DiMP uses diffusion to infer clean masked positions from visible context and to model full distributions of point displacements rather than means, delivering 11.21% and 13.65% absolute gains on offline and online action segmentation.
Droppos: Pre-training vision transformers by reconstructing dropped positions.Advances in Neural Information Processing Systems (NeurIPS)
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Diffusion Masked Pretraining for Dynamic Point Cloud
DiMP uses diffusion to infer clean masked positions from visible context and to model full distributions of point displacements rather than means, delivering 11.21% and 13.65% absolute gains on offline and online action segmentation.