OpenResearchAlpha

ACM Transactions on Multimedia Computing, Communications, and Applications · 20 Nov 2026

Enhancing Intangible Cultural Heritage Dance Formation Choreography in VR via Large Language Models

Feng Zhouh-index 4, Junkai Rao, Ju Dai, Junjun Pan, Yong Hu, Shuo Yan, Wei Zhou, Yu-kun Lai, Paul L. Rosinh-index 41

0
Citations
no database records one yet
0
Citations in 2026
so far
41
Leading author's h-index
Paul L. Rosin, in QAI's scholar index
37
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • OpenCitations0
  • Crossref0
  • OpenAlex0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

The recent popularity of consumer-grade virtual reality devices has enabled users to experience immersive Intangible Cultural Heritage (ICH) dances in virtual environments, where ICH is defined by UNESCO as traditions or living expressions inherited from our ancestors. As in real-world choreography, the dancers in a virtual environment should be instructed in how to perform their dance. However, this can be a time-consuming and challenging task with the current Virtual Reality (VR) controllers. To address these challenges, we introduce an innovative choreography system leveraging Large Language Models (LLMs) to automate dance creation and presentation in VR. To achieve this goal, we first establish a corpus dataset comprising almost 5,000 prompt phrases to describe fundamental movements and formation changes within dance formation choreography. We then leverage an LLM to understand these prompts, thereby comprehending the commands issued by users during the interaction. Based on the understanding provided by the LLM, these prompts are converted into primitive commands that our system can execute. This allows the virtual character to perform corresponding actions to complete the dance formation choreography. We conduct three user studies with 94 subjects to validate the proposed approach. Through user studies, we find that the proposed approach can help users generate high-quality ICH dances regarding human likeness, appropriateness, and operability. For the demo, please refer to this link.

What the data shows

  • No database records a citation yet, as is usual for a paper this new.
  • Paul L. Rosin has the highest h-index among the authors (41).

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (9)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (37)

What it cites, from open citation data, with Crossref's record of each.

Sign in to see 17 more references

A free account opens the rest of the citing papers and references on every paper’s page.