Deep Learning
Movement Signatures
Compact movement signatures for off-ball behavior — built to compare roles, styles, and tendencies across leagues and seasons.
Where this shows upPersonal PerformanceTeam Intelligence
What it is
A movement signature is a compact numerical description of how a body moves — not where it went, but how it got there. The foundation model compresses each four-second window of skeleton motion into a 384-dimensional embedding that keeps what matters: action type, speed, coordination, asymmetry, movement quality.
Two windows land near each other in this space when the movement is similar — regardless of camera angle, pitch position, body size, or which tracking system produced the data. That invariance is what makes signatures comparable across players, sessions, and data sources.
How it works
Signatures are learned self-supervised: the model learns directly from raw skeleton motion, across millions of frames — it never sees a hand-labeled event. Anatomical constraints keep the space honest: bone lengths stay consistent, velocities stay smooth. How the model trains — and how the corpus grows — is documented.
What you get
Independent checks — concept probes — confirm the space is readable: speed, torso lean, and knee asymmetry can each be read back from the signature alone. Results, protocols, and caveats live in the evaluation docs. In the product, signatures are the unit of comparison everything else builds on.
| Parameter | Value | Notes |
|---|---|---|
| Invariant to | camera, mirroring, body size | By training design — verified with invariance probes. |
| Sensitive to | action, speed, asymmetry, quality | The signal that signatures are built to carry. |
Status & roadmap
Prototype. Signatures are trained and probed at proof-of-concept scale — on a deliberately small corpus of real movement. Comparing roles and styles across leagues and seasons is the design goal the data roadmap works toward, not a shipped claim.