Katerina Fragkiadaki

I am interested in building machines that understand the stories that videos portray, and, inversely, on using videos to teach machines about the world. I am currently a post doctoral researcher with the video group at Google Research in Mountainview. Before that I spent two wonderful years as a post doctoral researcher at the Computer Vision laboratory at UC Berkeley, working with Prof. Jitendra Malik. I completed my Ph.D. in the GRASP Laboratory, at the University of Pennsylvania, where I was advised by Prof. Jianbo Shi. Before that I was in NTUA and before that I was in Crete.
The pen-ultimate goal is to build a machine that understands movie plots, and the ultimate a goal is to build a machine that would want to watch Bergman over this.


752 Sutardja Dai Hall
University of California, Berkeley
Berkeley, CA, 94720-1758
katef 'at' berkeley.edu


News


Publications

Learning Feature Hierarchies from Long-Range Temporal Associations in Videos
Panna Felsen, Katerina Fragkiadaki, Jitendra Malik and Alexei Efros
Workshop on Transfer and Multi-task Learning, in conjunction with NIPS 2015
paper
Learning Predictive Visual Models of Physics for Playing Billiards
Katerina Fragkiadaki*, Pulkit Agrawal*, Sergey Levine and Jitendra Malik
ICLR 2016
paper
Recurrent Network Models for Human Dynamics
Katerina Fragkiadaki, Sergey Levine, Panna Felsen and Jitendra Malik
ICCV 2015
paper | project page
Human Pose Estimation with Iterative Error Feedback
Joao Carreira, Pulkit Agrawal, Katerina Fragkiadaki, and Jitendra Malik
arXiv
paper|project page with code
Learning to Segment Moving Objects in Videos
Katerina Fragkiadaki, Pablo Arbelaez, Panna Felsen and Jitendra Malik
CVPR 2015
paper | poster | bibtex | project page with code
Grouping-Based Low-Rank Video Completion and 3D Reconstruction
Katerina Fragkiadaki, Marta Salas, Pablo Arbelaez, and Jitendra Malik
NIPS 2014
paper | poster | bibtex | project page with code
Pose from Flow and Flow from Pose
Katerina Fragkiadaki, Han Hu, and Jianbo Shi
CVPR 2013
paper | poster | bibtex
Two Granularity Tracking: Mediating Trajectory and Detection Graphs for Tracking under Occlusions
Katerina Fragkiadaki, Weiyu Zhang, Geng Zhang, and Jianbo Shi
ECCV 2012
paper | poster | bibtex | project page with code
Video Segmentation by tracing Discontinuities in a Trajectory Embedding
Katerina Fragkiadaki, Geng Zhang, and Jianbo Shi
CVPR 2012
paper | poster | bibtex | project page with code
Structural-Flow Trajectories for Unravelling Tubular Structure Bundles
Katerina Fragkiadaki, Weiyu Zhang, Jianbo Shi, and Elena Bernardis
MICCAI 2012 (oral presentation)
paper | slides | bibtex
Detection-free Tracking: Exploiting Motion and Topology for Segmenting and Tracking under Entanglement
Katerina Fragkiadaki and Jianbo Shi
CVPR 2011
paper | poster | bibtex
Figure-Ground Image Segmentation Helps Semi-Supervised Learning of Objects
Katerina Fragkiadaki and Jianbo Shi
ECCV 2010
paper | poster | bibtex

Other

Matlab/C code for Large Displacement Optical Flow (LDOF) here.