BriefGPT.xyz
Nov, 2018
交叉学习:跨模态自监督
Cross and Learn: Cross-Modal Self-Supervision
HTML
PDF
Nawid Sayed, Biagio Brattoli, Björn Ommer
TL;DR
本文介绍了一种利用两种不同形式的信息进行自监督表示学习的方法。我们使用视频数据进行我们的方法,得到良好的性能,并证明我们的特征表示可以转移至其他任务。
Abstract
In this paper we present a self-supervised method for
representation learning
utilizing two different modalities. Based on the observation that
cross-modal information
has a high semantic meaning we propose a met
→