.

Georgia Institute of Technology, Atlanta, Georgia
    Fall 2000 to Spring 2003.
    Member of Computational Perception Lab
    Advised by Irfan Essa.

Refereed Publications
Santosh Divvala, Derek Hoiem, James Hays, Alexei A. Efros, and Martial Hebert.
"An empirical study of Context in Object Detection"
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009.

James Hays and Alexei A. Efros.
"Where in the World? Human and Computer Geolocation of images"
9th Annual Meeting of the Vision Sciences Society. Abstract published in Journal of Vision.

Santosh Divvala, Derek Hoiem, James Hays, Alexei A. Efros, and Martial Hebert
"A Unified Approach for Detection, Classification and Segmentation"
European Conference on Computer Vision (ECCV) 2008, PASCAL VOC 2008 Workshop.

James Hays and Alexei A. Efros.
"Scene Completion Using Millions of Photographs"
Communications of the ACM, 51, 10 (Oct. 2008), 87-94.

James Hays and Alexei A. Efros.
"IM2GPS: estimating geographic information from a single image"
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2008.

Yanxi Liu, Tamara Belkina, James Hays, and Roberto Lublinerman.
"Image De-fencing"
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2008.

James Hays and Alexei A. Efros.
"Scene Completion Using Millions of Photographs"
ACM Transactions on Graphics (SIGGRAPH 2007).

Eugene Zhang, James Hays, and Greg Turk.
"Interactive Tensor Field Design and Visualization on Surfaces"
IEEE Transaction on Visualization and Computer Graphics, 2007, Vol 13(1), pp 94-107.

James Hays, Marius Leordeanu, Alexei A. Efros, and Yanxi Liu.
"Discovering Texture Regularity as a Higher-Order Correspondence Problem"
European Computer Vision Conference (ECCV) 2006.

Wen-Chieh Lin, James Hays, Chenyu Wu, Vivek Kwatra, and Yanxi Liu.
"Quantitative Evaluation of Near Regular Texture Synthesis Algorithms"
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2006.

Yanxi Liu, James Hays, Ying-Qing Xu, and Harry Shum.
"Digital Papercutting"
SIGGRAPH 2005 Sketches.

Yanxi Liu, Wen-Chieh Lin, and James Hays.
"Near-regular Texture Analysis and Manipulation"
ACM Transactions on Graphics (SIGGRAPH 2004), 23(3), August 2004.

James Hays and Irfan Essa.
"Image and Video-based Painterly Animation"
Non-Photorealistic Animation and Rendering 2004 (NPAR '04). pp. 113-120.

Awards

PASCAL Visual Object Class Challenge Honorable Mention, Fall 2008.
National Science Foundation Graduate Research Fellowship, Summer 2004 to Spring 2008.
College of Computing Outstanding Undergraduate Researcher, Spring 2003.
President's Undergraduate Research Award, Fall 2002.
First Place, College of Computing Undergraduate Research Symposium, Spring 2002.
Intel Undergraduate Research Award, Summer 2001.

Activities

Journal Reviewer:
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)
ACM Transactions on Graphics (ToG)
IEEE Computer Graphics and Applications (CGA)
IEEE Transactions on Visualization and Computer Graphics (TVCG)
The Visual Computer

Conference Reviewer:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
European Conference on Computer Vision (ECCV)
ACM SIGGRAPH 2005 through 2008
ACM SIGGRAPH Asia
ACM SIGCHI (Computer-Human Interaction)
Eurographics
Eurographics Symposium on Rendering
Non-photorealistic Animation and Rendering (NPAR)

Teaching Experience

Teaching Assistant for 15-463 Rendering and Image Processing, Carnegie Mellon University
    Fall 2004.

Teaching Assistant for 15-462: Computer Graphics, Carnegie Mellon University
    Spring 2004.

Volunteer Tutor for Georgia Tech Office of Minority Education
    Spring 2002
    Tutored students for introductory Computer Science classes.

Senior Teaching Assistant for CS1321, Georgia Tech
    Fall 2001.
    Taught recitation, managed seven TA's and over 170 students.
    Helped prepare course material.

Teaching Assistant for CS1311x, Georgia Tech
    Fall 2000, Spring 2001.
    Taught recitation, managed one section of students.

Invited Talks

"IM2GPS: estimating geographic information from a single image". Google Tech Talk, August 2008.
"Image-based Graphics and Vision". CMU Andrew's Leap high school program, July 2008.
"IM2GPS: estimating geographic information from a single image". CMU VASC Seminar, June 2008.
"Lots of Data" Panelist. Lake Como Workshop on Object Recognition, May 2008.
"Scene Completion Using Millions of Photographs". MIT, July 2007.
"Scene Completion Using Millions of Photographs". UIUC, September 2007.

Outreach

Computing Community Consortium (CCC):   Algorithm Estimates Geographic Location of Photos. November 19, 2008.
Ars Technica:   Using Flickr to teach computers to identify pictures. June 17th, 2008.
ZDNet:   Finding where a photo has been shot. June 19th, 2008.
CNET:   New geotagging method draws on Flickr photos. June 18th, 2008.
Chronicle of Higher Education:   New Software Can Tell Where a Photo Was Taken. June 16th, 2008.
Digg:   Using Flickr to teach computers to identify pictures. June 17th, 2008.
Slashdot:   Computer Scientists Scour Your Holiday Photos. June 18th, 2008.

MSNBC:   Software turns photos from bad to good. December 12th, 2007.
BBC News:   Photo tool could fix bad images. August 8th, 2007.
Daily Mail:   Picture Perfect - the software that fixes your dodgy holiday snaps. August 9th, 2007.
The Independent:   Instant makeup: Perfect your holiday snaps. September 19th, 2007.
USA Today:   Researchers try Google photo tactic. July 12th, 2007.
ZDNet:   Using Flickr to edit your photos. July 11th, 2007.
CNET:   Researchers try Google approach to understanding photos. July 11th, 2007.
Digg:   Algorithm draws on millions of images to seamlessly fill blanks in photos. August 17th, 2007.
Slashdot:   Algorithm Seamlessly Patches Holes In Images. August 9th, 2007.
Aperture Magazine:   Volume 190. Spring 2008.

Television
Local CBS affiliate KDKA:   Student Develops Picture Location Technology. June 18th, 2008.
Local ABC affiliate WTAE:   Plugged in: IM2GPS Estimates Where Photos are Taken in The World. July 17th, 2008.
Ivanhoe Broadcast News, Discoveries and Breakthroughs Inside Science:   Where in the World. December 2008.

Books
Cynthia Baron:   Adobe Photoshop Forensics: Sleuths, Truths, and Fauxtography. 2007. pp. 264-266.