arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.01641cs.CV
收藏

基于自然语言的视频时刻定位

Localizing Moments in Video with Natural Language

Adobe Research(Adobe 研究院);UC Berkeley(加州大学伯克利分校);INRIA(法国国家信息与自动化研究所)

Lisa Anne Hendricks, Oliver Wang, Eli Shechtman, Josef Sivic, Trevor Darrell, Bryan Russell

摘要:

我们考虑从给定自然语言文本描述的视频中检索特定的时间片段或时刻。设计用于用自然语言检索整个视频剪辑的方法确定视频中发生了什么,但不确定何时发生。为了解决这个问题,我们提出的时刻上下文网络(MCN),有效地本地化视频中的自然语言查询整合本地和全球视频功能随着时间的推移。训练我们的MCN模型的一个关键障碍是,当前的视频数据集不包括成对的本地化视频片段和引用表达式,或者唯一标识相应时刻的文本描述。因此,我们收集了独特的可描述时刻(DiDeMo)数据集,该数据集由10,000多个未经编辑的个人视频组成,这些视频在不同的视觉环境中具有成对的本地化视频片段和引用表达式。我们证明MCN的性能优于几种基线方法,并相信我们的初步结果以及DiDeMo的发布将激发人们对使用自然语言本地化视频时刻的进一步研究。

英文摘要:

We consider retrieving a specific temporal segment, or moment, from a video given a natural language text description. Methods designed to retrieve whole video clips with natural language determine what occurs in a video but not when. To address this issue, we propose the Moment Context Network (MCN) which effectively localizes natural language queries in videos by integrating local and global video features over time. A key obstacle to training our MCN model is that current video datasets do not include pairs of localized video segments and referring expressions, or text descriptions which uniquely identify a corresponding moment. Therefore, we collect the Distinct Describable Moments (DiDeMo) dataset which consists of over 10,000 unedited, personal videos in diverse visual settings with pairs of localized video segments and referring expressions. We demonstrate that MCN outperforms several baseline methods and believe that our initial results together with the release of DiDeMo will inspire further research on localizing video moments with natural language.

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。

↑