arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.11618cs.CVcs.AIcs.CL
收藏

VIOLIN:一个大规模的视频和语言推理数据集

VIOLIN: A Large-Scale Dataset for Video-and-Language Inference

Carnegie Mellon University(卡内基梅隆大学);University of California, Santa Barbara(加利福尼亚大学圣巴巴拉分校);Microsoft Dynamics 365 AI Research(微软Dynamics 365人工智能研究)

Jingzhou Liu, Wenhu Chen, Yu Cheng, Zhe Gan, Licheng Yu, Yiming Yang, Jingjing Liu

摘要:

我们介绍了一个新的任务,视频和语言推理,联合多模态理解的视频和文本。给定具有对齐的字幕的视频剪辑作为前提,与基于视频内容的自然语言假设配对,模型需要推断该假设是由给定的视频剪辑引起的还是矛盾的。为此任务引入了一个新的大规模数据集,名为Violin(视频和语言推理),它由来自15,887个视频剪辑的95,322个视频假设对组成,跨越582小时的视频。这些视频剪辑包含丰富的内容,具有不同的时间动态,事件转移和人的互动,从两个来源收集:(i)流行的电视节目,和(ii)来自YouTube频道的电影剪辑。为了解决我们新的多模态推理任务,需要一个模型拥有复杂的推理技能,从表面水平的基础(例如,识别视频中的对象和人物)到深入的常识推理(例如,推断视频中事件的因果关系)。我们对数据集进行了详细的分析,并对许多强基线进行了广泛的评估,为这项新任务的挑战提供了有价值的见解。

英文摘要:

We introduce a new task, Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. A new large-scale dataset, named Violin (VIdeO-and-Language INference), is introduced for this task, which consists of 95,322 video-hypothesis pairs from 15,887 video clips, spanning over 582 hours of video. These video clips contain rich content with diverse temporal dynamics, event shifts, and people interactions, collected from two sources: (i) popular TV shows, and (ii) movie clips from YouTube channels. In order to address our new multimodal inference task, a model is required to possess sophisticated reasoning skills, from surface-level grounding (e.g., identifying objects and characters in the video) to in-depth commonsense reasoning (e.g., inferring causal relations of events in the video). We present a detailed analysis of the dataset and an extensive evaluation over many strong baselines, providing valuable insights on the challenges of this new task.

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。

↑