A two-stage framework improves viewpoint-invariant and temporally consistent action detection in untrimmed videos by using virtual viewpoint augmentation at training time and a selective state-space temporal encoder, outperforming prior methods on PKU-MMD and BABEL.
Online human action detec- tion using joint classification-regression recurrent neural net- works,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Viewpoint-Invariance and Temporal Consistency for Action Detection
A two-stage framework improves viewpoint-invariant and temporally consistent action detection in untrimmed videos by using virtual viewpoint augmentation at training time and a selective state-space temporal encoder, outperforming prior methods on PKU-MMD and BABEL.