A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessment

TL;DR

This paper introduces a topology-aware GCN framework for human pose similarity and action quality assessment, leveraging skeletal graph structures to improve discriminative pose embeddings and outperform coordinate-based methods.

Contribution

It presents a novel GCN-PSN model that incorporates skeletal topology into pose embeddings, enhancing action quality assessment accuracy.

Findings

Outperforms coordinate-based baselines on AQA-7 and FineDiving datasets.

Validates the effectiveness of skeletal topology in pose similarity tasks.

Achieves competitive results demonstrating the model's robustness.

Abstract

Action Quality Assessment (AQA) requires fine-grained understanding of human motion and precise evaluation of pose similarity. This paper proposes a topology-aware Graph Convolutional Network (GCN) framework, termed GCN-PSN, which models the human skeleton as a graph to learn discriminative, topology-sensitive pose embeddings. Using a Siamese architecture trained with a contrastive regression objective, our method outperforms coordinate-based baselines and achieves competitive performance on AQA-7 and FineDiving benchmarks. Experimental results and ablation studies validate the effectiveness of leveraging skeletal topology for pose similarity and action quality assessment.