LaMoFCBench is a new benchmark covering 4 categories and 16 scenarios that exposes misalignment between mainstream feature codecs and the heterogeneous statistics of large-model activations.
Stereo image coding for machines with joint visual feature compression,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Large Model Feature Coding
LaMoFCBench is a new benchmark covering 4 categories and 16 scenarios that exposes misalignment between mainstream feature codecs and the heterogeneous statistics of large-model activations.