EUVIMEDEUVIMED entdecken
Crossref

MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators

Yaqi Zhang, Di Huang, Bin Liu, Shixiang Tang, Yan Lu, Lu Chen, Lei Bai, Qi Chu, Nenghai Yu, Wanli Ouyang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7368-7376

DOI: 10.1609/aaai.v38i7.28567 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yaqi Zhang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 87-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only a single modality of the control signal, which limits their application in the real digital human industry. This paper presents a Motion General-Purpose generaTor (MotionGPT) that can use multimodal control signals, e.g., text and single-frame poses, for generating consecutive human motions by treating multimodal signals as special input tokens in large language models (LLMs). Specifically, we first quantize multimodal control signals into discrete codes and then formulate them in a unified prompt instruction to ask the LLMs to generate the motion answer. Our MotionGPT demonstrates a unified human motion generation model with multimodal control signals by tuning a mere 0.4% of LLM parameters. To the best of our knowledge, MotionGPT is the first method to generate human motion by multimodal control signals, which we hope can shed light on this new direction. Visit our webpage at https://qiqiapink.github.io/MotionGPT/.

Zitieren

APA

Zhang, Y., Huang, D., Liu, B., Tang, S., Lu, Y., Chen, L., Bai, L., Chu, Q., Yu, N., & Ouyang, W. (2024). MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7368-7376. https://doi.org/10.1609/aaai.v38i7.28567

Vancouver

Zhang Y, Huang D, Liu B, Tang S, Lu Y, Chen L, et al. MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7368-7376. doi:10.1609/aaai.v38i7.28567

BibTeX
@article{Zhang2024,
  author = {Zhang, Yaqi and Huang, Di and Liu, Bin and Tang, Shixiang and Lu, Yan and Chen, Lu and Bai, Lei and Chu, Qi and Yu, Nenghai and Ouyang, Wanli},
  title = {MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {7},
  pages = {7368--7376},
  doi = {10.1609/aaai.v38i7.28567}
}
Kostenlos starten →