Training video LLMs on ordered static images with temporal questions nearly matches real video training on TVBench, suggesting video data is underused.
ShareGPT4Video: Improving Video Under- standing and Generation with Better Captions
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
How Important are Videos for Training Video LLMs?
Training video LLMs on ordered static images with temporal questions nearly matches real video training on TVBench, suggesting video data is underused.