2023
Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought
EMNLP 2023long main
Despite exciting recent results showing vision-language systems’ capacity to reason about images using natural language, their capacity for video reasoning remains underexplored. We motivate framing video reasoning as the sequential understanding of a small number of keyframes, thereby leveraging th…