Head detection plays an important role in localizing and identifying persons from visual data. Most existing methods treat head detection as a specific form of object detection. Head detection is nontrivial due to the considerable difficulty in building the local and global information under conditions of unconstrained pose and orientation. To address these issues, this paper presents an effective adaptive relational network to capture context information, which is greatly helpful to suppress missed detection. We show that the fundamental contextual properties, such as the global shape priors from different heads and the local adjacent relationship between the head and shoulders, can be systematically quantified by visual operators. Specifically, we propose a two-step search algorithm to quantify the global intergroup conflict with adaptive scale, pose and viewpoint. Meanwhile, a structured feature module is introduced to capture the local relation of intraindividual stability. Finally, the global priors and local relation are integrated seamlessly into a single-stage head detector that is end-to-end trainable. An extensive ablation analysis demonstrates the effectiveness of our approach. We achieve state-of-the-art results on two challenging datasets, i.e., HollywoodHeads and Brainwash.

中文翻译：

---

HeadNet：用于头部检测的端到端自适应关系网络

头部检测在根据视觉数据定位和识别人员方面起着重要作用。大多数现有方法将头部检测视为对象检测的一种特定形式。由于在不受约束的姿势和方向的条件下构建局部和全局信息相当困难，因此头部检测非常重要。针对这些问题，本文提出了一种有效的自适应关系网络来捕获上下文信息，这对抑制漏检有很大帮助。我们表明，基本的上下文属性，例如来自不同头部的全局形状先验和头部和肩部之间的局部相邻关系，可以通过视觉算子系统地量化。具体来说，我们提出了一种两步搜索算法来量化具有自适应尺度的全局组间冲突，姿势和观点。同时，引入了结构化特征模块来捕捉个体内部稳定性的局部关系。最后，全局先验和局部关系无缝集成到可端到端训练的单级头部检测器中。广泛的消融分析证明了我们方法的有效性。我们在两个具有挑战性的数据集上取得了最先进的结果，即 HollywoodHeads 和 Brainwash。