arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.09791cs.CV
收藏

身份感知的多句子视频描述

Identity-Aware Multi-Sentence Video Description

Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);University of California, Berkeley(加州大学伯克利分校)

Jae Sung Park, Trevor Darrell, Anna Rohrbach

摘要:

标准的视频和电影描述任务从人的身份中抽象出来,因此无法将句子中的身份联系起来。我们提出了一个多句子的身份感知视频描述任务,它克服了这一限制,并需要重新识别本地的一组连续的剪辑内的人。我们引入了一个辅助任务的填写身份,其目的是预测一致的人的身份在一组剪辑,当视频描述。我们提出的这个任务的方法利用了一个Transformer架构,允许多个ID的相干联合预测。其中一个关键组成部分是一个性别意识的文本表示,以及一个额外的性别预测目标的主要模型。这个辅助任务使我们能够提出一个两阶段的方法来识别视频描述。我们首先生成多句视频描述,然后应用我们的填充身份模型来建立预测的人实体之间的联系。为了能够解决这两个任务,我们增加了大规模电影描述挑战(LSMDC)基准与新的注释适合我们的问题陈述。实验表明,我们提出的填充身份模型优于几个基线和最近的作品,并允许我们生成本地重新识别的人的描述。

英文摘要:

Standard video and movie description tasks abstract away from person identities, thus failing to link identities across sentences. We propose a multi-sentence Identity-Aware Video Description task, which overcomes this limitation and requires to re-identify persons locally within a set of consecutive clips. We introduce an auxiliary task of Fill-in the Identity, that aims to predict persons' IDs consistently within a set of clips, when the video descriptions are given. Our proposed approach to this task leverages a Transformer architecture allowing for coherent joint prediction of multiple IDs. One of the key components is a gender-aware textual representation as well an additional gender prediction objective in the main model. This auxiliary task allows us to propose a two-stage approach to Identity-Aware Video Description. We first generate multi-sentence video descriptions, and then apply our Fill-in the Identity model to establish links between the predicted person entities. To be able to tackle both tasks, we augment the Large Scale Movie Description Challenge (LSMDC) benchmark with new annotations suited for our problem statement. Experiments show that our proposed Fill-in the Identity model is superior to several baselines and recent works, and allows us to generate descriptions with locally re-identified people.

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。

↑