Abstract: Techniques are generally described for displaying outfit recommendations using a recurrent neural network. In various examples, a computing device may receive a first state vector representing an outfit comprising at least one fashion item. First image data depicting a second fashion item of a first item category may be received. A recurrent neural network may generate a first output feature vector based on the first state vector, the first image data, a first attribute vector, and the first item category. The first output feature vector may be compared to other feature vectors representing other fashion items in the first category to determine distances between the first output feature vector and the other feature vectors. A set of fashion items may be recommended and displayed based on the distances between the first output feature vector and the other feature vectors.

Abstract: Techniques are generally described for performing outfit recommendation using a recurrent neural network. In various examples, a computing device may receive a first state vector representing an outfit comprising at least one fashion item. First image data depicting a second fashion item of a first item category may be received. A machine learning mode may generate a first output feature vector based on the first state vector, the first image data, a first attribute vector, and the first item category. The first output feature vector may be compared to other feature vectors representing other fashion items in the first category to determine distances between the first output feature vector and the other feature vectors. A set of fashion items may be recommended based on the distances between the first output feature vector and the other feature vectors.

Abstract: First image data representing a first human wearing a first article of clothing may be received. The first image data, when rendered on a display, may include a first photometric artifact. A first generator network may be used to generate second image data from the first image data. The first photometric artifact may be removed from the second image data. A second generator network may be used to generate third image data from the second image data, the third image data representing the first human in a different pose relative to the first image data. Fourth image data representing the first article of clothing segmented from the first human may be generated and displayed on a display.

Abstract: Devices and techniques are generally described for catalog normalization and segmentation for fashion images. First image data representing a first human wearing a first article of clothing may be received. The first image data, when rendered on a display, may include a first photometric artifact. A first generator network may be used to generate second image data from the first image data. The first photometric artifact may be removed from the second image data. A second generator network may be used to generate third image data from the second image data, the third image data representing the first human in a different pose relative to the first image data. Fourth image data representing the first article of clothing segmented from the first human may be generated and displayed on a display.

Abstract: Techniques are generally described for performing outfit recommendation using a recurrent neural network. In various examples, a computing device may receive a first state vector representing an outfit comprising at least one article of clothing. First image data depicting a second article of clothing of a first clothing category may be received. A recurrent neural network may generate a first output feature vector based on the first state vector, the first image data and the first clothing category. The first output feature vector may be compared to other feature vectors representing other articles of clothing in the first category to determine distances between the first output feature vector and the other feature vectors. A set of articles of clothing may be recommended based on the distances between the first output feature vector and the other feature vectors.

Abstract: A method for representing an input image, the method including the steps of applying a trained neural network (NN) on the input image, selecting a plurality of feature maps, determining a location of each of the feature maps in an image space of the input image, defining a plurality of interest points of the input image, representing the input image as a graph according to the interest points and geometric relations between the interest points, and employing the graph for performing a visual task, the graph including a plurality of vertices and edges, and maintaining the data respective of the geometric relations, the feature maps being selected of an output of at least one selected layer of the trained NN according to values attributed to the feature maps by the trained NN, the interest points of the input image being defined based on the locations corresponding to the feature maps.

Abstract: A method for producing a graph representation of an input image, the method including the procedures of applying convolutional layers of a trained convolutional neural network on the input image, defining a receptive field of a last convolutional layer of the trained convolutional neural network as a vertex of the graph representation, defining a vector of a three dimensional output matrix of the last convolutional layer that is mapped to the receptive field as a descriptor for the vertex and determining an edge between a pair of vertices of the graph representation by applying an operator on a pair of descriptors respective of the pair of vertices.

Abstract: A method for representing an input image includes the steps of applying a trained neural network on the input image, selecting a plurality of feature maps, determining a location of each of the plurality of feature maps in an image space of the input image, defining a plurality of interest points of the input image, and employing the plurality of interest points for representing the input image for performing a visual task. The plurality of feature maps are selected of an output of at least one selected layer of the trained neural network according to values attributed to the plurality of feature maps by the trained neural network. The plurality of interest points of the input image are defined based on the locations corresponding to the plurality of feature maps.

Abstract: A method for determining image similarity as a function of weighted descriptor similarities, including the procedures of feeding a query image to a network including a plurality of layers and defining an output of each of the layers as a descriptor of the query image, feeding a reference image to the network and defining an output of each of the layers as a descriptor of the reference image, determining a descriptor similarity score for respective descriptors that were produced by the same layer of the network fed the query image and the reference image, assigning a respective weight to each descriptor similarity score and defining an image similarity between the query image and the reference image as a function of the weighted descriptor similarity scores.

Abstract: A method for producing a graph representation of an input image, the method including the procedures of applying convolutional layers of a trained convolutional neural network on the input image, defining a receptive field of a last convolutional layer of the trained convolutional neural network as a vertex of the graph representation, defining a vector of a three dimensional output matrix of the last convolutional layer that is mapped to the receptive field as a descriptor for the vertex and determining an edge between a pair of vertices of the graph representation by applying an operator on a pair of descriptors respective of the pair of vertices.

Abstract: A method for representing an input image includes the steps of applying a trained neural network on the input image, selecting a plurality of feature maps, determining a location of each of the plurality of feature maps in an image space of the input image, defining a plurality of interest points of the input image, and employing the plurality of interest points for representing the input image for performing a visual task. The plurality of feature maps are selected of an output of at least one selected layer of the trained neural network according to values attributed to the plurality of feature maps by the trained neural network. The plurality of interest points of the input image are defined based on the locations corresponding to the plurality of feature maps.