Bag of Visual Words model

GPTKB entity

Statements (33)
Predicate Object
gptkbp:instanceOf computer vision model
gptkbp:alsoKnownAs gptkb:BoVW
gptkbp:application gptkb:machine_learning
computer vision
gptkbp:category pattern recognition
feature extraction
image representation
gptkbp:commonClusteringAlgorithm gptkb:k-means
gptkbp:commonDescriptor gptkb:SIFT
gptkb:ORB
gptkb:SURF
gptkbp:extendsTo gptkb:Spatial_Pyramid_Matching
Fisher Vector
VLAD
gptkbp:featureExtractionMethod local image descriptors
gptkbp:featureQuantization clustering
visual vocabulary
https://www.w3.org/2000/01/rdf-schema#label Bag of Visual Words model
gptkbp:input gptkb:illustrator
gptkbp:inspiredBy gptkb:Bag_of_Words_model
gptkbp:limitation ignores spatial relationships
gptkbp:notablePublication "Visual Categorization with Bags of Keypoints" by C. Schmid et al.
gptkbp:output feature vector
gptkbp:proposedBy 2003
gptkbp:relatedTo gptkb:Bag_of_Words_model
deep learning
gptkbp:replacedBy convolutional neural networks
gptkbp:represents histogram of visual words
gptkbp:usedIn image classification
object recognition
image retrieval
gptkbp:bfsParent gptkb:Josef_Sivic
gptkbp:bfsLayer 7