output
20032026
most citedUnsupervised Learning of Video Representations using LSTMs

1.6k citations

researchers with a paper here
collaborating institutions
Showing 2017Show all

1 paper · 1 filter

cs.CV2017

AMAT: Medial Axis Transform for Natural Images

Stavros Tsogkas, Sven Dickinson

We introduce Appearance-MAT (AMAT), a generalization of the medial axis transform for natural images, that is framed as a weighted geometric set cover problem. We make the followin…