A graph-based memory that tracks entity relations over time improves LLM-driven long-video question answering accuracy and frame efficiency.
Eysenck, and Michael C
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.