2-D SSM: A General Spatial Layer for Visual Transformers

1 code implementation • 11 Jun 2023 • Ethan Baron, Itamar Zimerman, Lior Wolf

For example, vision transformers equipped with our layer exhibit effective performance even without positional encoding

Inductive Bias Position

Bike2Vec: Vector Embedding Representations of Road Cycling Riders and Races

1 code implementation • 17 May 2023 • Ethan Baron, Bram Janssens, Matthias Bogaert

Vector embeddings have been successfully applied in several domains to obtain effective representations of non-numeric data which can then be used in various downstream tasks.