Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models.
Jize CaoZhe GanYu ChengLicheng YuYen-Chun ChenJingjing LiuPublished in: ECCV (6) (2020)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- probabilistic model
- statistical language models
- computer vision
- speech recognition
- training data
- information retrieval
- language modelling
- query expansion
- image sequences
- retrieval model
- training examples
- video sequences
- smoothing methods
- single image
- vision system
- real scenes
- input image
- appearance variations
- control signals
- neural network
- text mining
- relevance model
- feature selection