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 2007.08814cs.CV
收藏

视频中的视觉关系基础

Visual Relation Grounding in Videos

National University of Singapore(新加坡国立大学);Chinese Academy of Sciences(中国科学院)

Junbin Xiao, Xindi Shang, Xun Yang, Sheng Tang, Tat-Seng Chua

摘要:

在本文中,我们探索了一个新的任务命名为视频中的视觉关系接地(vRGV)。该任务旨在时空定位视频中以主谓宾形式存在的给定关系,以便为其他高级视频语言任务(例如,视频语言基础和视频问答)。该任务中的挑战包括但不限于:(1)主体和对象都需要被时空定位以建立查询关系;(2)视频中视觉关系的时间动态性质难以捕获;以及(3)应该在没有空间和时间上的任何直接监督的情况下实现建立。为了解决这些问题,我们通过关系关注和重构,在构建的层次时空区域图上协同优化两个区域序列,并进一步提出了一种通过视觉实体之间的空间注意力转移来传递消息的机制。实验结果表明,我们的模型不仅可以显着优于基线方法,但也产生视觉上有意义的事实,以支持视觉接地。(Code可以在https://github.com/doc-doc/vRGV上找到)。

英文摘要:

In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV). The task aims at spatio-temporally localizing the given relations in the form of subject-predicate-object in the videos, so as to provide supportive visual facts for other high-level video-language tasks (e.g., video-language grounding and video question answering). The challenges in this task include but not limited to: (1) both the subject and object are required to be spatio-temporally localized to ground a query relation; (2) the temporal dynamic nature of visual relations in videos is difficult to capture; and (3) the grounding should be achieved without any direct supervision in space and time. To ground the relations, we tackle the challenges by collaboratively optimizing two sequences of regions over a constructed hierarchical spatio-temporal region graph through relation attending and reconstruction, in which we further propose a message passing mechanism by spatial attention shifting between visual entities. Experimental results demonstrate that our model can not only outperform baseline approaches significantly, but also produces visually meaningful facts to support visual grounding. (Code is available at https://github.com/doc-doc/vRGV).

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。

↑