Visual Relationship Recognition via Language and Position Guided Attention
Visual Relationship Recognition via Language and Position Guided Attention
复制标题
DOI：
10.1109/icassp.2019.8683464
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Hao Zhou;Chuanping Hu;Chongyang Zhang;Shengyang Shen
中科院分区：
文献类型：
--
作者：
Hao Zhou;Chuanping Hu;Chongyang Zhang;Shengyang Shen
视觉关系识别作为一项具有挑战性的任务，用于区分对象对之间的相互作用，近年来受到了广泛的关注。考虑到大多数视觉关系是人类定义的语义概念，其中隐藏着许多人类知识或先验知识，这些知识尚未被现有方法充分利用。在这项工作中，我们提出了一种新的视觉关系识别模型，使用语言和位置引导的注意：语言和位置信息的开发和矢量化的第一，然后两者都用来指导注意力地图的生成。通过引导注意，可以更好地利用隐藏的人类知识来增强空间和信道特征的选择。在VRD [2]和VGR [1]上的实验表明，通过语言和位置引导注意模块，我们提出的模型达到了最先进的性能。
Visual relationship recognition, as a challenging task used to distinguish the interactions between object pairs, has received much attention recently. Considering the fact that most visual relationships are semantic concepts defined by human beings, there are many human knowledge, or priors, hidden in them, which haven’t been fully exploited by existing methods. In this work, we propose a novel visual relationship recognition model using language and position guided attention: language and position information are exploited and vectored firstly, and then both of them are used to guide the generation of attention maps. With the guided attention, the hidden human knowledge can be made better use to enhance the selection of spatial and channel features. Experiments on VRD [2] and VGR [1] show that, with language and position guided attention module, our proposed model achieves state-of-the-art performance.