MCGCN: Multi-Correlation Graph Convolutional Network for Pedestrian Attribute Recognition

文献类型： 外文期刊

第一作者： Yu, Yang

作者： Yu, Yang;Liu, Longlong;Zhu, Ye;Cen, Shixin;Li, Yang

作者机构：

关键词： key pedestrian attribute recognition; synthesis graph; semantic correlation; regional correlation

期刊名称：IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS （ 影响因子：0.7； 五年影响因子：0.7 ）

ISSN： 0916-8532

年卷期： 2024 年 E107D 卷 3 期

页码：

收录情况： SCI

摘要： Pedestrian attribute recognition (PAR) aims to recognize a series of a person's semantic attributes, e.g., age, gender, which plays an important role in video surveillance. This paper proposes a multi-cor relation graph convolutional network named MCGCN for PAR, which includes a semantic graph, visual graph, and synthesis graph. We construct a semantic graph by using attribute features with semantic constraints. A graph convolution is employed, based on prior knowledge of the dataset, to learn the semantic correlation. 2D features are projected onto visual graph nodes and each node corresponds to the feature region of each attribute group. Graph convolution is then utilized to learn regional correlation. The visual graph nodes are connected to the semantic graph nodes to form a synthesis graph. In the synthesis graph, regional and semantic correlation are embedded into each other through inter-graph edges, to guide each other's learning and to update the visual and semantic graph, thereby constructing semantic and regional correlation. On this basis, we use a better loss weighting strategy, the suit_polyloss, to address the imbalance of pedestrian attribute datasets. Experiments on three benchmark datasets show that the proposed approach achieves superior recognition performance compared to existing technologies, and achieves state-of-the-art performance.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序