Interleaving key video frames into step-by-step reasoning improves video question answering by 1.7 to 5.5 points over text-only chain-of-thought on a new self-built benchmark.
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
-
ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models
Interleaving key video frames into step-by-step reasoning improves video question answering by 1.7 to 5.5 points over text-only chain-of-thought on a new self-built benchmark.