CM3T shows that multi-head vision adapters plus cross-attention adapters can adapt frozen supervised-pretrained video transformers with a fraction of the trainable parameters of full fine-tuning.
Multimodal vision transformers with forced attention for behavior analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets
CM3T shows that multi-head vision adapters plus cross-attention adapters can adapt frozen supervised-pretrained video transformers with a fraction of the trainable parameters of full fine-tuning.