Mean Box Pooling: A Rich Image Representation and Output Embedding for the Visual Madlibs Task.
Mateusz MalinowskiAshkan MokarianMario FritzPublished in: BMVC (2016)
Keyphrases
- image representation
- image classification
- multiscale
- scene categorization
- object recognition
- visual features
- representation scheme
- image retrieval
- quadtree
- visual information
- visual words
- bag of words
- image content
- scene categories
- sparse coding
- scene recognition
- low level features
- bag of features
- image features
- visual vocabulary
- feature representations
- spatial pyramid matching
- spatial layout
- scene classification
- feature space
- bag of visual words
- cbir systems
- receptive fields
- object retrieval
- machine learning
- high level