Ross B. Girshick URL

Ross B. Girshick
Research Scientist
Facebook AI Research (FAIR)
Researcher
Microsoft Research, Redmond
Postdoctoral fellow
University of California, Berkeley, EECS
[email protected] 
cv /  google scholar /  Ph.D. thesis
papers:  arXiv /  journal /  conference 
MSR website

from: http://www.cs.berkeley.edu/~rbg/

About me

I finished my Ph.D. in computer vision at  The University of Chicago under the supervision of  Pedro Felzenszwalb in April 2012. Then, I spent two unbelievably wonderful years as a postdoc at  UC Berkeleyunder  Jitendra Malik. From Berkeley, I spent just over one year as a Researcher at Microsoft Research, Redmond. Now, I'm off on a new adventure as a Research Scientist with the terrific group of researchers and engineers in Facebook AI Research (FAIR). 

My main research interests are in computer vision, AI, and machine learning. I'm particularly focused on building models for object detection and recognition. These models aim to incorporate the "right" biases so that machine learning algorithms can understand image content from moderate to large-scale datasets. I always have an eye towards fast systems that work well in practice. 

During my Ph.D., I spent time as a research intern at  Microsoft Research Cambridge, UK working on human pose estimation from (Kinect) depth images. I also participated in several first-place entries into the PASCAL VOC object detection challenge, and was awarded a "lifetime achievement"  prize for my work on deformable part models. I think this refers to the lifetime of the PASCAL challenge—and not mine! 

News

•  Sean Bell led our team, together with Kavita Bala and Larry Zitnick, to 3rd place in the 2015 MS COCO object detection challenge! Sean also won the prize for the best student-led entry. Check out our tech report describing the ION (inside-outside network) detector:
•  Faster R-CNN: paper / Python code / Matlab code
•  Fast R-CNN: paper / code

Project pages

• Faster R-CNN github repository (Python source code for training and using Faster R-CNN)
• Fast R-CNN github repository (Python source code for training and using Fast R-CNN)
• R-CNN github repository (Matlab source code for training and using R-CNN)
• SDS: Simultaneous Detection and Segmentation
• R-CNN (and more!) for RGB-D data
• LSDA: Large Scale Detection through Adaptation
• Deformable Part Models (DPM) (voc-release5 — dissertation code / includes cascade and NIPS grammar model)
• Cascade object detection with deformable part models (add-on code for voc-release4.01)

arXiv tech reports

Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
Sean Bell, C. Lawrence Zitnick, Kavita Bala,  Ross Girshick
arXiv [cs.CV]
abstract /  bibtex

Object Detection Networks on Convolutional Feature Maps
Shaoqing Ren, Kaiming He,  Ross Girshick, Xiangyu Zhang, Jian Sun
arXiv [cs.CV]
bibtex

Journal papers

Region-based Convolutional Networks for Accurate Object Detection and Semantic Segmentation
R. Girshick, J. Donahue, T. Darrell, J. Malik
IEEE Transactions on Pattern Analysis and Machine Intelligence (accepted May 18, 2015)
abstract /  code /  CVPR'14 version

Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation
Saurabh Gupta, Pablo Arbeláez,  Ross Girshick, Jitendra Malik 
International Journal of Computer Vision (IJCV), 2014
code /  bibtex

Efficient Human Pose Estimation from Single Depth Images
J. Shotton,  R. Girshick, A. Fitzgibbon, T. Sharp, M. Cook, M. Finocchio, R. Moore, P. Kohli, A. Criminisi, A. Kipman, A. Blake
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, No. 12, Dec. 2013
abstract /  bibtex

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, Sep. 2010 
abstract /  PAMI code /  latest code (voc-release5) /  bibtex 

See also, CACM Research Highlight:

Visual Object Detection with Deformable Part Models
P. Felzenszwalb,  R. Girshick, D. McAllester, D. Ramanan
Communications of the ACM, no. 9 (2013): 97-105

Conference papers

2015

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He,  Ross Girshick, Jian Sun 
Neural Information Processing Systems (NIPS), 2015
Python code /  Matlab code /  bibtex

Fast R-CNN
Ross Girshick 
IEEE International Conference on Computer Vision (ICCV), 2015 
oral presentation 
code /  slides /  bibtex

Contextual Action Recognition with R*CNN
Georgia Gkioxari,  Ross Girshick, Jitendra Malik
IEEE International Conference on Computer Vision (ICCV), 2015 
code /  bibtex

Actions and Attributes from Wholes and Parts
Georgia Gkioxari,  Ross Girshick, Jitendra Malik
IEEE International Conference on Computer Vision (ICCV), 2015 
bibtex

Hypercolumns for object segmentation and fine-grained localization
Bharath Hariharan, Pablo Arbeláez,  Ross Girshick, Jitendra Malik
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
oral presentation
bibtex

