arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1705.02101cs.CV
收藏

TALL:基于语言查询的时间活动定位

TALL: Temporal Activity Localization via Language Query

University of Southern California(南加州大学);Google Research(谷歌研究院)

Jiyang Gao, Chen Sun, Zhenheng Yang, Ram Nevatia

摘要:

本文主要研究未裁剪视频中动作的时间定位问题。现有方法通常针对预定义的动作列表来训练分类器,并且以滑动窗口的方式来应用它们。然而,在野外的活动包括演员,动作和对象的广泛组合;很难设计一个适当的活动列表,以满足用户的需求。我们建议本地化活动的自然语言查询。通过语言的时间活动定位(TALL)是具有挑战性的,因为它需要:(1)文本和视频表示的适当设计,以允许动作和语言查询的跨模态匹配;(2)从有限粒度的滑动窗口中准确定位动作的能力。我们提出了一种新的跨模态时间回归定位器(CTRL),联合建模文本查询和视频剪辑,输出对齐分数和候选剪辑的动作边界回归结果。为了进行评估,我们采用TaCoS数据集,并通过添加句子时间注释,在Charades之上为该任务构建一个新的数据集,称为Charades-STA。我们还在Charades-STA中构建了复杂句子查询进行测试。实验结果表明,CTRL在两个数据集上都明显优于以前的方法。

英文摘要:

This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist of a wide combination of actors, actions and objects; it is difficult to design a proper activity list that meets users' needs. We propose to localize activities by natural language queries. Temporal Activity Localization via Language (TALL) is challenging as it requires: (1) suitable design of text and video representations to allow cross-modal matching of actions and language queries; (2) ability to locate actions accurately given features from sliding windows of limited granularity. We propose a novel Cross-modal Temporal Regression Localizer (CTRL) to jointly model text query and video clips, output alignment scores and action boundary regression results for candidate clips. For evaluation, we adopt TaCoS dataset, and build a new dataset for this task on top of Charades by adding sentence temporal annotations, called Charades-STA. We also build complex sentence queries in Charades-STA for test. Experimental results show that CTRL outperforms previous methods significantly on both datasets.

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。

↑