Most open-source Video-LLMs are near chance-level at verifying their own temporal predictions, and a proposed event-temporal verification tuning improves both grounding and consistency.
Instructblip: Towards general-purpose vision- language models with instruction tuning, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Consistency of Video Large Language Models in Temporal Comprehension
Most open-source Video-LLMs are near chance-level at verifying their own temporal predictions, and a proposed event-temporal verification tuning improves both grounding and consistency.