STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.
Temporal-attentive covariance pooling networks for video recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.