Video dataset of Balinese dance basic movement for action recognition

Abstract

In the convergence of cultural heritage preservation and computational research, this paper presents a comprehensive dataset capturing the nuanced artistry of traditional Balinese dancing. This endeavour not only documents but also aims to protect these intricate dance movements, bridging technological advancements with rich cultural traditions. The dataset includes 1740 and 828 high-definition video recordings of female and male dancers, respectively, showcasing 24 unique dance movements. These recordings, made using multiple smartphone cameras from various perspectives, reflect the dance's complex nature and emphasize gender-based movement variations, key for detailed cultural analysis. Our systematic approach involved three strategically placed cameras, capturing diverse angles for a holistic view. The subsequent preprocessing stage, including segmenting and labelling, has enhanced the dataset's clarity, making it a valuable resource for cultural studies and computational analysis in preserving intangible cultural heritage. The videos, stored in MP4 format, are categorized by dancer gender, dance type, and camera angle, offering researchers a rich, multifaceted tool for exploring this traditional art form.

Keywords

• Video dataset
• Balinese dance
• Action recognition