Katerina Fragkiadaki

I am a post doctoral researcher at the Computer Vision laboratory at UC Berkeley, working with Prof. Jitendra Malik. Before that, I completed my Ph.D. in the GRASP Laboratory, at University of Pennsylvania, where I was advised by Prof. Jianbo Shi. I am interested in all aspects of video understanding. In particular, I have been working on estimating human motion and body pose in videos as a means towards inferring what people are doing or want to do next.


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


Software

Matlab/C code for two-granularity multi-object tracking here.
Matlab/C code for monocular video segmentation here.
Matlab/C code for Large Displacement Optical Flow (LDOF) here.

Publications

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
in 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
in 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
in 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
in CVPR 2011
paper | poster | bibtex
Figure-Ground Image Segmentation Helps Semi-Supervised Learning of Objects
Katerina Fragkiadaki and Jianbo Shi
in ECCV 2010
paper | poster | bibtex