Layer 4 – Expressive Qualities

The highest layer focuses on how an observer perceives movement, connecting computational features with human-centered interpretation.
It addresses nonverbal communication, emotions, and intentions conveyed through movement, supporting cross-modal experiences (e.g., “listening to a choreography”) and enabling applications in art, therapy, rehabilitation, and HCI

Key Concepts

  • Observer perspective: perception, not physical effort, defines qualities.
  • Memory and context: recent history influences interpretation (e.g., expectancy, contrast, saliency).
  • Machine learning: used to map mid-level trajectories to expressive qualities.

Examples of Expressive Qualities

Quality Description Implemented
Predictability / Expectancy Extent to which movement can be anticipated by an observer. :material-close:
Hesitation When intention behind movement is unclear to an observer. :material-close:
Attraction / Repulsion Degree to which an observer feels drawn to or repelled by the movement. :material-close:
Groove Extent to which movement elicits movement in the observer. :material-close:
Saliency1 How a movement stands out compared to others in context. :material-close:
Emotion Expressive emotional content conveyed via body movement (categorical or dimensional). :material-close:

References

  1. Romano, G., Rajeev Sabharwal, S., Gnecco, G., Camurri, A. (2025). A Computational Framework for Identifying Salient Moments in Motion Capture Data. In: Nicosia, G., Ojha, V., Giesselbach, S., Pardalos, M.P., Umeton, R. (eds) Machine Learning, Optimization, and Data Science. LOD ACAIN 2024 2024. Lecture Notes in Computer Science, vol 15509. Springer, Cham. :material-link-variant: ↩