Search Results for author: Haider Al-Tahan

Found 3 papers, 0 papers with code

The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning

no code implementations13 Oct 2021 Haider Al-Tahan, Yalda Mohsenzadeh

Hence, we extensively investigate composition of temporal augmentations suitable for learning audiovisual representations; we find lossy spatio-temporal transformations that do not corrupt the temporal coherency of videos are the most effective.

Contrastive Learning Representation Learning +1

CLAR: Contrastive Learning of Auditory Representations

no code implementations19 Oct 2020 Haider Al-Tahan, Yalda Mohsenzadeh

We illustrate that by combining all these methods and with substantially less labeled data, our framework (CLAR) achieves significant improvement on prediction performance compared to supervised approach.

Contrastive Learning Self-Supervised Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.