A text-based visual context modulation neural model for multimodal machine translation.
Soonmo KwonByung-Hyun GoJong-Hyeok LeePublished in: Pattern Recognit. Lett. (2020)
Keyphrases
- machine translation
- neural model
- visual context
- temporal context
- neural network
- object detection
- audio visual
- multimedia
- recurrent neural networks
- natural language processing
- information extraction
- control scheme
- target language
- multi modal
- natural language
- image search
- visual words
- visual features
- multi layer perceptron
- artificial intelligence
- semantic information
- visual information
- knowledge base