arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.02586cs.CV
收藏

利用多模态大语言模型改进视觉叙事

Improving Visual Storytelling with Multimodal Large Language Models

Henan Polytechnic University(河南理工大学)

Xiaochuan Lin, Xiangyong Chen

AI总结:

本文提出结合LLMs与LVLMs并通过指令微调、监督学习和强化学习改进视觉叙事生成,实验表明其在连贯性、相关性、情感深度和整体质量上显著优于现有模型。

摘要:

视觉叙事是一个新兴领域,它结合图像与叙述来创造引人入胜且语境丰富的故事。尽管具有潜力,但由于对齐视觉与文本信息的复杂性,生成连贯且富有情感共鸣的视觉故事仍然具有挑战性。本文提出了一种新颖的方法,利用大语言模型(LLMs)和大视觉语言模型(LVLMs)并结合指令微调来应对这些挑战。我们引入了一个新的数据集,其中包含多样的视觉故事,并标注了详细的字幕和多模态元素。我们的方法采用监督学习和强化学习相结合的方式对模型进行微调,以增强其叙事生成能力。使用GPT-4进行的定量评估和定性人工评估表明,我们的方法显著优于现有模型,在叙事连贯性、相关性、情感深度和整体质量方面取得了更高的分数。结果强调了指令微调的有效性以及LLMs/LVLMs在推进视觉叙事方面的潜力。

英文摘要:

Visual storytelling is an emerging field that combines images and narratives to create engaging and contextually rich stories. Despite its potential, generating coherent and emotionally resonant visual stories remains challenging due to the complexity of aligning visual and textual information. This paper presents a novel approach leveraging large language models (LLMs) and large vision-language models (LVLMs) combined with instruction tuning to address these challenges. We introduce a new dataset comprising diverse visual stories, annotated with detailed captions and multimodal elements. Our method employs a combination of supervised and reinforcement learning to fine-tune the model, enhancing its narrative generation capabilities. Quantitative evaluations using GPT-4 and qualitative human assessments demonstrate that our approach significantly outperforms existing models, achieving higher scores in narrative coherence, relevance, emotional depth, and overall quality. The results underscore the effectiveness of instruction tuning and the potential of LLMs/LVLMs in advancing visual storytelling.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