Practical Cross-modal Manifold Alignment for Grounded Language

Andre T. Nguyen
Andre T. Nguyen
Luke E. Richards
Luke E. Richards
Gaoussou Youssouf Kebe
Gaoussou Youssouf Kebe
Kasra Darvish
Kasra Darvish
Frank Ferraro
Frank Ferraro
Cited by: 0|Bibtex|Views2
Other Links: arxiv.org

Abstract:

We propose a cross-modality manifold alignment procedure that leverages triplet loss to jointly learn consistent, multi-modal embeddings of language-based concepts of real-world items. Our approach learns these embeddings by sampling triples of anchor, positive, and negative data points from RGB-depth images and their natural language d...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments