Metraipolis › archive › dc_7e4328d5bf2d
Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition — arXiv:2609.02510
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02510
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T04:44:32.020Z
- SHA-256 of the archived text
75585b9125ee8bb45c122f9e7a65a2359508007e1de54d6753980357b8630b42- Stable URL of this page
https://metraipolis.com/documento/dc_7e4328d5bf2d
How to cite
Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition — arXiv:2609.02510 — arXiv (en), https://arxiv.org/abs/2609.02510 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e4328d5bf2d (Metraipolis archive dc_7e4328d5bf2d, sha256 75585b9125ee8bb45c122f9e7a65a2359508007e1de54d6753980357b8630b42)
BibTeX
@misc{dc7e4328d5bf2d,
title = {Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition — arXiv:2609.02510},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02510},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e4328d5bf2d; sha256 75585b9125ee8bb45c122f9e7a65a2359508007e1de54d6753980357b8630b42},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02510. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study body-only, 12-class acted-emotion classification from skeleton motion under leave-performer-out (LPO) evaluation, a hard, underdetermined setting: chance is 8.3%, and a protocol-matched reproduced STGCN++ baseline reaches only 25.73 +/- 4.03% Macro-F1. We show that reliable gains come not from a new architecture but from combining eleven models with orthogonal error modes: under 10-fold LPO cross-validation on the labeled training performers, an equal-weight logit-mean ensemble reaches 36.80 +/- 4.00% per-fold Macro-F1, a protocol-matched +11.07 pp (+43% relative) over the same-split reproduced baseline. Our central contribution is a tested explanation suite: for a strong ensemble member, part-masking and counterfactual edits show (rather than assert) that its decisions depend on motion-grounded body-region evidence, and this region saliency aligns with rule-based Laban Movement Analysis (LMA) attributes far more than with classical kinematics: region-level saliency-LMA Spearman rho = +0.500 versus +0.033, roughly 15x, and the alignment holds for the submitted 11-way ensemble itself at rho = +0.517; the audit is post hoc and needs no retraining. The same suite faithfully reports a negative: within-window temporal saliency is diffuse rather than localized. On the hidden challenge test set the submitted ensemble scored 37.23 % Macro-F1 and received the Best Performance Award of the MMAC Challenge 2026 (Human score is 39 %). Code is available at this https URL and the presentation at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.HC). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.02510 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T04:09:22.123Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).