论文标题
人类群体检测的自我监督社会关系表示
Self-supervised Social Relation Representation for Human Group Detection
论文作者
论文摘要
将人群分组分组的人类群体检测是基于视频的人类社交活动分析的重要步骤。人类群体检测的核心是人类的社会关系代表和划分。在本文中，我们为人类群体检测提出了一个新的两阶段多头框架。在第一阶段，我们建议人类行为模拟者负责人学习社会关系特征的嵌入，该特征是通过利用社会扎根的多人行为关系来自学训练的。在第二阶段，基于社会关系嵌入，我们开发了一个自我发挥的启发人类群体检测网络。在两个最先进的大规模基准（即熊猫和JRDB组）上表现出色，可以验证拟议框架的有效性。受益于自我监督的社会关系嵌入，我们的方法可以提供有希望的结果，而培训数据很少（标签）。我们将向公众发布源代码。
Human group detection, which splits crowd of people into groups, is an important step for video-based human social activity analysis. The core of human group detection is the human social relation representation and division.In this paper, we propose a new two-stage multi-head framework for human group detection. In the first stage, we propose a human behavior simulator head to learn the social relation feature embedding, which is self-supervisely trained by leveraging the socially grounded multi-person behavior relationship. In the second stage, based on the social relation embedding, we develop a self-attention inspired network for human group detection. Remarkable performance on two state-of-the-art large-scale benchmarks, i.e., PANDA and JRDB-Group, verifies the effectiveness of the proposed framework. Benefiting from the self-supervised social relation embedding, our method can provide promising results with very few (labeled) training data. We will release the source code to the public.
