Browsing Theses by Subject "multimodal deep learning"
Now showing items 1-1 of 1
-
Adaptive Fusion Techniques for Effective Multimodal Deep Learning
(University of Waterloo, 2020-08-28)Effective fusion of data from multiple modalities, such as video, speech, and text, is a challenging task due to the heterogeneous nature of multimodal data. In this work, we propose fusion techniques that aim to model ...