Alexander Krull

Assistant Professor, Birmingham University

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

ShapeEmbed: a self-supervised learning framework for 2D contour quantification

#1708 · Anna Foix Romero, Craig Russell, Alexander Krull, Virginie Uhlmann

ShapeEmbed is a self-supervised method using Euclidean distance matrices to encode the shape of objects in 2D images in a way that is robust to shape-preserving geometric transformations