Sampling RGB at 10Hz and 3D hand pose at 30Hz preserves egocentric action recognition accuracy while reducing CPU usage by roughly 3x compared with all-30Hz input.
Avatars grow legs: Generating smooth human motion from sparse tracking in- puts with diffusion model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Efficient Egocentric Action Recognition with Multimodal Data
Sampling RGB at 10Hz and 3D hand pose at 30Hz preserves egocentric action recognition accuracy while reducing CPU usage by roughly 3x compared with all-30Hz input.