Human-Object Interaction Detection with Missing Objects
Human-Object Interaction Detection with Missing Objects
复制标题
DOI：
10.23919/mva51890.2021.9511361
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Kaen Kogashi;Yang Wu;S. Nobuhara;K. Nishino
中科院分区：
文献类型：
--
作者：
Kaen Kogashi;Yang Wu;S. Nobuhara;K. Nishino
现有的人-物交互(HoI)研究假设可以检测到人和对象实例。针对对象实例不一定容易检测的情况，提出了一种更实用的HOI检测方法。据我们所知，我们引入了第一种方法来检测这种具有挑战性的HOI，它结合了全局场景信息。两个使用最广泛的公共HOI基准数据集显示包含许多具有缺失对象的HOI案例(HOI-MO)。我们对这些进行标记，以组成所提出的方法的新测试集。通过大量的实验和比较，证明了该方法的有效性和优越性。
Existing studies on human-object interaction (HOI) assume that human and object instances can be detected. This paper proposes a more practical HOI detection method for when object instances are not necessarily easily detectable. To our knowledge, we introduce the first method for such challenging HOI detection that incorporates global scene information. The two most widely used public HOI benchmark datasets are shown to contain many cases of HOI with missing objects (HOI-MO). We label these to compose new test sets for the proposed method. The effectiveness and superiority of the proposed method are demonstrated through extensive experiments and comparisons.