The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

With the exponential surge in diverse multimodal data, traditional unimodal retrieval
methods struggle to meet the needs of users seeking access to data across various …

Image-based visual-language (I-VL) pre-training has shown great success for learning joint
visual-textual representations from large-scale web data, revealing remarkable ability for …

The canonical approach to video action recognition dictates a neural model to do a classic
and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined …

Video-and-language pre-training has shown promising improvements on various
downstream tasks. Most previous methods capture cross-modal interactions with a …

In text-video retrieval, the objective is to learn a cross-modal similarity function between a
text and a video that ranks relevant text-video pairs higher than irrelevant pairs. However …

We present CLIP2Video network to transfer the image-language pre-training model to video-
text retrieval in an end-to-end manner. Leading approaches in the domain of video-and …

The task of retrieving video content relevant to natural language queries plays a critical role
in effectively handling internet-scale datasets. Most of the existing methods for this caption-to …

Videos are a rich source of multi-modal supervision. In this work, we learn representations
using self-supervision by leveraging three modalities naturally present in videos: visual …

We study joint video and language (VL) pre-training to enable cross-modality learning and
benefit plentiful downstream VL tasks. Existing works either extract low-quality video …