Metraipolis › archive › dc_8da29eed7809

One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learning — arXiv:2609.07078

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07078
License (as archived)
CC0-1.0
Archived
2026-10-16T15:11:37.402Z
SHA-256 of the archived text
5f96e699064a4e1a403730908ff9e408b95b917432b785322e5dc901ea11d29f
Stable URL of this page
https://metraipolis.com/documento/dc_8da29eed7809

How to cite

One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learning — arXiv:2609.07078 — arXiv (en), https://arxiv.org/abs/2609.07078 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8da29eed7809 (Metraipolis archive dc_8da29eed7809, sha256 5f96e699064a4e1a403730908ff9e408b95b917432b785322e5dc901ea11d29f)
BibTeX
@misc{dc8da29eed7809,
  title = {One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learning — arXiv:2609.07078},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07078},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8da29eed7809; sha256 5f96e699064a4e1a403730908ff9e408b95b917432b785322e5dc901ea11d29f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07078. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.07078 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T14:49:57.178Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).