A Text-Image Pair Is Not Enough: Language-Vision Relation Inference with Auxiliary Modality Translation.
Wenjie LuDong ZhangShoushan LiGuodong ZhouPublished in: NLPCC (2) (2023)
Keyphrases
- image pairs
- machine translation system
- language generation
- target language
- stereo images
- source language
- english text
- image matching
- image registration
- epipolar geometry
- single image
- computational linguistics
- machine translation
- fundamental matrix
- multi modal
- vision system
- computer vision
- real time
- disparity map
- cross language information retrieval
- natural language
- medical images
- dense correspondences
- query translation
- statistical machine translation
- image processing
- character n grams
- epipolar constraint
- disparity estimation
- bayesian networks
- machine learning