Dance Style Classification using Laban-Inspired and Frequency-Domain Motion Features

2025-11-25

AI Summary

Dance style classification is challenging due to high similarity in pose configurations and motion patterns across styles. To address this, we propose a lightweight, interpretable two-stream motion representation method. First, inspired by Laban Movement Analysis, we extract local spatiotemporal dynamic descriptors—including upper-body velocity, acceleration, and joint-angle variation—from skeletal trajectories estimated from video. Second, we capture rhythmic periodicity via frequency-domain features derived from Fast Fourier Transform (FFT). Unlike deep learning–based approaches, our method requires no complex neural architectures, ensuring strong physical interpretability and computational efficiency. Evaluated on benchmark datasets, it achieves robust fine-grained dance style classification under low-resource constraints. Experimental results demonstrate that integrating biomechanically grounded dynamic modeling with spectral analysis yields an effective, generalizable, and human-interpretable motion representation for discriminative dance genre recognition.

Technology Category

• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Representation Learning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Dance is an essential component of human culture and serves as a tool for conveying emotions and telling stories. Identifying and distinguishing dance genres based on motion data is a complex problem in human activity recognition, as many styles share similar poses, gestures, and temporal motion patterns. This work presents a lightweight framework for classifying dance styles that determines motion characteristics based on pose estimates extracted from videos. We propose temporal-spatial descriptors inspired by Laban Movement Analysis. These features capture local joint dynamics such as velocity, acceleration, and angular movement of the upper body, enabling a structured representation of spatial coordination. To further encode rhythmic and periodic aspects of movement, we integrate Fast Fourier Transform features that characterize movement patterns in the frequency domain. The proposed approach achieves robust classification of different dance styles with low computational effort, as complex model architectures are not required, and shows that interpretable motion representations can effectively capture stylistic nuances.

Problem

• Classifying dance styles using motion data from video pose estimates
• Distinguishing similar dance genres with shared poses and temporal patterns
• Developing lightweight computational framework for interpretable dance movement analysis

Innovation

• Laban-inspired temporal-spatial descriptors for joint dynamics
• Fast Fourier Transform features for frequency-domain movement patterns
• Lightweight framework using pose estimates from videos