# Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprinting

arXiv: https://arxiv.org/abs/2604.00927 · HTML: https://mlsanity.com/paper/2604.00927/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://mlsanity.com/paper/1712.03453/) (2017)
- [A Spatio-temporal Transformer for 3D Human Motion Prediction](https://mlsanity.com/paper/2004.08692/) (2020)
- [HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2008.00206/) (2020)
- [Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images](https://mlsanity.com/paper/2109.05885/) (2021)
- [Music-Driven Group Choreography](https://mlsanity.com/paper/2303.12337/) (2023)
- [BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos](https://mlsanity.com/paper/2501.07800/) (2025)
- [PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation](https://mlsanity.com/paper/2010.05302/) (2020)
- [Dance Any Beat: Blending Beats with Visuals in Dance Video Generation](https://mlsanity.com/paper/2405.09266/) (2024)
- [Audio-based Musical Version Identification: Elements and Challenges](https://mlsanity.com/paper/2109.02472/) (2021)
- [Dual networks based 3D Multi-Person Pose Estimation from Monocular Video](https://mlsanity.com/paper/2205.00748/) (2022)
- [CoMotion: Concurrent Multi-person 3D Motion](https://mlsanity.com/paper/2504.12186/) (2025)
- [BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval](https://mlsanity.com/paper/2310.10300/) (2023)
- [Let's Dance: Learning From Online Dance Videos](https://mlsanity.com/paper/1801.07388/) (2018)
- [EnchantDance: Unveiling the Potential of Music-Driven Dance Movement](https://mlsanity.com/paper/2312.15946/) (2023)
- [Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation](https://mlsanity.com/paper/2508.04513/) (2025)
- [Will You Ever Become Popular? Learning to Predict Virality of Dance Clips](https://mlsanity.com/paper/2111.03819/) (2021)
- [Digital Fingerprinting on Multimedia: A Survey](https://mlsanity.com/paper/2408.14155/) (2024)
- [Just Another Hour on TikTok: ID sampling to obtain a complete slice of TikTok](https://mlsanity.com/paper/2504.13279/) (2025)
- [SpectroMap: Peak detection algorithm for audio fingerprinting](https://mlsanity.com/paper/2211.00982/) (2022)
- [Music Genre Classification: Training an AI model](https://mlsanity.com/paper/2405.15096/) (2024)
- [Automatic Dance Video Segmentation for Understanding Choreography](https://mlsanity.com/paper/2405.19727/) (2024)
- [Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution](https://mlsanity.com/paper/2407.21525/) (2024)
- [Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks](https://mlsanity.com/paper/2504.03052/) (2025)
- [MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation](https://mlsanity.com/paper/2506.02661/) (2025)

## Abstract (arXiv)

We present DANCEMATCH, an end-to-end framework for motion-based dance retrieval, the task of identifying semantically similar choreographies directly from raw video, defined as DANCE FINGERPRINTING. While existing motion analysis and retrieval methods can compare pose sequences, they rely on continuous embeddings that are difficult to index, interpret, or scale. In contrast, DANCEMATCH constructs compact, discrete motion signatures that capture the spatio-temporal structure of dance while enabling efficient large-scale retrieval. Our system integrates Skeleton Motion Quantisation (SMQ) with Spatio-Temporal Transformers (STT) to encode human poses, extracted via Apple CoMotion, into a structured motion vocabulary. We further design DANCE RETRIEVAL ENGINE (DRE), which performs sub-linear retrieval using a histogram-based index followed by re-ranking for refined matching. To facilitate reproducible research, we release DANCETYPESBENCHMARK, a pose-aligned dataset annotated with quantised motion tokens. Experiments demonstrate robust retrieval across diverse dance styles and strong generalisation to unseen choreographies, establishing a foundation for scalable motion fingerprinting and quantitative choreographic analysis.