A graph-based memory that tracks entity relations over time improves LLM-driven long-video question answering accuracy and frame efficiency.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding Long Videos via LLM-Powered Entity Relation Graphs
A graph-based memory that tracks entity relations over time improves LLM-driven long-video question answering accuracy and frame efficiency.