T-MASK uses temporal token masking to improve cross-view driver activity recognition with foundation models, claiming gains of +1.23% over probing and +8.0% over PEFT on Drive&Act.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
T-MASK: Temporal Masking for Probing Foundation Models across Camera Views in Driver Monitoring
T-MASK uses temporal token masking to improve cross-view driver activity recognition with foundation models, claiming gains of +1.23% over probing and +8.0% over PEFT on Drive&Act.