VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding

arXiv:2403.14743v1 Announce Type: new
Abstract: Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In contrast, this paper introduces a Video Understanding and Reasoning Framework (VURF) based on the reasoning power of LLMs. Ours is a novel approach to extend the utility of LLMs in the context of video tasks, leveraging their capacity to generalize from minimal …

abstract arxiv contrast cs.cv framework general images language language models large language large language models llms modules paper reasoning studies tasks type understanding video video understanding visual