Train error detection and ground feedback from commodity motion capture

Establish how to train the perceptual skill of fencing error detection and how to ground reviewer feedback in the movement itself using commodity monocular video capture rather than specialized multi-sensor systems.

Background

The paper identifies a gap between movement information and the movement it describes. Beginners need guidance directing their attention to features that distinguish correct from erroneous execution, while coaches and advanced fencers need tools for attaching feedback to specific spatial and temporal features of a recorded movement.

Existing XR systems primarily support reproducing movements correctly, and closely related trainer-facing systems rely on multi-sensor volumetric capture. The paper presents FenceXR as an initial response using monocular smartphone video, but explicitly characterizes the broader questions of perceptual training and commodity-capture-based feedback grounding as unresolved.

References

The questions of how to train the perceptual skill of error detection, and how to ground reviewer feedback in the movement itself from commodity capture, remain open.

— FenceXR: AR Movement Replay for Error-Detection Training and Spatially Grounded Feedback  (2609.19505 - Nargund et al., 16 Sep 2026) in Section 1, Introduction

Whether this reasoning would transfer to correcting a learner's own lunge remains an open question for future work.

— FenceXR: AR Movement Replay for Error-Detection Training and Spatially Grounded Feedback  (2609.19505 - Nargund et al., 16 Sep 2026) in Section 7, Discussion and Design Implications, subsection “Is error detection trainable using XR systems? Did participants learn?”