A driving VQA model prunes image tokens using the text query and enhances the survivors with cross-frame attention, reporting 168x token reduction and gains over its baseline.
Is space-time attention all you need for video under- standing? In Proceedings of the International Confer- ence on Machine Learning (ICML) , 2021
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
-
LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement
A driving VQA model prunes image tokens using the text query and enhances the survivors with cross-frame attention, reporting 168x token reduction and gains over its baseline.