Large pretrained (eg," foundation") models exhibit distinct capabilities depending on the
domain of data they are trained on. While these domains are generic, they may only barely …

Vision and text have been fully explored in contemporary video-text foundational models,
while other modalities such as audio and subtitles in videos have not received sufficient …

The goal of this work is to build flexible video-language models that can generalize to
various video-to-text tasks from few examples. Existing few-shot video-language learners …

Contrastive learning-based video-language representation learning approaches, eg, CLIP,
have achieved outstanding performance, which pursue semantic interaction upon pre …

Most existing text-video retrieval methods focus on cross-modal matching between the
visual content of videos and textual query sentences. However, in real-world scenarios …

In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model
(VALOR) for multi-modal understanding and generation. Different from widely-studied vision …

Existing text-video retrieval solutions are, in essence, discriminant models focused on
maximizing the conditional likelihood, ie, p (candidates| query). While straightforward, this …

The pre-trained image-text models, like CLIP, have demonstrated the strong power of vision-
language representation learned from a large scale of web-collected image-text data. In light …

Abstract Video-Text Retrieval (VTR) aims to search for the most relevant video related to the
semantics in a given sentence, and vice versa. In general, this retrieval task is composed of …

Image-text pretrained models, eg, CLIP, have shown impressive general multi-modal
knowledge learned from large-scale image-text data pairs, thus attracting increasing …