论文标题
最重要的人为引导的双分支交叉点关注小组情感识别
Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition
论文作者
论文摘要
群体影响是指小组中外部刺激引起的主观情绪，这是塑造群体行为和结果的重要因素。认识群体的影响涉及在人群中识别重要的个人和显着物体，以唤起情绪。但是，大多数现有方法都缺乏对组动态中情感含义的关注，并且无法说明小组级图像中面部和对象的上下文相关性。在这项工作中，我们通过纳入最重要的人（MIP）的心理概念来提出解决方案，该概念代表了人群中最值得注意的面孔，并具有情感的语义含义。我们介绍了双分支交叉斑点注意变压器（DCAT），该变压器（DCAT）将全局图像和MIP一起用作输入。具体而言，我们首先分别学习了MIP和全球背景所产生的内容丰富的面部区域。然后，提出了交叉点注意模块将MIP和全局上下文的特征融合在一起以相互补充。我们提出的方法优于GAF 3.0，GroupeMow和Heco数据集上的最新方法。此外，我们通过证明我们所提出的模型可以转移到另一组群体任务，组凝聚力并实现可比的结果来证明更广泛的应用的潜力。
Group affect refers to the subjective emotion that is evoked by an external stimulus in a group, which is an important factor that shapes group behavior and outcomes. Recognizing group affect involves identifying important individuals and salient objects among a crowd that can evoke emotions. However, most existing methods lack attention to affective meaning in group dynamics and fail to account for the contextual relevance of faces and objects in group-level images. In this work, we propose a solution by incorporating the psychological concept of the Most Important Person (MIP), which represents the most noteworthy face in a crowd and has affective semantic meaning. We present the Dual-branch Cross-Patch Attention Transformer (DCAT) which uses global image and MIP together as inputs. Specifically, we first learn the informative facial regions produced by the MIP and the global context separately. Then, the Cross-Patch Attention module is proposed to fuse the features of MIP and global context together to complement each other. Our proposed method outperforms state-of-the-art methods on GAF 3.0, GroupEmoW, and HECO datasets. Moreover, we demonstrate the potential for broader applications by showing that our proposed model can be transferred to another group affect task, group cohesion, and achieve comparable results.
