HumanML3D is a 3D human motion-language dataset that originates from a combination of HumanAct12 and Amass dataset. It covers a broad range of human actions such as daily activities (e.g., 'walking', 'jumping'), sports (e.g., 'swimming', 'playing golf'), acrobatics (e.g., 'cartwheel') and artistry (e.g., 'dancing'). Overall, HumanML3D dataset consists of 14,616 motions and 44,970 descriptions composed by 5,371 distinct words. The total length of motions amounts to 28.59 hours. The average motion length is 7.1 seconds, while average description length is 12 words.
GitHub - LinghaoChan/UniMoCap: [Open-source Project] UniMoCap: community implementation to unify the text-motion datasets (HumanML3D, KIT-ML, and BABEL) and whole-body motion dataset (Motion-X).
3D Body Keypoint Datasets — MMPose 1.3.1 documentation
GitHub - EricGuo5513/HumanML3D: HumanML3D: A large and diverse 3d human motion-language dataset.
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
POSTS
Congyi Wang - CatalyzeX
arxiv-sanity
arxiv-sanity
Creating Authentic Human Motion Synthesis via Diffusion - Metaphysic.ai
PDF] MotionGPT: Human Motion as a Foreign Language
MoMask: Generative Masked Modeling of 3D Human Motions – arXiv Vanity
Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition
NeurIPS 2023
Generate Movement from Text Descriptions with T2M-GPT - Voxel51
Electronics, Free Full-Text