About Me

I'm a fifth-(and-final!-)year Ph.D. student in Computer Science at The University of Chicago, where I do research in the field of Computer Vision. My advisor is Pedro Felzenszwalb.

Research Interests

• Computer Vision (primarily object category detection/classification/localization)
• Machine Learning
• AI (broadly speaking)

Projects

• Object detection with mixtures of deformable part models
  State-of-the-art results in the PASCAL VOC 2008 & 2009 object detection challenge.
  voc-release4: updated on 21-Apr-2010.

• Cascade Object Detection with Deformable Part Models
  Source code is now available for our CVPR paper.

News, updates

• 23-Nov-2011: We've release voc-release4.01 which includes a runtime performance bug fix on recent versions of matlab (>= 2010b).
• 25-Oct-2011: NIPS 2011 paper posted.
• 25-Oct-2011: ICCV 2011 paper posted.
• 11-Sep-2010: PASCAL Visual Object Challenge "Lifetime Achievement" Prize, 2010
• 26-Jul-2010: CVPR Oral video
• 21-May-2010: Star Cascade: We've released code for fast cascade detection with our deformable part models.
• 21-Apr-2010: VOC Release 4: We've released a new version of our object detection system.
• 20-Mar-2010: I will be an intern at Microsoft Research Cambridge, UK from July to October.
• 24-Feb-2010: CVPR 2010:
  My paper with Pedro Felzenszwalb and David McAllester on efficient cascade detection with deformable part models was accepted as a oral at CVPR 2010.
• 3-Oct-2009: PASCAL VOC Challenge 2009 Results:
  Pedro Felzenszwalb, David McAllester, and I co-won (with Oxford) the object detection challenge. Slides from the workshop.

Papers, etc.

• Object Detection with Grammar Models
  R. Girshick, P. Felzenszwalb, D. McAllester.
  To Appear in Neural Information Processing Systems (NIPS) 2011 (spotlight).
  pdf
  
• Efficient Regression of General-Activity Human Poses from Depth Images
  R. Girshick, J. Shotton, P. Kohli, A. Criminisi, A. Fitzgibbon.
  To Appear in Proceedings of the IEEE ICCV 2011.
  pdf supplementary material video
  
• Cascade Object Detection with Deformable Part Models
  P. Felzenszwalb, R. Girshick, D. McAllester.
  Proceedings of the IEEE CVPR 2010 (oral presentation: pdf, keynote). pdf
  [latest source code release]
• Object Detection with Discriminatively Trained Part Based Models
  P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan.
  IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, No. 9, September 2010. pdf
  [source code for paper] [latest source code release]
• Visibility Constraints on Features of 3D Objects
  R. Basri, P. Felzenszwalb, R. Girshick, D. Jacobs, C. Klivans.
  Proceedings of the IEEE CVPR 2009. pdf
• Object Detection with Heuristic Coarse-to-Fine Search
  R. Girshick
  Master's Thesis pdf

Talks

• Cascade Object Detection with Deformable Part Models
  CVPR 2010 Oral, San Francisco, CA, USA, June 2010.
  [slides: pdf, keynote] [video: videolectures.net]
• Object detection with heuristic coarse-to-fine search
  ICVSS (International Computer Vision Summer School), Sicily, July 2009.
  (Award for best student presentation.)
• Object detection with heuristic coarse-to-fine search
  Illinois Computer Vision Workshop, TTI-C, May 2009
• Discriminatively trained mixtures of deformable part models for detection
  Illinois Computer Vision Workshop, UIUC, October 2008
• An introduction to object recognition with deformable part models
  CS graduate student seminar, University of Chicago, October 2008

Scholarships

• ARCS Foundation Scholar, 2008 to present

Teaching Experience

• Teaching Assistant: Unix Systems Programming [CSPP 51081]
• Teaching Assistant: Game Construction [CMSC 23800 & CSPP 53800]

Random Stuff

• Some photos.
• Some better photos.
• A lay explanation of why computer vision is hard.
• A poster on object recognition targeted at a general audience
• How to choose dinner.
• Like wikipedia?
  
• A dubious figure of questionable character.
• An article on convex relaxation.