CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding.
Qiongyi ZhouChangde DuShengpei WangHuiguang HePublished in: ICLR (2024)
Keyphrases
- information sources
- domain knowledge
- semantically rich
- higher level
- semantic information
- low level features
- contextual information
- semantically meaningful
- semantic content
- semantic analysis
- visual information
- user interaction
- neural network
- visual features
- information extraction
- recommender systems
- visual data
- natural language
- keywords
- semantic knowledge
- visual representation
- high level
- semantic level
- metadata