← CHI 2026 map

CHI '26 · Honorable mention · full-paper review · confidence medium-high

DanXeReflect: Interacting with the Spatio-Temporal Past Movements for Embodied, Reflective Choreographic Collaboration

Hyunju Kim , Francois Guimbretiere , Bokyung Lee

DOI PDF Program page Page JSON

DanXeReflect is a credible CHI-style interaction contribution: it reframes choreographic video review as embodied XR collaboration and ties that idea to concrete interactions for search, revision, and annotation. The paper’s main strength is conceptual integration; its main weakness is that the evidence is qualitative and lab-bound, so the claims should stay scoped to reflective support rather than broader workflow impact.

Axes Lens

Rare contribution shape, typical evidence profile. The point here is not a score. It is to show what kind of claim the paper makes, and whether the evidence pattern is unusual or baseline in this 268 -review set.

Review Summary

DanXeReflect’s strongest contribution is not a new capture algorithm, but a new interaction framing for choreographic reflection. The paper argues that once rehearsal is mediated by video, annotations lose bodily grounding and subtle movement differences become harder to discuss; its response is to re-materialize past movement into interactive avatars inside XR. That is a meaningful departure from common-sense video review, because the system treats the recorded body as something dancers can re-enter, search through, revise alongside, and annotate at the level of body parts. The novelty is therefore best read as an integrated interaction technique and system architecture for reflective collaboration, rather than as a standalone technical breakthrough in motion capture. The validation, however, is intentionally bounded. The study recruited nine participants and used post-questionnaires plus semi-structured interviews to explore how users perceived the system’s support for reflective dialogue. That is appropriate for an early CHI contribution, but it means the evidence supports qualitative plausibility and design insight more than generalizable efficacy. The paper also acknowledges important limits: live-tracking coverage, avatar fidelity, segmentation alignment, and the fact that the study is lab-based rather than embedded in real rehearsal practice. So the right expert reading is that this is a well-scoped, conceptually strong embodied interaction paper with a clear creative-collaboration use case, but not one that should be overread as solving the broader production challenges of choreographic tooling.

What Changed

Canon before

Prior choreographic video review tools typically keep reflection screen-bound and detached from embodied movement, making annotations and feedback less spatially grounded.

Departure from common sense

The paper’s core move is to treat rehearsal video not as a passive record but as something that can be re-materialized into embodied XR interaction, so reflection happens through avatars and bodily reenactment rather than only through flat playback and notes.

Actual novelty

DanXeReflect combines pose-based embodied search, time-anchored embodied revision, and body-anchored multimodal annotation inside a shared virtual studio that re-materializes rehearsal video as interactive avatars. The novelty is in the integrated interaction model, not just in using motion capture or XR visualization alone.

Evidence

The paper frames a clear problem in choreographic reflection: video-based review detaches annotations from bodies and weakens spatial grounding. It then proposes DanXeReflect as an XR system that turns rehearsal video into interactive avatars and supports pose reenactment, alternative revisions, and body-part annotations. Validation is a small qualitative study with nine participants, using post-questionnaires and semi-structured interviews to understand perceived support for reflective dialogue. The evidence supports a focused interaction contribution and a bounded qualitative evaluation, but not broad performance claims.

Limits

Method limits

The evaluation is qualitative and exploratory rather than comparative or quantitative: the study recruited nine participants and relied primarily on post-questionnaires and semi-structured interviews to thematically analyze perceptions of the system’s support for reflective dialogue.

Deployment limits

The authors note constraints in live-tracking coverage, avatar fidelity, and segmentation alignment, and they explicitly frame the study as lab-based rather than integrated into actual rehearsal workflows.

Boundary conditions

The approach is most applicable when rehearsal video can be reconstructed into usable 3D avatars and when choreographic reflection benefits from embodied, asynchronous review; it is less certain for settings needing high-fidelity expressive detail or robust real-time capture.

Manual check: No manual check required for schema completeness; evidence is bounded and should be interpreted as qualitative support only.

Position in field

This sits at the intersection of embodied interaction, XR rehearsal tools, and creative collaboration support. Its contribution is a choreographic reflection system that re-centers movement as an interactive object for review, revision, and annotation rather than treating video as a static artifact.

Abstract

Choreographic reflection relies on iterative dialogue, where dancers and choreographers refine movement through embodied demonstration and shared feedback in studio rehearsal. With the shift to video, this exchange becomes constrained: annotations detach from the body, gestures lose spatial grounding, and subtle variations are difficult to capture. Advances in markerless motion capture enable 3D reconstruction from rehearsal video, allowing past recordings to be re-materialized for embodied interaction in XR. We present DanXeReflect, an XR system that transforms flat video into a virtual studio where movements appear as interactive avatars. Users can re-enact poses to search sequences, perform alternative revisions alongside originals, and attach annotations directly to body parts. A study with choreographers and dancers shows how these embodied interactions reposition spatio-temporal data as collaborative anchors, extending reflective dialogue beyond co-located rehearsal into asynchronous, distributed practice.