VK-G2T: Vision and Context Knowledge Enhanced Gloss2text.
Liqiang JingXuemeng SongXinxing ZuNa ZhengZhongzhou ZhaoLiqiang NiePublished in: ICASSP (2024)
Keyphrases
- computer vision
- information retrieval
- textual case based reasoning
- contextual knowledge
- knowledge retrieval
- world knowledge
- prior knowledge
- conceptual framework
- knowledge sources
- context aware
- general knowledge
- knowledge extraction
- context sensitive
- domain knowledge
- real time
- knowledge discovery
- text mining
- design process
- database
- knowledge acquisition
- digital libraries
- key concepts
- domain dependent
- knowledge base
- global knowledge
- vision system
- contextual information
- text retrieval
- semantic network
- domain specific
- natural language
- keywords
- neural network