# One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learning

arXiv: https://arxiv.org/abs/2609.07078 · HTML: https://mlsanity.com/paper/2609.07078/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 66 of its 83 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 30 of 66)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN](https://mlsanity.com/paper/1803.04831/) (2018)
- [Cross-view Action Modeling, Learning and Recognition](https://mlsanity.com/paper/1405.2941/) (2014)
- [Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation](https://mlsanity.com/paper/1804.06055/) (2018)
- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1703.08274/) (2017)
- [PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding](https://mlsanity.com/paper/1703.07475/) (2017)

## Abstract (arXiv)

For learning generalizable motion representations from large-scale unlabeled data, Self-supervised learning (SSL) has become a widely adopted methodology. However, existing approaches are primarily limited by the inherent heterogeneity of skeleton data---characterized by varying joint counts, indexing protocols, and topological structures across different sensors---which typically necessitates training separate, sensor-specific, or even entirely dataset-specific models. To overcome this, we introduce SOfA (Skeleton One for All), the first generalist foundation model designed to achieve sensor-unified skeleton representation learning across diverse sensors. To accommodate the dimensional gap caused by varying joint counts, we introduce a fixed-size set of learnable Canonical Joint Slots, acting as a universal vessel that seamlessly accommodates arbitrary skeletal topologies. SOfA fills these slots via an attention mechanism that dynamically aggregates skeletal information from sensor-specific inputs. Furthermore, we resolve joint index misalignment between various sensors by introducing a Semantic Joint Embedding derived from a pre-trained text encoder, rather than relying on absolute positional embeddings. To validate our approach, we standardized ten 3D skeleton datasets for unified training. Extensive experiments demonstrate that SOfA can serve as a truly universal encoder, achieving state-of-the-art (SOTA) performance across a wide range of downstream tasks and sensor types, often outperforming dataset-specific specialist models with a single foundation model.