Improving Social Awareness Through DANTE: Deep Affinity Network for Clustering Conversational Interactants
Improving Social Awareness Through DANTE: Deep Affinity Network for Clustering Conversational Interactants
复制标题
通过 DANTE 提高社交意识：用于聚类对话交互者的深度亲和力网络
DOI：
10.1145/3392824
复制
发表时间：
2020
影响因子：
--
通讯作者：
Vázquez, Marynel
中科院分区：
文献类型：
--
作者：
Swofford, Mason;Peruzzi, John;Tsoi, Nathan;Thompson, Sydney;Martín-Martín, Roberto;Savarese, Silvio;Vázquez, Marynel
我们提出了一种数据驱动的方法来检测对话组，方法是识别这些焦点社交接触的典型空间安排。我们的方法使用一种新颖的深度亲和力网络(Dante)来预测场景中的两个人是同一对话组的一部分的可能性，考虑到他们的社会背景。然后，在图聚类框架中使用预测的成对亲和度来识别小的(例如，二元的)和大的组。我们在多个已建立的基准上的评估结果表明，与以前的方法相比，将强大的深度学习方法与经典的聚类技术相结合可以提高会话组的检测能力。最后，我们在人-机器人交互场景中演示了该方法的实用性。我们的努力表明，我们的工作不仅在理论上推进了群体检测，而且在实践中也取得了进步。
We propose a data-driven approach to detect conversational groups by identifying spatial arrangements typical of these focused social encounters. Our approach uses a novel Deep Affinity Network (DANTE) to predict the likelihood that two individuals in a scene are part of the same conversational group, considering their social context. The predicted pair-wise affinities are then used in a graph clustering framework to identify both small (e.g., dyads) and large groups. The results from our evaluation on multiple, established benchmarks suggest that combining powerful deep learning methods with classical clustering techniques can improve the detection of conversational groups in comparison to prior approaches. Finally, we demonstrate the practicality of our approach in a human-robot interaction scenario. Our efforts show that our work advances group detection not only in theory, but also in practice.