Metraipolis › archive › dc_4e64bd33c6fb
Kinematic Knowledge Maps for Pattern Alignment: Structured Latent Representational Learning in Multimodal Gait Analysis — arXiv:2608.20969
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20969
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:53:05.903Z
- SHA-256 of the archived text
68feb8f56aedb10a6ed341cf0c3ec230b077ce6cbd5fa5e8cae853ff3e07cde4- Stable URL of this page
https://metraipolis.com/documento/dc_4e64bd33c6fb
How to cite
Kinematic Knowledge Maps for Pattern Alignment: Structured Latent Representational Learning in Multimodal Gait Analysis — arXiv:2608.20969 — arXiv (en), https://arxiv.org/abs/2608.20969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e64bd33c6fb (Metraipolis archive dc_4e64bd33c6fb, sha256 68feb8f56aedb10a6ed341cf0c3ec230b077ce6cbd5fa5e8cae853ff3e07cde4)
BibTeX
@misc{dc4e64bd33c6fb,
title = {Kinematic Knowledge Maps for Pattern Alignment: Structured Latent Representational Learning in Multimodal Gait Analysis — arXiv:2608.20969},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20969},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e64bd33c6fb; sha256 68feb8f56aedb10a6ed341cf0c3ec230b077ce6cbd5fa5e8cae853ff3e07cde4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal clinical AI is limited by weakly aligned inputs and the absence of domain-specific interpretable representations, particularly when learning from dense video stream, structured time-series, and template-based kinematic text. Here we present ScoliDetect, an explainable framework for adolescent idiopathic scoliosis screening from monocular gait video, built around a kinematic knowledge map (KKM) and complementary template-based kinematic text derived from per-sequence pose statics. KKM is a fixed-index structured representation that encodes gait features across absolute motion, self-skeleton configuration and joint-joint signal correlation, providing anchor-referenced multimodal fusion and factor-level interpretation. We integrate video, KKM, and template-based kinematic text through bidirectional cross-attention with latent-bottleneck aggregation. In a multicenter cohort (n = 1,858 after exclusions), prespecified supervised ablations on an external screening cohort show that KKM-mediated multimodal fusion outperforms unimodal models and late concatenation. Under a staged training protocol, trimodal contrastive pretraining is applied after architecture selection as representation initialization, improving external ROC-AUC from 0.961 to 0.972. Furthermore, the structured nature of the KKM provides inherent, factor-level attributions mapped directly to specific kinematic phases and skeletal indices, offering verifiable interpretability. The results demonstrate that embedding explicit structural topologies into latent spaces significantly enhances both the generalization and explainability of multimodal pattern analysis systems. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.20969 — 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 2026-10-18T10:48:13.583Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).