Dance Style Recognition Using Laban Movement Analysis

2025-04-29

AI Summary

To address the challenge of modeling temporal dynamics and inter-frame transitions in Laban Movement Analysis (LMA) features for automatic dance style recognition, this paper proposes a spatiotemporal-enhanced LMA feature extraction and classification framework. It integrates 3D pose estimation, SMPL-X human mesh reconstruction, and ground-aware motion modeling to generate physically grounded motion representations. We introduce a novel sliding-window temporal encoding mechanism that explicitly captures the dynamic evolution of core LMA components—effort, space, and shape. Furthermore, a multi-model classifier is combined with SHAP-based interpretability analysis to quantify the contribution of each motion dimension to classification decisions. Evaluated on a standard dance dataset, our method achieves 99.18% accuracy, substantially outperforming state-of-the-art approaches. This demonstrates both the efficacy and interpretability of temporally enhanced LMA features for fine-grained dance style recognition.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Motion & Tracking
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

The growing interest in automated movement analysis has presented new challenges in recognition of complex human activities including dance. This study focuses on dance style recognition using features extracted using Laban Movement Analysis. Previous studies for dance style recognition often focus on cross-frame movement analysis, which limits the ability to capture temporal context and dynamic transitions between movements. This gap highlights the need for a method that can add temporal context to LMA features. For this, we introduce a novel pipeline which combines 3D pose estimation, 3D human mesh reconstruction, and floor aware body modeling to effectively extract LMA features. To address the temporal limitation, we propose a sliding window approach that captures movement evolution across time in features. These features are then used to train various machine learning methods for classification, and their explainability explainable AI methods to evaluate the contribution of each feature to classification performance. Our proposed method achieves a highest classification accuracy of 99.18% which shows that the addition of temporal context significantly improves dance style recognition performance.

Problem

• Recognizing dance styles using Laban Movement Analysis features
• Addressing temporal context limitations in movement analysis
• Improving classification accuracy with explainable AI methods

Innovation

• Combines 3D pose estimation and mesh reconstruction
• Uses sliding window for temporal movement analysis
• Applies explainable AI for feature contribution evaluation