Metraipolis › archive › dc_ef3eec26f870
VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation — arXiv:2608.05782
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05782
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:36:15.066Z
- SHA-256 of the archived text
c9316676f9f2e6a91bea3892afa327b21bc25c9471575e33930dbd7f94ba06d3- Stable URL of this page
https://metraipolis.com/documento/dc_ef3eec26f870
How to cite
VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation — arXiv:2608.05782 — arXiv (en), https://arxiv.org/abs/2608.05782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef3eec26f870 (Metraipolis archive dc_ef3eec26f870, sha256 c9316676f9f2e6a91bea3892afa327b21bc25c9471575e33930dbd7f94ba06d3)
BibTeX
@misc{dcef3eec26f870,
title = {VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation — arXiv:2608.05782},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05782},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef3eec26f870; sha256 c9316676f9f2e6a91bea3892afa327b21bc25c9471575e33930dbd7f94ba06d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Wearable human activity recognition (HAR) is often limited by the scarcity of labeled sensor data, especially in low-resource, class-imbalanced, and subject-generalization settings. Synthetic IMU generation can reduce this dependency and enhance HAR machine learning model's performance, but existing approaches face a trade-off without addressing all factors: video-driven methods are visually grounded but sensitive to pose-estimation errors, while text-driven methods are controllable but often weakly grounded in how activities are actually performed. We present VSMP-IMU, a video-grounded framework for controllable synthetic IMU generation based on a structured Semantic Motion Program (SMP), which separates activity-defining semantics from label-preserving variation. Given an input video, VSMP-IMU extracts and augments an SMP, uses it to synthesize motion, converts the motion into virtual IMU signals, and grounds the resulting signals to the target wearable domain. We evaluate VSMP-IMU against state-of-the-art synthetic data generation methods on five public IMU-HAR datasets under leave-one-person-out evaluation. VSMP-IMU achieves an average Macro-F1 of 78.33%, improving over real-only training by 9.77% and over the strongest prior synthetic baseline by 4.04%. In low-resource settings with reduced training data-samples, it improves over real-only training by 18.54% and over the strongest prior synthetic baselines by more than 6% on average. Under long-tail evaluation in imbalanced datasets, it improves tail-class Macro-F1 by 19.86% over Real-only training and by 4.76% over SOTA. These results show that structured video-grounded semantics provide a practical foundation for controllable, wearable-relevant synthetic sensor data generation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.05782 — 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 2026-10-31T10:23:31.016Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).