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

2025/11/03 by Zeng, Minmin
Computer Science · Engineering · Psychology · #68T07 (Artificial neural networks and deep learning) #68U10 (Computer graphics #Action Observation and Synchronization #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Motion and Animation #Human Pose and Action Recognition #computational geometry)

paper · pdf · doi:10.48550/arxiv.2511.01194

openalex publication_date 2025/11/03 · openalex created_date 2025/11/06 · openalex updated_date 2026/07/28

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.

Citations

• AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements
• DFM: Deep Fourier Mimic for Expressive Dance Motion Learning
• A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions
• A Comprehensive Survey of Action Quality Assessment: Method and Benchmark
• A Survey on 3D Egocentric Human Pose Estimation
• Action Quality Assessment with Temporal Parsing Transformer
• FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment
• A survey of top-down approaches for human pose estimation
• Group-aware Contrastive Regression for Action Quality Assessment
• Feedback Graph Convolutional Network for Skeleton-based Action Recognition
• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

Related

• Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition
• UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
• Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
• Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition
• Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition