Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models.
Lin LiJun XiaoGuikun ChenJian ShaoYueting ZhuangLong ChenPublished in: CoRR (2023)
Keyphrases
- visual cues
- language model
- visual information
- low level
- language modeling
- probabilistic model
- n gram
- document retrieval
- speech recognition
- query expansion
- mid level
- vector space model
- visual features
- statistical language models
- language modelling
- retrieval model
- information retrieval
- test collection
- document ranking
- context sensitive
- object detection
- smoothing methods
- multimedia
- metadata
- translation model
- language models for information retrieval
- pseudo relevance feedback
- key frames
- keywords
- feature extraction
- high level
- computer vision