English

Robust Latent Representations via Cross-Modal Translation and Alignment

Machine Learning 2021-03-10 v2 Multimedia

Abstract

Multi-modal learning relates information across observation modalities of the same physical phenomenon to leverage complementary information. Most multi-modal machine learning methods require that all the modalities used for training are also available for testing. This is a limitation when the signals from some modalities are unavailable or are severely degraded by noise. To address this limitation, we aim to improve the testing performance of uni-modal systems using multiple modalities during training only. The proposed multi-modal training framework uses cross-modal translation and correlation-based latent space alignment to improve the representations of the weaker modalities. The translation from the weaker to the stronger modality generates a multi-modal intermediate encoding that is representative of both modalities. This encoding is then correlated with the stronger modality representations in a shared latent space. We validate the proposed approach on the AVEC 2016 dataset for continuous emotion recognition and show the effectiveness of the approach that achieves state-of-the-art (uni-modal) performance for weaker modalities.

Keywords

Cite

@article{arxiv.2011.01631,
  title  = {Robust Latent Representations via Cross-Modal Translation and Alignment},
  author = {Vandana Rajan and Alessio Brutti and Andrea Cavallaro},
  journal= {arXiv preprint arXiv:2011.01631},
  year   = {2021}
}
R2 v1 2026-06-23T19:52:55.161Z