MSTA, a multi-modal spatio-temporal adapter with an LLM-based consistency constraint, achieves strong base-to-novel and few-shot video recognition performance using only a small fraction of trainable parameters.
Quo vadis, action recognition? A new model and the kinetics dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Transfer Learning for Video-language Foundation Models
MSTA, a multi-modal spatio-temporal adapter with an LLM-based consistency constraint, achieves strong base-to-novel and few-shot video recognition performance using only a small fraction of trainable parameters.