DynFocus dynamically allocates a few tokens to selected frames and two tokens to the rest, reporting competitive video QA accuracy with lower token budgets.
Frozen in time: A joint video and image encoder for end-to- end retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding
DynFocus dynamically allocates a few tokens to selected frames and two tokens to the rest, reporting competitive video QA accuracy with lower token budgets.