A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessment
By: Minmin Zeng
Potential Business Impact:
Teaches computers to judge how well people do actions.
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.
Similar Papers
G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
CV and Pattern Recognition
Helps computers tell similar actions apart.
Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation
CV and Pattern Recognition
Helps computers guess body poses from pictures.
Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks
CV and Pattern Recognition
Teaches computers to recognize actions with less data.