Search Results for author:
Found 2 papers, 0 papers with code
Refining Multimodal Representations using a modality-centric self-supervised module
Tasks that rely on multi-modal information typically include a fusion module that combines information from different modalities.
Multimodal Fusion Refiner Networks
In this work, we develop a Refiner Fusion Network (ReFNet) that enables fusion modules to combine strong unimodal representation with strong multimodal representations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
