# Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition

arXiv: https://arxiv.org/abs/2012.13823 · HTML: https://mlsanity.com/paper/2012.13823/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2020.

## Built on by (most cited first, 23 of 23)

- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2105.01563/) (2021)
- [Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition](https://mlsanity.com/paper/2210.16820/) (2022)
- [Uncertainty-DTW for Time Series and Sequences](https://mlsanity.com/paper/2211.00005/) (2022)
- [Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions](https://mlsanity.com/paper/2202.11423/) (2022)
- [One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching](https://mlsanity.com/paper/2307.07286/) (2023)
- [CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner](https://mlsanity.com/paper/2403.10082/) (2024)
- [A Comprehensive Review of Few-shot Action Recognition](https://mlsanity.com/paper/2407.14744/) (2024)
- [3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na"ive](https://mlsanity.com/paper/2112.12668/) (2021)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2209.10073/) (2022)
- [Instance-level Few-shot Learning with Class Hierarchy Mining](https://mlsanity.com/paper/2304.07459/) (2023)
- [MoFM: A Large-Scale Human Motion Foundation Model](https://mlsanity.com/paper/2502.05432/) (2025)
- [Enhancing Brazilian Sign Language Recognition through Skeleton Image Representation](https://mlsanity.com/paper/2404.19148/) (2024)
- [SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation](https://mlsanity.com/paper/2504.11749/) (2025)
- [Recovering Complete Actions for Cross-dataset Skeleton Action Recognition](https://mlsanity.com/paper/2410.23641/) (2024)
- [Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.09150/) (2022)
- [Easing Automatic Neurorehabilitation via Classification and Smoothness Analysis](https://mlsanity.com/paper/2212.14797/) (2022)
- [Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Data](https://mlsanity.com/paper/2309.15635/) (2023)
- [Proper Body Landmark Subset Enables More Accurate and 5X Faster Recognition of Isolated Signs in LIBRAS](https://mlsanity.com/paper/2510.24887/) (2025)
- [Skarimva: Skeleton-based Action Recognition is a Multi-view Application](https://mlsanity.com/paper/2602.23231/) (2026)
- [SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition](https://mlsanity.com/paper/2606.03610/) (2026)
- [Fine-grained Human Motion Understanding with Language Models](https://mlsanity.com/paper/2606.20888/) (2026)

## Abstract (arXiv)

One-shot action recognition allows the recognition of human-performed actions with only a single training example. This can influence human-robot-interaction positively by enabling the robot to react to previously unseen behaviour. We formulate the one-shot action recognition problem as a deep metric learning problem and propose a novel image-based skeleton representation that performs well in a metric learning setting. Therefore, we train a model that projects the image representations into an embedding space. In embedding space the similar actions have a low euclidean distance while dissimilar actions have a higher distance. The one-shot action recognition problem becomes a nearest-neighbor search in a set of activity reference samples. We evaluate the performance of our proposed representation against a variety of other skeleton-based image representations. In addition, we present an ablation study that shows the influence of different embedding vector sizes, losses and augmentation. Our approach lifts the state-of-the-art by 3.3% for the one-shot action recognition protocol on the NTU RGB+D 120 dataset under a comparable training setup. With additional augmentation our result improved over 7.7%.