CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding.
Qiongyi ZhouChangde DuShengpei WangHuiguang HePublished in: CoRR (2024)
Keyphrases
- high level
- visual cues
- information retrieval
- semantically rich
- multimedia
- keywords
- natural language
- video clips
- multimedia data
- visual information
- information sources
- domain ontology
- semantic context
- semantically meaningful
- spatial information
- semantic information
- contextual information
- information processing
- higher level
- end users
- low level
- domain knowledge
- prior knowledge
- metadata
- social networks