arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.02579cs.CV
收藏

基于空间注意网络的视频操作技能评估

Manipulation-skill Assessment from Videos with Spatial Attention Network

The University of Tokyo(东京大学);Hunan University(湖南大学)

Zhenqiang Li, Yifei Huang, Minjie Cai, Yoichi Sato

摘要:

计算机视觉的最新进展使从视频中自动评估人类执行任务的操作技能成为可能,这在健康康复和制造等领域孕育了许多重要的应用。以前的基于视频的技能评估方法没有考虑人类在评估视频时使用的注意力机制,限制了它们的性能,因为只有一小部分视频区域为技能评估提供信息。我们的动机是估计视频中的注意力,这有助于关注至关重要的视频区域,以更好地进行技能评估。特别是,我们提出了一种新的基于RNN的空间注意力模型,该模型考虑了先前帧的累积注意力状态以及有关正在进行的任务进展的高级知识。我们评估我们的方法上新收集的数据集的婴儿抓握任务和现有的四个数据集的手操作任务。实验结果表明,国家的最先进的性能,可以通过考虑在自动技能评估的注意。

英文摘要:

Recent advances in computer vision have made it possible to automatically assess from videos the manipulation skills of humans in performing a task, which breeds many important applications in domains such as health rehabilitation and manufacturing. Previous methods of video-based skill assessment did not consider the attention mechanism humans use in assessing videos, limiting their performance as only a small part of video regions is informative for skill assessment. Our motivation here is to estimate attention in videos that helps to focus on critically important video regions for better skill assessment. In particular, we propose a novel RNN-based spatial attention model that considers accumulated attention state from previous frames as well as high-level knowledge about the progress of an undergoing task. We evaluate our approach on a newly collected dataset of infant grasping task and four existing datasets of hand manipulation tasks. Experiment results demonstrate that state-of-the-art performance can be achieved by considering attention in automatic skill assessment.

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。

↑