Abstract: Methods for identifying data files responsive to a search query and weighted according to a stylistic preference are provided. In one aspect, a method includes receiving a search query for a collection of media files from a device associated with a user associated with a user identifier, and identifying a set of image files from the collection that is responsive to the query. Each image file in the set is associated with a relevancy score. The method also includes retrieving a stylistic preference profile associated with the user identifier to apply to the set, and weighting the score for each image file according to the profile to generate a weighted stylistic preference score for each image file. The method further includes creating a listing of the set that is sorted according to weighted stylistic preference score, and providing the listing to the device. Systems and machine-readable media are also provided.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for clustering search results based on image composition. A system may, for each image in a set of images, determine a compositional vector representing one or more objects and corresponding locations within the image using a trained computer-operated convolutional neural network. The system may provide each image through a clustering algorithm to produce one or more clusters based on compositional similarity. The system may provide images from the set of images clustered by composition, in which the images include a different listing of images for each of the one or more clusters. The system may provide a prioritized listing of images responsive to a user search query, in which the prioritized listing of images includes a different listing of images for each cluster of compositional similarity based on the metadata of each image associated with the cluster.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for clustering search results based on image composition. A system may, for each image in a set of images, determine a compositional vector representing one or more objects and corresponding locations within the image using a trained computer-operated convolutional neural network. The system may provide each image through a clustering algorithm to produce one or more clusters based on compositional similarity. The system may provide images from the set of images clustered by composition, in which the images include a different listing of images for each of the one or more clusters. The system may provide a prioritized listing of images responsive to a user search query, in which the prioritized listing of images includes a different listing of images for each cluster of compositional similarity based on the metadata of each image associated with the cluster.