TAA-GCN: A temporally aware Adaptive Graph Convolutional Network for age estimation. (February 2023)

• Record Type: Journal Article
• Authors: Korban, Matthew; Youngs, Peter; Acton, Scott T.
• Is Part Of: Pattern recognition. Volume 134(2023)
• Publication Date: 2023-02
• Subjects: Age estimation -- Graph convolutional network -- Facial graphs -- Skeletal graphs; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109066
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Proposed a new age estimation algorithm using Facial and Skeletal-Cosmetic graphs. The proposed TAA-GCN includes two new modules AGCL and TMM. The TMM capture non-ordinal temporal dependencies and the AGCL refines graphs. Proposed a new graph representation based on face, skeleton, posture, and clothing. The proposed algorithm outperformed SOTA methods on four public datasets. Abstract: This paper proposes a novel age estimation algorithm, the Temporally-Aware Adaptive Graph Convolutional Network (TAA-GCN). Using a new representation based on graphs, the TAA-GCN utilizes skeletal, posture, clothing, and facial information to enrich the feature set associated with various ages. Such a novel graph representation has several advantages: First, reduced sensitivity to facial expression and other appearance variances; Second, robustness to partial occlusion and non-frontal-planar viewpoint, which is commonplace in real-world applications such as video surveillance. The TAA-GCN employs two novel components, (1) the Temporal Memory Module (TMM) to compute temporal dependencies in age; (2) Adaptive Graph Convolutional Layer (AGCL) to refine the graphs and accommodate the variance in appearance. The TAA-GCN outperforms the state-of-the-art methods on four public benchmarks, UTKFace, MORPHII, CACD, and FG-NET. Moreover, the TAA-GCN showed reliability in different camera viewpoints and reduced quality images.