Incorporating visual features into word embeddings: A bimodal autoencoder-based approach.
Mika HasegawaTetsunori KobayashiYoshihiko HayashiPublished in: IWCS(2) (2017)
Keyphrases
- visual features
- keywords
- visual information
- image classification
- image retrieval
- visual content
- text queries
- low level features
- image search
- low level
- semantic gap
- image collections
- image annotation
- semantic features
- visual appearance
- co occurrence
- vector space
- semantic concepts
- bag of features
- n gram
- bridge the semantic gap
- dimensionality reduction
- global features
- web images
- acoustic features
- visual properties
- key frames
- automatic image annotation
- probabilistic latent semantic analysis
- labeled images