On Architectures for Including Visual Information in Neural Language Models for Image Description.
Marc TantiAlbert GattKenneth P. CamilleriPublished in: CoRR (2019)
Keyphrases
- visual information
- language model
- image description
- low level features
- language modeling
- visual features
- image understanding
- low level
- document retrieval
- visual content
- n gram
- audio visual
- probabilistic model
- retrieval model
- information retrieval
- image retrieval
- eye movements
- test collection
- query expansion
- image representation
- feature detection
- visual data
- semantic information
- data modeling
- image annotation
- active learning
- color histogram
- higher level
- bayesian networks
- databases