We describe a DNN for video classification and captioning, trained end-to-end, with shared
features, to solve tasks at different levels of granularity, exploring the link between …

We describe a DNN for fine-grained action classification and video captioning. It gives state-
of-the-art performance on the challenging Something-Something dataset, with over 220, 000 …

Self-supervised learning has become increasingly important to leverage the abundance of
unlabeled data available on platforms like YouTube. Whereas most existing approaches …

Video content is multifaceted, consisting of objects, scenes, interactions or actions. The
existing datasets mostly label only one of the facets for model training, resulting in the video …

With the advent of large-scale multimodal video datasets, especially sequences with audio
or transcribed speech, there has been a growing interest in self-supervised learning of video …

We introduce InternVideo2, a new video foundation model (ViFM) that achieves the state-of-
the-art performance in action recognition, video-text tasks, and video-centric dialogue. Our …

We are creating multimedia contents everyday and everywhere. While automatic content
generation has played a fundamental challenge to multimedia community for decades …

Applying large scale pre-trained image-language model to video-language tasks has
recently become a trend, which brings two challenges. One is how to effectively transfer …

The recent growth in the consumption of online media by children during early childhood
necessitates data-driven tools enabling educators to filter out appropriate educational …

Joint video-language learning has received increasing attention in recent years. However,
existing works mainly focus on single or multiple trimmed video clips (events), which makes …