TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation
This addresses age estimation for applications like video surveillance by improving robustness to facial expressions, occlusions, and non-frontal viewpoints, though it appears incremental as it builds on existing graph convolutional methods.
The paper tackled age estimation by proposing TAA-GCN, a novel graph-based network that integrates skeletal, posture, clothing, and facial information, achieving state-of-the-art performance on benchmarks like UTKFace, MORPHII, CACD, and FG-NET.
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.