Hier-EgoPack learns reusable task prototypes from support tasks and uses them to improve novel task learning across egocentric video benchmarks.
Static and dynamic concepts for self-supervised video representation learning
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
-
Learning reusable concepts across different egocentric video understanding tasks
Hier-EgoPack learns reusable task prototypes from support tasks and uses them to improve novel task learning across egocentric video benchmarks.