We investigate deep generative models that can exchange multiple modalities bi- directionally, eg, generating images from corresponding texts and vice versa. Recently …
Y Shi, B Paige, P Torr - Advances in neural information …, 2019 - proceedings.neurips.cc
Learning generative models that span multiple data modalities, such as vision and language, is often motivated by the desire to learn more useful, generalisable …
Multimodal variational autoencoders (VAEs) have shown promise as efficient generative models for weakly-supervised data. Yet, despite their advantage of weak supervision, they …
Learning from different data types is a long-standing goal in machine learning research, as multiple information sources co-occur when describing natural phenomena. However …
W Guo, J Wang, S Wang - Ieee Access, 2019 - ieeexplore.ieee.org
Multimodal representation learning, which aims to narrow the heterogeneity gap among different modalities, plays an indispensable role in the utilization of ubiquitous multimodal …
Learning multimodal representations is a fundamentally complex research problem due to the presence of multiple heterogeneous sources of information. Although the presence of …
K Sohn, W Shang, H Lee - Advances in neural information …, 2014 - proceedings.neurips.cc
Deep learning has been successfully applied to multimodal representation learning problems, with a common strategy to learning joint representations that are shared across …
Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining. In this work, we explore …
G Pandey, A Dukkipati - 2017 international joint conference on …, 2017 - ieeexplore.ieee.org
In this paper, we address the problem of conditional modality learning, whereby one is interested in generating one modality given the other. While it is straightforward to learn a …