For video question answering, feeding each frame together with question-aware captions of distant frames into an image-language model, then max-pooling per-frame answers, gives competitive open-model accuracy.
Self- chained image-language model for video localization and question answering,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
method 1polarities
extend 1representative citing papers
citing papers explorer
-
VidCtx: Context-aware Video Question Answering with Image Models
For video question answering, feeding each frame together with question-aware captions of distant frames into an image-language model, then max-pooling per-frame answers, gives competitive open-model accuracy.