# TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation

arXiv: https://arxiv.org/abs/2305.08779 · HTML: https://mlsanity.com/paper/2305.08779/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 68 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 16 of 16)

- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [Rank consistent ordinal regression for neural networks with application to age estimation](https://mlsanity.com/paper/1901.07884/) (2019)
- [Deep Regression Forests for Age Estimation](https://mlsanity.com/paper/1712.07195/) (2017)
- [PML: Progressive Margin Loss for Long-tailed Age Classification](https://mlsanity.com/paper/2103.02140/) (2021)
- [C3AE: Exploring the Limits of Compact Model for Age Estimation](https://mlsanity.com/paper/1904.05059/) (2019)
- [Label Distribution Learning Forests](https://mlsanity.com/paper/1702.06086/) (2017)
- [Deep Ordinal Regression with Label Diversity](https://mlsanity.com/paper/2006.15864/) (2020)
- [Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion](https://mlsanity.com/paper/2112.10167/) (2021)
- [Age Progression and Regression with Spatial Attention Modules](https://mlsanity.com/paper/1903.02133/) (2019)
- [Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision](https://mlsanity.com/paper/1911.12509/) (2019)
- [Disguised Face Identification (DFI) with Facial KeyPoints using Spatial Fusion Convolutional Network](https://mlsanity.com/paper/1708.09317/) (2017)
- [FOSS: Multi-Person Age Estimation with Focusing on Objects and Still Seeing Surroundings](https://mlsanity.com/paper/2010.07544/) (2020)

## Built on by (most cited first, 7 of 7)

- [Masked Contrastive Graph Representation Learning for Age Estimation](https://mlsanity.com/paper/2306.17798/) (2023)
- [From Age Estimation to Age-Invariant Face Recognition: Generalized Age Feature Extraction Using Order-Enhanced Contrastive Learning](https://mlsanity.com/paper/2501.01760/) (2025)
- [GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization](https://mlsanity.com/paper/2412.11450/) (2024)
- [Self-Attention Empowered Graph Convolutional Network for Structure Learning and Node Embedding](https://mlsanity.com/paper/2403.03465/) (2024)
- [A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection](https://mlsanity.com/paper/2405.08204/) (2024)
- [LRA-GNN: Latent Relation-Aware Graph Neural Network with Initial and Dynamic Residual for Facial Age Estimation](https://mlsanity.com/paper/2502.05423/) (2025)
- [Learning Subjective Time-Series Data via Utopia Label Distribution Approximation](https://mlsanity.com/paper/2307.07682/) (2023)

## Abstract (arXiv)

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.