Mogo generates 3D human motion from text with a single hierarchical causal transformer and residual vector quantization, reporting a HumanML3D FID of 0.079, the best among GPT-type models.
Transformer-XL: At- tentive language models beyond a fixed-length context
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mogo: RQ Hierarchical Causal Transformer for High-Quality 3D Human Motion Generation
Mogo generates 3D human motion from text with a single hierarchical causal transformer and residual vector quantization, reporting a HumanML3D FID of 0.079, the best among GPT-type models.