arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02748cs.CVcs.AI
收藏

基于视觉输入的故事生成:技术、相关任务与挑战

Story Generation from Visual Inputs: Techniques, Related Tasks, and Challenges

Daniel A. P. Oliveira, Eugénio Ribeiro, David Martins de Matos

AI总结:

该综述聚焦视觉输入故事生成领域,梳理相关方法的原理、优缺点,介绍图像视频字幕、视觉问答等关联任务,分析主流数据集与评估指标的局限,为领域发展提供参考。

摘要:

从视觉数据中生成引人入胜的叙事对自动化数字媒体消费、辅助技术及互动娱乐至关重要。本综述涵盖了此类叙事生成所采用的方法体系,重点阐述其原理、优势与局限性。\n 本综述还涉及与自动故事生成相关的任务,如图像与视频字幕生成、视觉问答,以及无视觉输入的故事生成。这些任务与视觉故事生成存在共同挑战,且为该领域所用技术提供了思路。我们分析了主要数据集与评估指标,并就其局限性给出批判性观点。

英文摘要:

Creating engaging narratives from visual data is crucial for automated digital media consumption, assistive technologies, and interactive entertainment. This survey covers methodologies used in the generation of these narratives, focusing on their principles, strengths, and limitations. The survey also covers tasks related to automatic story generation, such as image and video captioning, and visual question answering, as well as story generation without visual inputs. These tasks share common challenges with visual story generation and have served as inspiration for the techniques used in the field. We analyze the main datasets and evaluation metrics, providing a critical perspective on their limitations.

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。

↑