论文标题
深层模板匹配行人属性识别与属性关键的辅助监督的匹配
Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints
论文作者
论文摘要
由于其在视频监视场景中的重要作用，行人属性识别（PAR）引起了广泛的关注。在大多数情况下，特定属性的存在与部分区域密切相关。最近的作品设计了复杂的模块，例如注意机制和身体部位的建议，以定位属性相应的区域。这些作品进一步证明，属性特定区域的定位精确将有助于提高性能。但是，这些基于部分信息的方法仍然不准确，并且增加了模型复杂性，这使得很难在现实的应用程序上部署。在本文中，我们提出了一种基于模板匹配的深度匹配方法，以捕获较少计算的身体部位特征。此外，我们还提出了一种辅助监督方法，该方法使用人类姿势关键点来指导学习界面的局部线索。广泛的实验表明，与大规模行人属性数据集（包括PETA，PA-100K，RAP，RAP和RAPV2 ZS）相比，该提出的方法比最先进的方法优于计算复杂性，并且具有较低的计算复杂性。
Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios. In most cases, the existence of a particular attribute is strongly related to a partial region. Recent works design complicated modules, e.g., attention mechanism and proposal of body parts to localize the attribute corresponding region. These works further prove that localization of attribute specific regions precisely will help in improving performance. However, these part-information-based methods are still not accurate as well as increasing model complexity which makes it hard to deploy on realistic applications. In this paper, we propose a Deep Template Matching based method to capture body parts features with less computation. Further, we also proposed an auxiliary supervision method that use human pose keypoints to guide the learning toward discriminative local cues. Extensive experiments show that the proposed method outperforms and has lower computational complexity, compared with the state-of-the-art approaches on large-scale pedestrian attribute datasets, including PETA, PA-100K, RAP, and RAPv2 zs.
