BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//BritCHI//Schedule//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Craft Knowledge and Embodied Labelling in ML-Assisted Motion C
 apture
BEGIN:VEVENT
UID:paper-session-1-ai-expertise-and-changing-practice-craft-knowledge-and-
 embodied-labelling-in-ml@britchi.uk
DTSTAMP:20261014T154232Z
DTSTART:20261102T111000Z
DTEND:20261102T112000Z
SUMMARY:Craft Knowledge and Embodied Labelling in ML-Assisted Motion Captur
 e
DESCRIPTION:BritCHI 2026 · Paper Session 1: AI\, Expertise and Changing Pr
 actice\nKoterwas\, Morrow\, Braghetto\, Vaughan\nThe StyleCap project deve
 loped a Machine Learning (ML) model for styling full body animation from s
 parse motion capture and text. The development contributes an approach to 
 Artificial Intelligence (AI) in HCI research prioritising subjective exper
 tise and embodied knowledge. Interviews with animators documented their va
 lues\, expertise and use of language in animation. The interviews included
  a live motion capture session and were coded to produce a database of wor
 ds describing style. Inverting the traditional process of using language t
 o label data\, data was created by expressing language through bodily move
 ment. An ML model was trained on this dataset to produce stylised animatio
 ns which were evaluated by professional animators. These evaluations were 
 then used to measure the effectiveness of GPT 4.1 as a translator of the e
 valuators’ language to the specific labels utilised in training. The acc
 uracy of these translations of the craft knowledge and vocabulary used by 
 individual practitioners and enacted through embodied performance demonstr
 ates the potential of human-centred approaches to HCI research with AI.
LOCATION:Brunel University London\, Kingston Lane\, Uxbridge UB8 3PH
URL:https://www.britchi.uk/programme/schedule/paper-session-1-ai-expertise-
 and-changing-practice/
END:VEVENT
END:VCALENDAR