Person attribute recognition aims to identify the attribute labels from the pedestrian images. Extracting contextual relation from the images and attributes, including the spatial-semantic relations, the spatial context and the semantic correlation, is beneficial to enhance the discrimination of the features for recognizing the attributes. Thus, this work proposes a sequence contextual relation learning (SCRL) method to capture these relations. It first embeds the images and attributes into sequences in two branches. Then SCRL flexibly learns the contextual relation from the sequences with the parallel attention model structure, which integrates the inter-attention and intra-attention models. The inter-attention module is utilized to extract the spatial-semantic relations, while the intra-attention is designed to gain the spatial context and the semantic correlation. Both attention modules are comprised of several parallel attention units and each unit can obtain the pairwise relations in one subspace. Therefore, they obtain the relations in multiple subspaces, which can improve the comprehensiveness of the relation learning. Additionally, for the sake of better extraction of spatial-semantic relations, this paper employs connectionist temporal classification (CTC) loss which is capable of driving the network to enforce monotonic alignment between the image and attribute. It can also accelerate the convergence of the network by the algorithm in it. Extensive experiments on five public datasets, i.e., Market-1501 attribute, Duke attribute, PETA, RAP and PA-100K datasets, demonstrate the effectiveness of the proposed method.

中文翻译：

---

基于序列上下文关系学习的人物属性识别

行人属性识别旨在从行人图像中识别属性标签。从图像和属性中提取上下文关系，包括空间语义关系、空间上下文和语义相关性，有利于增强特征的判别能力，以识别属性。因此，这项工作提出了一种序列上下文关系学习（SCRL）方法来捕获这些关系。它首先将图像和属性嵌入到两个分支的序列中。然后SCRL灵活地从具有并行注意力模型结构的序列中学习上下文关系，该结构集成了注意力间和注意力内模型。inter-attention模块用于提取空间语义关系，而intra-attention旨在获得空间上下文和语义相关性。两个注意力模块都由几个并行的注意力单元组成，每个单元都可以在一个子空间中获得成对关系。因此，他们获得了多个子空间中的关系，可以提高关系学习的综合性。此外，为了更好地提取空间语义关系，本文采用了连接主义时间分类（CTC）损失，它能够驱动网络强制执行图像和属性之间的单调对齐。它还可以通过其中的算法加速网络的收敛。在五个公共数据集上进行了大量实验，即 Market-1501 属性、Duke 属性、PETA、RAP 和 PA-100K 数据集，