Aligning 3D models to RGB-D images of cluttered scenes
Saurabh Gupta, Pablo Arbeláez,  Ross Girshick, Jitendra Malik
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
bibtex

Deformable Part Models are Convolutional Neural Networks
Ross Girshick, Forrest Iandola, Trevor Darrell, Jitendra Malik
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
bibtex

2014

LSDA: Large Scale Detection through Adaptation
Judy Hoffman, Sergio Guadarrama, Eric Tzeng, Ronghang Hu, Jeff Donahue, Ross Girshick, Trevor Darrell, Kate Saenko
Neural Information Processing Systems (NIPS), 2014
project, code, models /  bibtex

Simultaneous Detection and Segmentation
Bharath Hariharan, Pablo Arbeláez,  Ross Girshick, Jitendra Malik
European Conference on Computer Vision (ECCV), 2014
project page (with code) /  bibtex

Learning Rich Features from RGB-D Images for Object Detection and Segmentation
Saurabh Gupta,  Ross Girshick, Pablo Arbeláez, Jitendra Malik
European Conference on Computer Vision (ECCV), 2014
code, models, and data /  bibtex

Analyzing the Performance of Multilayer Neural Networks for Object Recognition
Pulkit Agrawal,  Ross Girshick, Jitendra Malik
European Conference on Computer Vision (ECCV), 2014
bibtex

Part-based R-CNNs for Fine-grained Category Detection
Ning Zhang, Jeff Donahue,  Ross Girshick, Trevor Darrell
European Conference on Computer Vision (ECCV), 2014
oral presentation
bibtex

On Learning to Localize Objects with Minimal Supervision
Hyun Oh Song,  Ross Girshick, Stefanie Jegelka, Julien Mairal, Zaid Harchaoui, Trevor Darrell
International Conference on Machine Learning (ICML), 2014
code /  bibtex

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
R. Girshick, J. Donahue, T. Darrell, J. Malik
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
oral presentation
arXiv tech report (includes ImageNet results) /  supplement /  code /  poster / slides /  bibtex

Using k-poselets for Detecting People and Localizing their Keypoints
G. Gkioxari*, B. Hariharan*,  R. Girshick, J. Malik
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
* equal contribution
project page /  code /  github /  bibtex

Understanding Objects in Detail with Fine-grained Attributes
A. Vedaldi, S. Mahendran, S. Tsogkas, S. Maji,  R. Girshick, J. Kannala, E. Rahtu, I. Kokkinos, M. B. Blaschko, D. Weiss, B. Taskar, K. Simonyan, N. Saphra, S. Mohamed 
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
dataset /  bibtex

2013

Training Deformable Part Models with Decorrelated Features
R. Girshick, J. Malik
IEEE International Conference on Computer Vision (ICCV), 2013 
supplement /  LM-LLDA DPM training code /  bibtex

Discriminatively Activated Sparselets
R. Girshick*, H. O. Song*, T. Darrell
International Conference on Machine Learning (ICML), 2013
oral presentation
supplement /  Caltech-101 demo code /  bibtex

2012 and earlier

Sparselet Models for Efficient Multiclass Object Detection
H.O. Song, S. Zickler, T. Althoff,  R. Girshick, M. Fritz, C. Geyer, P. Felzenszwalb, T. Darrell
European Conference on Computer Vision (ECCV), 2012
code /  bibtex

Object Detection with Grammar Models
R. Girshick, P. Felzenszwalb, D. McAllester
Neural Information Processing Systems (NIPS), 2011
spotlight video /  code (voc-release5) /  bibtex

Efficient Regression of General-Activity Human Poses from Depth Images
R. Girshick, J. Shotton, P. Kohli, A. Criminisi, A. Fitzgibbon
IEEE International Conference on Computer Vision (ICCV), 2011 
supplement /  video /  bibtex

Cascade Object Detection with Deformable Part Models ^†
P. Felzenszwalb,  R. Girshick, D. McAllester
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010
oral presentation
slides (pdf) /  slides (keynote) /  talk /  code (voc-release5) /  bibtex

Visibility Constraints on Features of 3D Objects ^†
R. Basri, P. Felzenszwalb,  R. Girshick, D. Jacobs, C. Klivans
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009
bibtex

Simulating Chinese Brush Painting: the Parametric Hairy Brush
R. Girshick
ACM SIGGRAPH Posters, 2004
Session: Nonphotorealistic Animation and Rendering
bibtex

^†Authors listed alphabetically

Ph.D. dissertation

From Rigid Templates to Grammars: Object Detection with Structured Models
R. Girshick
Ph.D. dissertation, The University of Chicago, Apr. 2012
slides /  bibtex

Object Detection with Heuristic Coarse-to-Fine Search
R. Girshick
M.S. thesis, The University of Chicago, Dec. 2009 
bibtex

Erdös = 3 (via two paths)

I like this website