EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TransMotion: Text-Guided Transformation Learning for Composed Human Motion Retrieval

Gyojin Han, Jongsuk Kim, Junmo Kim

Applied Sciences · 02.11.2026 · 16 (21) · 10842

DOI: 10.3390/app162110842 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.11.2026. Verfasst von Gyojin Han und 2 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Defense Acquisition Program Administration, Korea government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-to-motion retrieval systems enable users to find 3D human motion using natural-language descriptions. However, conveying highly specific intent with a single text query is often difficult, and users may wish to find a motion that preserves the core semantics of an existing motion while reflecting specific modifications. To address these scenarios, we introduce Composed Human Motion Retrieval (CHMR), a new task that aims to retrieve a target motion from a database using a composed query that combines a reference motion with a textual modification instruction. We propose TransMotion, a framework designed for the CHMR task. TransMotion supervises the motion representation through two complementary objectives, yielding invariant and adaptive components. The invariant component preserves the core semantic identity between the reference and target motions, while the adaptive component models the dynamic transformation specified by the text instruction. Through extensive experiments, we determine that a contrastive learning objective paired with a cross-attention-based transformation predictor yields the most effective configuration, which we attribute to the attention mechanism’s capacity to model complex text–motion relationships. We validate our approach on two independently constructed datasets, MotionFix and STANCE, demonstrating superior performance over native composed-retrieval baselines and strong baselines adapted from motion editing and standard retrieval domains.

Förderung

  • Defense Acquisition Program Administration
  • Korea government

Zitieren

APA

Han, G., Kim, J., & Kim, J. (2026). TransMotion: Text-Guided Transformation Learning for Composed Human Motion Retrieval. Applied Sciences, 16(21), 10842. https://doi.org/10.3390/app162110842

Vancouver

Han G, Kim J, Kim J. TransMotion: Text-Guided Transformation Learning for Composed Human Motion Retrieval. Applied Sciences. 2026;16(21):10842. doi:10.3390/app162110842

BibTeX
@article{Han2026,
  author = {Han, Gyojin and Kim, Jongsuk and Kim, Junmo},
  title = {TransMotion: Text-Guided Transformation Learning for Composed Human Motion Retrieval},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {21},
  pages = {10842},
  doi = {10.3390/app162110842}
}
Kostenlos starten →