A Visual Attention Grounding Neural Model for Multimodal Machine Translation.
Mingyang ZhouRunxiang ChengYong Jae LeeZhou YuPublished in: CoRR (2018)
Keyphrases
- visual attention
- machine translation
- neural model
- neural network
- saliency map
- eye tracking
- eye movements
- cross lingual
- recurrent neural networks
- information extraction
- control scheme
- vision system
- natural language processing
- visual perception
- language independent
- multi modal
- natural language
- higher level
- target language
- machine translation system
- word alignment
- cross language information retrieval
- multi layer perceptron
- object based visual attention
- statistical machine translation
- audio visual
- closed loop
- artificial neural networks
- multimedia
- data mining
- real time
- artificial intelligence
- image retrieval
- source language