Language-guided, recursively refined spatiotemporal object and frame graphs yield state-of-the-art video summarization scores on standard benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
Language-guided, recursively refined spatiotemporal object and frame graphs yield state-of-the-art video summarization scores on standard benchmarks.