最重要人物引导的双分支跨补丁注意力用于群体情感识别
Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition
AI总结：
本文提出双分支跨补丁注意力Transformer（DCAT），引入最重要人物（MIP）概念，融合全局与MIP特征，在多个群体情感数据集上超越现有方法，并展示其可迁移至群体凝聚力任务。
摘要：
群体情感是指群体中由外部刺激引发的主观情绪，它是塑造群体行为和结果的重要因素。识别群体情感涉及识别群体中能够引发情绪的重要个体和显著对象。然而，现有大多数方法缺乏对群体动态中情感意义的关注，并且未能考虑群体级图像中面部和物体的上下文相关性。在这项工作中，我们通过引入心理学概念“最重要人物”（MIP）来提出一种解决方案，该概念代表群体中最值得注意的面部，并具有情感语义。我们提出了双分支跨补丁注意力Transformer（DCAT），它将全局图像和MIP共同作为输入。具体来说，我们首先分别学习由MIP和全局上下文产生的信息性面部区域。然后，提出跨补丁注意力模块，将MIP和全局上下文的特征融合在一起，以相互补充。我们提出的方法在GAF 3.0、GroupEmoW和HECO数据集上优于最先进的方法。此外，我们通过展示所提出的模型可以迁移到另一个群体情感任务——群体凝聚力，并取得可比结果，证明了其更广泛应用的潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
