Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model.
Zipeng XuTianwei LinHao TangFu LiDongliang HeNicu SebeRadu TimofteLuc Van GoolErrui DingPublished in: CVPR (2022)
Keyphrases
- language model
- image manipulation
- pre trained
- information retrieval
- language modeling
- image editing
- speech recognition
- probabilistic model
- n gram
- training data
- query expansion
- text mining
- training examples
- image composition
- mixture model
- computer vision
- image processing
- control signals
- multi view
- single image
- information extraction
- knn
- training set
- multimedia