Most transformer-based video encoders are limited to short temporal contexts due to their
quadratic complexity. While various attempts have been made to extend this context, this …

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for
video understanding, that capably understands arbitrary-length video with a constant …

Long-form video understanding represents a significant challenge within computer vision,
demanding a model capable of reasoning over long multi-modal sequences. Motivated by …

This survey presents an overview of methods for learning from video (LfV) in the context of
reinforcement learning (RL) and robotics. We focus on methods capable of scaling to large …

Existing methods for long video understanding primarily focus on videos only lasting tens of
seconds, with limited exploration of techniques for handling longer videos. The increased …

Large Language Models (LLMs), known to contain a strong awareness of world knowledge,
have allowed recent approaches to achieve excellent performance on Long-Video …

Long-form videos that span across wide temporal intervals are highly information redundant
and contain multiple distinct events or entities that are often loosely-related. Therefore, when …

In this report, we present our champion solution for Ego4D EgoSchema Challenge in CVPR
2024. To deeply integrate the powerful egocentric captioning model and question reasoning …