MERV fuses four frozen specialized visual encoders with spatio-temporal alignment and cross-attention, improving video QA accuracy over single-encoder VideoLLMs by up to 4.6 percentage points.
We explore different training recipe strategies, starting with the standard LLaV A recipe which Video-LLaV A adopted, along with some other variations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unifying Specialized Visual Encoders for Video Language Models
MERV fuses four frozen specialized visual encoders with spatio-temporal alignment and cross-attention, improving video QA accuracy over single-encoder VideoLLMs by up to 4.6 percentage points.