A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessment
This work addresses fine-grained human motion evaluation for applications like sports analysis, but it is incremental as it builds on existing GCN methods for pose similarity.
The paper tackled the problem of Action Quality Assessment (AQA) by proposing a topology-aware Graph Convolutional Network (GCN-PSN) that models human skeletons as graphs to learn pose embeddings, achieving competitive performance on AQA-7 and FineDiving benchmarks.
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.