DIR improves out-of-domain image captioning by guiding image features with a frozen diffusion model and retrieving text decomposed into objects, actions, and environments.
nocaps: novel object caption- ing at scale
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
-
DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding
DIR improves out-of-domain image captioning by guiding image features with a frozen diffusion model and retrieving text decomposed into objects, actions, and environments.