HaVTR: Improving Video-Text Retrieval Through Augmentation Using Large Foundation Models

arXiv:2404.05083v1 Announce Type: cross
Abstract: While recent progress in video-text retrieval has been driven by the exploration of powerful model architectures and training strategies, the representation learning ability of video-text retrieval models is still limited due to low-quality and scarce training data annotations. To address this issue, we present a novel video-text learning paradigm, HaVTR, which augments video and text data to learn more generalized features. Specifically, we first adopt a simple augmentation method, which generates self-similar data by randomly …

abstract annotations architectures arxiv augmentation cs.cl cs.cv cs.ir cs.lg data exploration foundation improving issue low progress quality representation representation learning retrieval strategies text through training training data type video