Knowledge-driven Scene Priors for Semantic Audio-Visual Embodied Navigation.
Gyan TatiyaJonathan FrancisLuca BondiIngrid NavarroEric NybergJivko SinapovJean OhPublished in: CoRR (2022)
Keyphrases
- audio visual
- knowledge driven
- visual data
- multi modal
- audio visual content
- visual information
- multi stream
- audio visual speech recognition
- video sequences
- semantic web
- three dimensional
- microarray
- semantic information
- image sequences
- multimedia
- temporal context
- high dimensional
- visual features
- high dimensional data
- image data
- visual content
- network model
- keywords
- feature extraction
- high level