Three lightweight VVC profiles for feature coding achieve up to 2.96% BD-Rate gain and 95.6% encoding speedup while preserving downstream task accuracy under the MPEG-AI FCM framework.
Common test and train- ing conditions for FCM,
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
-
New VVC profiles targeting Feature Coding for Machines
Three lightweight VVC profiles for feature coding achieve up to 2.96% BD-Rate gain and 95.6% encoding speedup while preserving downstream task accuracy under the MPEG-AI FCM framework.