T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations

doi:doi:10.57702/zz8w5z3w

T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations

Generating motion from textual descriptions can be used in numerous applications in the game industry, ﬁlm-making, and animating robots. For example, a typical way to access new motion in the game industry is to perform motion capture, which is expensive. Therefore automatically generating motion from textual descriptions, which allows producing meaningful motion data, could save time and be more economical.

BibTex:

@dataset{Jianrong_Zhang_and_Yangsong_Zhang_and_Xiaodong_Cun_and_Shaoli_Huang_and_Hongwei_Zhao_and_Hongtao_Lu_and_Xi_Shen_2024,
    abstract = {Generating motion from textual descriptions can be used in numerous applications in the game industry, ﬁlm-making, and animating robots. For example, a typical way to access new motion in the game industry is to perform motion capture, which is expensive. Therefore automatically generating motion from textual descriptions, which allows producing meaningful motion data, could save time and be more economical.},
    author = {Jianrong Zhang and Yangsong Zhang and Xiaodong Cun and Shaoli Huang and Hongwei Zhao and Hongtao Lu and Xi Shen},
    doi = {10.57702/zz8w5z3w},
    institution = {No Organization},
    keyword = {'discrete representations', 'human motion', 'textual descriptions'},
    month = {dec},
    publisher = {TIB},
    title = {T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations},
    url = {https://service.tib.eu/ldmservice/dataset/t2m-gpt--generating-human-motion-from-textual-descriptions-with-discrete-representations},
    year = {2024}
}