Supervised saliency maps for first-person videos based on sparse coding
Supervised saliency maps for first-person videos based on sparse coding
复制标题
DOI：
10.23919/apsipa.2018.8659499
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Yujie Li;Atsunori Kanemura;H. Asoh;Taiki Miyanishi;M. Kawanabe
中科院分区：
文献类型：
--
作者：
Yujie Li;Atsunori Kanemura;H. Asoh;Taiki Miyanishi;M. Kawanabe
第一人称视觉中的非注意区域在我们日常生活中寻找有意义的物体时起着重要的作用。显著性检测是定位这种注意区域的主要技术。然而，即使从用户的角度捕获的FPV总是与他/她的动作相关联，现有的显着性检测方法是自下而上的，并且它们不能结合关于用户的动作的信息。由于人们会看他们动作的目标，FPV的显着性检测算法应该考虑哪些对象更有可能被用户操纵。在本文中，我们提出了一种监督显着性检测方法，使用人类的凝视信息时，用户执行的监督信号的行动。我们提出的方法是基于稀疏编码（字典学习）与监督显着字典。使用真实世界的凝视数据集的实验表明，我们提出的方法优于一个国家的最先进的显着性检测算法的基础上稀疏编码。
Specifying attentive regions in first-person vision (FPV) plays an important role to find meaningful objects in our daily life. Saliency detection is a major technique to locate such attentive regions. However, even though the FPV captured from the user perspective is always associated with his/her actions, existing saliency detection methods are bottom-up, and they cannot incorporate the information about the actions of the user. Since people look at the target of their actions, saliency detection algorithms for FPV should take into account which objects are more likely to be manipulated by the user. In this paper, we propose a supervised saliency detection method that uses human gaze information when the user performs actions as supervised signals. Our proposed method is based on sparse coding (dictionary learning) with a supervised saliency dictionary. Experiments using a real-world gaze dataset show that our proposed approach outperforms a state-of-the-art saliency detection algorithm based on sparse coding.