← Search

Xizi Wang

2 accepted papers

2023

VindLU: A Recipe for Effective Video-and-Language Pretraining

CVPR 2023poster

The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks…