In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze mutual interactions between linguistic texts and local regional objects. It uncovers global and local visual clues from paired video sequences and text descriptions for detailed visual and text relation modeling. Second, we introduce a TaNgled Transformer block (TNT) to encode three sources of information, i.e., global actions, local regional objects, and linguistic descriptions. Global-local correspondences are discovered via judicious clues extraction from contextual information. It enforces the joint video-text representation to be aware of fine-grained objects as well as global human intention. We validate the generalization capability of ActBERT on downstream video-and-language tasks, i.e., text-video clip retrieval, video captioning, video question answering, action segmentation, and action step localization. ActBERT significantly outperforms the stateof-the-art, demonstrating its superiority in video-text representation learning.actbct * This work was done when Linchao Zhu visited Baidu Research. Yi Yang is the corresponding author.
translated by 谷歌翻译