FEAT combines spatial, temporal, and channel attention in a diffusion transformer and reports improved medical video generation metrics with lower parameter counts than Endora.
In: Proceedings of the IEEE/CVF International conference on com- puter vision
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
-
FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation
FEAT combines spatial, temporal, and channel attention in a diffusion transformer and reports improved medical video generation metrics with lower parameter counts than Endora.