Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning.
Zhuolin YangWei PingZihan LiuVijay KorthikantiWeili NieDe-An HuangLinxi FanZhiding YuShiyi LanBo LiMing-Yu LiuYuke ZhuMohammad ShoeybiBryan CatanzaroChaowei XiaoAnima AnandkumarPublished in: CoRR (2023)
Keyphrases
- language model
- retrieval model
- document retrieval
- image retrieval
- language modeling
- query expansion
- low level
- visual features
- information retrieval
- ad hoc information retrieval
- test collection
- statistical language models
- image classification
- query terms
- language models for information retrieval
- probabilistic model
- n gram
- smoothing methods
- speech recognition
- cross language retrieval
- image collections
- mixture model
- document ranking
- image content
- image features
- context sensitive
- query specific
- retrieval process
- image representation
- visual information
- news video
- relevance model
- language modelling
- image segmentation
- vector space model
- low level features
- bayesian framework