MotionHiFlow generates text-aligned 3D human motions using hierarchical flow matching across temporal scales, cross-scale transitions, a Text-Motion Diffusion Transformer, and a topology-aware Motion VAE, achieving state-of-the-art results on HumanML3D and KIT-ML.
Motiongpt: Human motion as a foreign language
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
HOI-PAGE creates realistic 4D human-object interactions from text by using LLM-derived part affordance graphs to guide object decomposition, reference video extraction, and constraint-based motion optimization in zero-shot fashion.
citing papers explorer
-
MotionHiFlow: Text-to-motion via hierarchical flow matching
MotionHiFlow generates text-aligned 3D human motions using hierarchical flow matching across temporal scales, cross-scale transitions, a Text-Motion Diffusion Transformer, and a topology-aware Motion VAE, achieving state-of-the-art results on HumanML3D and KIT-ML.
-
HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
HOI-PAGE creates realistic 4D human-object interactions from text by using LLM-derived part affordance graphs to guide object decomposition, reference video extraction, and constraint-based motion optimization in zero-shot fashion.