Retraining VMAF on teleoperation-specific subjective ratings reduces RMSE from 10.36 to 8.83 and MAD from 8.71 to 6.38 compared to the standard model.
Zenseact open dataset: A large-scale and diverse multimodal dataset for autonomous driving,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond VMAF: Towards Application-Specific Metrics for Teleoperation Video
Retraining VMAF on teleoperation-specific subjective ratings reduces RMSE from 10.36 to 8.83 and MAD from 8.71 to 6.38 compared to the standard model.