Weakly Supervised Learning of Interactions between Humans and Objects
Weakly Supervised Learning of Interactions between Humans and Objects
复制标题
DOI：
10.1109/tpami.2011.158
复制
发表时间：
2012-03-01
影响因子：
23.6
通讯作者：
Ferrari, Vittorio
中科院分区：
文献类型：
--
作者：
Prest, Alessandro;Schmid, Cordelia;Ferrari, Vittorio
我们介绍了一种弱监督的方法来学习人类的行为建模为人类和对象之间的相互作用。我们的方法是以人为中心：我们首先定位图像中的人，然后确定与动作相关的对象及其与人的空间关系。该模型是从一组只标注了动作标签的静态图像中自动学习的。我们的方法依赖于人类检测器来初始化模型学习。对于不同程度的可见性的鲁棒性，我们建立了一个检测器，学习联合收割机一组现有的部分检测器。从人类检测到的一组图像描绘的行动，我们的方法确定的动作对象和它的空间关系的人。其最终输出是人-物体交互的概率模型，即，人与物体之间的空间关系。我们对来自[1]的体育动作数据集、PASCAL Action 2010数据集[2]和新的人机交互数据集进行了广泛的实验评估。
We introduce a weakly supervised approach for learning human actions modeled as interactions between humans and objects. Our approach is human-centric: We first localize a human in the image and then determine the object relevant for the action and its spatial relation with the human. The model is learned automatically from a set of still images annotated only with the action label. Our approach relies on a human detector to initialize the model learning. For robustness to various degrees of visibility, we build a detector that learns to combine a set of existing part detectors. Starting from humans detected in a set of images depicting the action, our approach determines the action object and its spatial relation to the human. Its final output is a probabilistic model of the human-object interaction, i.e., the spatial relation between the human and the object. We present an extensive experimental evaluation on the sports action data set from [1], the PASCAL Action 2010 data set [2], and a new human-object interaction data set.