当前位置: X-MOL 学术IEEE Trans. Affect. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
On Social Involvement in Mingling Scenarios: Detecting Associates of F-formations in Still Images
IEEE Transactions on Affective Computing ( IF 11.2 ) Pub Date : 2018-01-01 , DOI: 10.1109/taffc.2018.2855750
Lu Zhang , Hayley Hung

In this paper, we carry out an extensive study of social involvement in free standing conversing groups (the so-called F-formations) from static images. By introducing a novel feature representation, we show that the standard features which have been used to represent full membership in an F-formation cannot be applied to the detection of associates of F-formations due their sparser occurence. We enrich state-of-the-art F-formation modelling by learning a frustum of attention that accounts for the spatial context. That is, F-formation configurations vary with respect to the arrangement of furniture and the non-uniform crowdednessin the space during mingling scenarios. Moroever, the majority of prior works have considered the labelling of conversing groups as an objective task, requiring only a single annotator. However, we show that by embracing the subjectivity of social involvement, we not only generate a richer model of the social interactions in a scene but can use the detected associates to improve initial estimates of the full members of an F-formation. We carry out extensive experimental validation of our proposed approach by collecting a novel set of multi-annotator labels of involvement on two publicly available datasets; The Idiap Poster Data and SALSA data set.

中文翻译:

关于混合场景中的社会参与:检测静止图像中 F 形的关联

在本文中,我们从静态图像中对自由站立的对话群体(所谓的 F 阵型)中的社会参与进行了广泛的研究。通过引入一种新的特征表示,我们表明已用于表示 F 编组中完全隶属关系的标准特征不能应用于检测 F 编组的关联,因为它们的出现较为稀疏。我们通过学习解释空间上下文的注意力截头体来丰富最先进的 F 形成建模。也就是说,在混合场景中,F 形配置因家具的布置和空间中不均匀的拥挤程度而异。此外,大多数先前的工作都将会话组的标记视为一项客观任务,只需要一个注释者。然而,我们表明,通过接受社会参与的主观性,我们不仅可以生成更丰富的场景中社会互动模型,而且可以使用检测到的关联来改进对 F 组完整成员的初始估计。我们通过在两个公开可用的数据集上收集一组新的多注释器标签,对我们提出的方法进行了广泛的实验验证;Idiap 海报数据和 SALSA 数据集。
更新日期:2018-01-01
down
wechat
bug