A new regularization loss on an element-wise product of features and classifier weights improves domain-generalized human activity recognition across four benchmarks.
M.; Min, K.; Wang, H.; Piran, M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning
A new regularization loss on an element-wise product of features and classifier weights improves domain-generalized human activity recognition across four benchmarks.