Attention-Based Pedestrian Attribute Analysis
Attention-Based Pedestrian Attribute Analysis
复制标题
基于注意力的行人属性分析
DOI：
10.1109/tip.2019.2919199
复制
发表时间：
2019-12-01
影响因子：
10.6
通讯作者：
Li, Stan Z.
中科院分区：
文献类型：
--
作者：
Tan, Zichang;Yang, Yang;Li, Stan Z.
在监控场景中识别行人属性是一项具有挑战性的任务，特别是对于具有大姿态变化，复杂背景和不同摄像机视角的行人图像。为了选择重要和有区别的区域或像素，提出了三种注意机制，包括解析注意、标签注意和空间注意。这些注意的目的是通过从不同的角度考虑问题来获取有效的信息。具体来说，解析注意不仅通过学习将注意力转向哪里，而且通过学习如何从人体的不同语义区域（如头部和上半身）聚集特征来提取判别特征。标签关注的目的是有针对性地收集每个属性的判别特征。与解析和标签注意机制不同，空间注意从全局角度考虑问题，旨在为所有属性选择几个重要的、有区别的图像区域或像素。然后，我们提出了一个以多任务方式制定的联合学习框架，同时学习这三种注意机制，以提取互补和相关的特征。这个联合学习框架被命名为行人属性分析的解析注意、标签注意和空间注意联合学习（JLPLS-PAA，简称）。在PA-100K、RAP、PETA、Market-1501和Duke属性数据集等多个大规模基准上进行了广泛的对比评估，进一步证明了所提出的JLPLS-PAA框架用于行人属性分析的有效性。
Recognizing the pedestrian attributes in surveillance scenes is an inherently challenging task, especially for the pedestrian images with large pose variations, complex backgrounds, and various camera viewing angles. To select important and discriminative regions or pixels against the variations, three attention mechanisms are proposed, including parsing attention, label attention, and spatial attention. Those attentions aim at accessing effective information by considering problems from different perspectives. To be specific, the parsing attention extracts discriminative features by learning not only where to turn attention to but also how to aggregate features from different semantic regions of human bodies, e.g., head and upper body. The label attention aims at targetedly collecting the discriminative features for each attribute. Different from the parsing and label attention mechanisms, the spatial attention considers the problem from a global perspective, aiming at selecting several important and discriminative image regions or pixels for all attributes. Then, we propose a joint learning framework formulated in a multi-task-like way with these three attention mechanisms learned concurrently to extract complementary and correlated features. This joint learning framework is named Joint Learning of Parsing attention, Label attention, and Spatial attention for Pedestrian Attributes Analysis (JLPLS-PAA, for short). Extensive comparative evaluations conducted on multiple large-scale benchmarks, including PA-100K, RAP, PETA, Market-1501, and Duke attribute datasets, further demonstrate the effectiveness of the proposed JLPLS-PAA framework for pedestrian attribute analysis.