Georgia Gkioxari
gkioxari@eecs.berkeley.edu

I am a postdoctoral researcher at FAIR. I received my PhD from UC Berkeley, where I was advised by Jitendra Malik. I did my bachelors in ECE at NTUA in Athens, Greece.

cv / / / /



News

  • Code and models (PASCAL VOC Action, Berkeley Attributes of People Dataset, Stanford 40 Dataset) for R*CNN now available at my github page
  • Code and models for "Finding Action Tubes" are now avalaibe at the project's webpage!
  • Deploy code and models for "R-CNNs for Pose Estimation and Action Detection" are now available at the project's webpage!



Research

My primary research interests are in the fields of computer vision and machine learning. In particular, I am interested in object recognition and object detection from 2D images. My current research focus is on detecting people, recognizing their action and predicting their pose from commercial type images.

game

Detecting and Recognizing Human-Object Intaractions
Georgia Gkioxari, Ross Girshick, Piotr Dollàr and Kaiming He

arxiv / bibtex
@article{gkioxari2017interactnet,
  Author    = {Georgia Gkioxari and Ross Girshick and 
               Piotr Doll\'{a}r and Kaiming He},
  Title     = {Detecting and Recognizing 
              Human-Object Intaractions},
  Journal   = {arXiv preprint arXiv:1704.07333},
  Year      = {2017}}
                
game

Mask R-CNN
Kaiming He, Georgia Gkioxari, Piotr Dollàr and Ross Girshick

arxiv / bibtex
@article{he2017maskrcnn,
  Author    = {Kaiming He and Georgia Gkioxari and
               Piotr Doll\'{a}r and Ross Girshick},
  Title     = {Mask R-CNN},
  Journal   = {arXiv preprint arXiv:1703.06870},
  Year      = {2017}}
                
game tennis

Chained Predictions Using Convolutional Neural Networks
Georgia Gkioxari, Alexander Toshev and Navdeep Jaitly
European Conference of Computer Vision (ECCV), 2016  

arxiv / project page / bibtex
@article{chain16,
  Author = {G. Gkioxari and A. Toshev and N. Jaitly},
  Title = {Chained Predictions Using 
           Convolutional Neural Networks},
  Booktitle = {ECCV},
  Year = {2016}}
                
rstarcnn

Contextual Action Recognition with R*CNN
Georgia Gkioxari, Ross Girshick and Jitendra Malik
International Conference of Computer Vision (ICCV), 2015  

arxiv / github / bibtex
@article{rstarcnn,
  Author = {G. Gkioxari and R. Girshick and J. Malik},
  Title = {Contextual Action Recognition with R*CNN},
  Booktitle = {ICCV},
  Year = {2015}}
                
deepparts

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

arxiv / bibtex
@article{deepparts,
  Author = {G. Gkioxari and R. Girshick and J. Malik},
  Title = {Actions and Attributes from Wholes and Parts},
  Booktitle = {ICCV},
  Year = {2015}}
                
fat

Finding Action Tubes
Georgia Gkioxari and Jitendra Malik
Computer Vision and Pattern Recognition (CVPR), 2015  

project page / arxiv / github / negative results / UCF Sports Benchmark / bibtex
@article{actiontubes,
  Author = {G. Gkioxari and J. Malik},
  Title = {Finding Action Tubes},
  Booktitle = {CVPR},
  Year = {2015}}
                
multiloss

R-CNNs for Pose Estimation and Action Detection
Georgia Gkioxari, Bharath Hariharan, Ross Girshick and Jitendra Malik

project page / arxiv / bibtex
@article{poseactionrcnn,
  Author = {G. Gkioxari and B. Hariharan
        and R. Girshick and J. Malik},
  Title = {R-CNNs for Pose Estimation and Action Detection},
  ArchivePrefix = {arXiv},
  Eprint = {1406.5212},
  PrimaryClass = {cs.CV},
  Year = {2014}}
                
kposelets

Using k-poselets for detecting people and localizing their keypoints
Georgia Gkioxari*, Bharath Hariharan*, Ross Girshick and Jitendra Malik
Computer Vision and Pattern Recognition (CVPR), 2014  
* authors contributed equally

project page / code / github / spotlight / bibtex
@inproceedings{kposelets,
  Author = {G. Gkioxari and B. Hariharan 
        and R. Girshick and J. Malik},
  Title = {Using k-poselets for  detecting people and 
        localizing their keypoints},
  Booktitle = {CVPR},
  Year = {2014}}
              
armlets

Articulated Pose Estimation using Discriminative Armlet Classifiers
Georgia Gkioxari, Pablo Arbelaez, Lubomir Bourdev and Jitendra Malik
Computer Vision and Pattern Recognition (CVPR), 2013  

slides / bibtex
@inproceedings{armlets,
  Author = {G. Gkioxari and P. Arbelaez 
        and L. Bourdev and J. Malik},
  Title  = {Articulated Pose Estimation using 
        Discriminative Armlet Classifiers},
  Booktitle = {CVPR},
  Year  = {2013}}
              


Teaching
pacman

CS188 - Fall 2011 (GSI - GSI Outstanding Award)

pipe

CS 280 - Fall 2012 (GSI)


Mesmerizing Brilliant GirlPower

(Erdös = 3)