Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models

TL;DR

This paper presents VideoNarrator, a training-free, multimodal large language model-based pipeline that generates accurate, temporally aligned dense video captions, improving video understanding and supporting downstream tasks without additional training.

Contribution

The introduction of VideoNarrator, a flexible, training-free pipeline utilizing off-the-shelf models to produce high-quality, temporally aligned video narrations with reduced hallucinations.

Findings

Enhanced caption quality and accuracy demonstrated.

Significant reduction in hallucinations in generated narrations.

Improved performance in downstream tasks like video summarization.

Abstract

In this paper, we introduce VideoNarrator, a novel training-free pipeline designed to generate dense video captions that offer a structured snapshot of video content. These captions offer detailed narrations with precise timestamps, capturing the nuances present in each segment of the video. Despite advancements in multimodal large language models (MLLMs) for video comprehension, these models often struggle with temporally aligned narrations and tend to hallucinate, particularly in unfamiliar scenarios. VideoNarrator addresses these challenges by leveraging a flexible pipeline where off-the-shelf MLLMs and visual-language models (VLMs) can function as caption generators, context providers, or caption verifiers. Our experimental results demonstrate that the synergistic interaction of these components significantly enhances the quality and accuracy of video narrations, effectively reducing hallucinations and improving temporal alignment. This structured approach not only enhances video understanding but also facilitates downstream tasks such as video summarization and video question answering, and can be potentially extended for advertising and marketing applications.