Boosting Audio-visual Zero-shot Learning with Large Language Models.
Haoxing ChenYaohui LiYan HongZizheng HuangZhuoer XuZhangxuan GuJun LanHuijia ZhuWeiqiang WangPublished in: CoRR (2023)
Keyphrases
- audio visual
- language model
- multi modal
- language modeling
- probabilistic model
- document retrieval
- n gram
- passage retrieval
- visual information
- information retrieval
- speech recognition
- test collection
- visual data
- retrieval model
- query expansion
- multimedia
- multi stream
- feature selection
- smoothing methods
- machine learning
- pseudo relevance feedback
- relevance model
- feature space
- metadata