Xie is the lead author of the study, which will be presented at the International Conference on Learning Representations. The findings are published on the arXiv preprint server. When we look at an ...

In recent years, computer scientists have created various highly performing machine learning tools to generate texts, images, ...

In particular, we are investigating how fusing the audio and visual modalities can improve self-supervised representation learning and it’s down-stream applications to egocentric action recognition.