LITE, a lightweight MLP trained to mimic a gradient-based oracle, improves the GFLOPs/accuracy trade-off over random selection and prior efficient video transformers.
Space-time mixing attention for video transformer
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
-
Principles of Visual Tokens for Efficient Video Understanding
LITE, a lightweight MLP trained to mimic a gradient-based oracle, improves the GFLOPs/accuracy trade-off over random selection and prior efficient video transformers.