Gtnet: guided transformer network for detecting human-object interactions
Gtnet: guided transformer network for detecting human-object interactions
复制标题
DOI：
10.1117/12.2663936
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
A S M Iftekhar;Satish Kumar;R. McEver;Suya You;B. S. Manjunath
中科院分区：
文献类型：
--
作者：
A S M Iftekhar;Satish Kumar;R. McEver;Suya You;B. S. Manjunath
人-物交互(HoI)检测任务是指定位人、定位对象以及预测每个人-物对之间的交互。HOI被认为是真正理解复杂视觉场景的基本步骤之一。为了检测HOI，重要的是利用相对空间构型和对象语义来找到突出显示人类对象对之间相互作用的图像的显著空间区域。基于自我注意的新型引导变压器网络GTNet解决了这一问题。GTNet通过自我注意在人类和物体视觉特征中编码这种空间上下文信息，同时在V-COCO1和HICO-DET2数据集上获得最先进的结果。代码可以在∗上在线获得。
The human-object interaction (HOI) detection task refers to localizing humans, localizing objects, and predicting the interactions between each human-object pair. HOI is considered one of the fundamental steps in truly understanding complex visual scenes. For detecting HOI, it is important to utilize relative spatial configurations and object semantics to find salient spatial regions of images that highlight the interactions between human object pairs. This issue is addressed by the novel self-attention based guided transformer network, GTNet. GTNet encodes this spatial contextual information in human and object visual features via self-attention while achieving state of the art results on both the V-COCO1 and HICO-DET2 datasets. Code is available online∗.