arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.14682cs.CVcs.CL
收藏

用上下文文本丰富视频字幕

Enriching Video Captions With Contextual Text

ETH Zürich(苏黎世联邦理工学院)

Philipp Rimle, Pelin Dogan, Markus Gross

摘要:

理解视频内容并生成具有上下文的字幕是一项重要且具有挑战性的任务。与以前的方法,通常试图生成通用的视频字幕没有上下文不同,我们的架构通过注入相关的文本数据提取的信息上下文字幕。我们提出了一个端到端的序列到序列模型,该模型根据视觉输入生成视频字幕,并从上下文文本中挖掘相关知识,如名称和位置。与以前的方法相比,我们不对文本进行进一步的预处理,而是让模型直接学习关注它。在视觉输入的指导下,模型能够通过指针生成器网络从上下文文本中复制单词,从而生成更具体的视频字幕。我们在新闻视频数据集上展示了具有竞争力的性能,并通过消融研究验证了上下文视频描述的有效性以及我们模型架构中的个性化设计选择。

英文摘要:

Understanding video content and generating caption with context is an important and challenging task. Unlike prior methods that typically attempt to generate generic video captions without context, our architecture contextualizes captioning by infusing extracted information from relevant text data. We propose an end-to-end sequence-to-sequence model which generates video captions based on visual input, and mines relevant knowledge such as names and locations from contextual text. In contrast to previous approaches, we do not preprocess the text further, and let the model directly learn to attend over it. Guided by the visual input, the model is able to copy words from the contextual text via a pointer-generator network, allowing to produce more specific video captions. We show competitive performance on the News Video Dataset and, through ablation studies, validate the efficacy of contextual video captioning as well as individual design choices in our model architecture.

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。

↑