Dyadic Mamba uses a state-space backbone and simple concatenation to generate text-conditioned two-person motion that extends beyond training length, with a per-person NDMS long-term benchmark.
Tm2d: Bimodality driven 3d dance generation via music- text integration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dyadic Mamba: Long-term Dyadic Human Motion Synthesis
Dyadic Mamba uses a state-space backbone and simple concatenation to generate text-conditioned two-person motion that extends beyond training length, with a per-person NDMS long-term benchmark.