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 1705.09467cs.CV
收藏

基于相对注意模型的人机交互预测

Predicting Human Interaction via Relative Attention Model

Shanghai Jiao Tong University(上海交通大学)

Yichao Yan, Bingbing Ni, Xiaokang Yang

摘要:

预测人类交互是具有挑战性的,因为必须基于部分观察到的视频来推断正在进行的活动。从本质上讲,一个好的算法应该有效地模拟两个交互主体之间的相互影响。此外,只有场景中的一个小区域是有区别的,用于识别正在进行的交互。在这项工作中,我们提出了一个相对注意力模型,明确地解决这些困难。建立在一个三耦合的深度递归结构,代表相互作用的主题和全球互动状态,建议的网络收集时空信息,从每个主题,纠正与全球互动信息,产生有效的互动表示。此外,建议的网络还统一了一个注意力模块,以分配更高的重要性,与正在进行的行动相关的区域。在两个公共数据集上进行了大量的实验,结果表明,所提出的相对注意力网络成功地预测了交互主体之间的信息区域,从而产生了优越的人类交互预测精度。

英文摘要:

Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model the mutual influence between the two interacting subjects. Also, only a small region in the scene is discriminative for identifying the on-going interaction. In this work, we propose a relative attention model to explicitly address these difficulties. Built on a tri-coupled deep recurrent structure representing both interacting subjects and global interaction status, the proposed network collects spatio-temporal information from each subject, rectified with global interaction information, yielding effective interaction representation. Moreover, the proposed network also unifies an attention module to assign higher importance to the regions which are relevant to the on-going action. Extensive experiments have been conducted on two public datasets, and the results demonstrate that the proposed relative attention network successfully predicts informative regions between interacting subjects, which in turn yields superior human interaction prediction accuracy.

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。

↑