Introduces cross-axis feature fusion transformers and a joint-wise Soft-DTW regression auxiliary task for text-based 3D human motion editing, reporting state-of-the-art results on the MotionFix dataset.
Shape conditioned human motion generation with diffusion model.arXiv preprint arXiv:2405.06778, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
Introduces cross-axis feature fusion transformers and a joint-wise Soft-DTW regression auxiliary task for text-based 3D human motion editing, reporting state-of-the-art results on the MotionFix dataset.