Rejecting mismatches of visual words by contextual descriptors.
Jinliang YaoBing YangQiuming ZhuPublished in: ICARCV (2014)
Keyphrases
- visual words
- bag of features
- object retrieval
- sift descriptors
- keypoints
- bag of words
- image retrieval
- sift features
- image classification
- bag of visual words
- semantic context
- visual vocabulary
- image representation
- discriminative power
- bag of words models
- spatial pyramid matching
- co occurrence
- image features
- visual phrases
- visual context
- contextual information
- scene classification
- object categories
- spatial information
- visual content
- image descriptors
- feature space
- image matching
- visual dictionary
- n gram
- object recognition
- shape descriptors
- gaussian mixture model
- action recognition
- pairwise
- multiscale
- scale invariant feature transform
- visual features
- feature vectors
- face recognition
- image database
- information extraction