Optimizing Visual Representations in Semantic Multi-modal Models with Dimensionality Reduction, Denoising and Contextual Information.
Maximilian KöperKim Anh NguyenSabine Schulte im WaldePublished in: GSCL (2017)
Keyphrases
- multi modal
- contextual information
- visual representations
- denoising
- context aware
- semantic concepts
- semantic information
- high dimensional
- dimensionality reduction
- audio visual
- image processing
- spatial context
- visual representation
- generative model
- probabilistic model
- low level
- contextual knowledge
- intelligent tutoring systems
- particle filter
- image retrieval
- feature extraction