{"ID":2846479,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01194","arxiv_id":"2511.01194","title":"A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessment","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.","short_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 emb...","url_abs":"https://arxiv.org/abs/2511.01194","url_pdf":"https://arxiv.org/pdf/2511.01194v1","authors":"[\"Minmin Zeng\"]","published":"2025-11-03T03:38:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}