Abstract: A method of updating a classifier on-the-fly is provided. The method includes providing a base classifier. The base classifier is a neural network. The method further includes receiving a class and a set of images associated with the class. The method further includes splitting the set of images into an evaluation set and a training set. The method further includes updating the base classifier on-the-fly to provide an updated classifier. Updating the base classifier includes (1) extracting features for each image from the training set from the base classifier; (2) training the updated classifier using the extracted features; and (3) scoring the evaluation set with the updated classifier.

Abstract: A method for assigning a personalized aesthetic score to an image is provided. The method includes providing a base neural network for generating learned features. The base neural network is trained on a first set of training images and the base neural network includes two or more layers comprising one or more initial layers and one or more final layers. The method further includes receiving a second set of training images and updating the base neural network to generate a personalized neural network based on the received second set of training images. Updating the base neural network comprises re-training the final layers of the base neural network with the second set of images and keeping the initial layers of the base neural network, such that the personalized neural network includes two or more layers comprising one or more initial layers and one or more final layers.

Abstract: A system, method, and computer program product for assigning an aesthetic score to an image. A method of the present invention includes receiving an image. The method further includes executing a neural network on the image to generate learned features. The method further includes applying a machine-learned model to assign an aesthetic score to the image, where a more aesthetically-pleasing image is given a higher aesthetic score and a less aesthetically-pleasing image is given a lower aesthetic score. The learned features are inputs to the machine-learned model.

Abstract: A system, method, and computer program product for assigning an aesthetic score to an image. A method of the present invention includes receiving an image comprising a set of global features. The method includes extracting a set of global features for the image. The method further includes encoding the extracted set of global features into a high-dimensional feature vector. The method further includes reducing the dimension of the high-dimensional feature vector. The method further includes applying a machine-learned model to assign an aesthetic score to the image, wherein a more aesthetically-pleasing image is given a higher aesthetic score and a less aesthetically-pleasing image is given a lower aesthetic score.

Abstract: A system, method, and computer program product for assigning an aesthetic score to an image. A method of the present invention includes receiving an image. The method further includes executing a neural network on the image to generate learned features. The method further includes applying a machine-learned model to assign an aesthetic score to the image, where a more aesthetically-pleasing image is given a higher aesthetic score and a less aesthetically-pleasing image is given a lower aesthetic score. The learned features are inputs to the machine-learned model.

Abstract: A system, method, and computer program product for assigning an aesthetic score to an image. A method of the present invention includes receiving an image comprising a set of global features. The method includes extracting a set of global features for the image. The method further includes encoding the extracted set of global features into a high-dimensional feature vector. The method further includes reducing the dimension of the high-dimensional feature vector. The method further includes applying a machine-learned model to assign an aesthetic score to the image, wherein a more aesthetically-pleasing image is given a higher aesthetic score and a less aesthetically-pleasing image is given a lower aesthetic score.

Abstract: A system, method, and computer program product for displaying a plurality of images. A method of the present invention includes storing image-associated metadata for each image. The method further includes storing user-associated metadata for each user. The method further includes creating a graph comprising the plurality of images, based on the image-associated and user-associated metadata. The method further includes processing the plurality of images based on the graph to generate a subset of the plurality of images. The method further includes displaying the subset of the plurality of images.

Abstract: A system, method, and computer program product for enabling a user to enlarge a displayed image on a user device. A method of the present invention comprises requesting an image selected by a user from a remote device and receiving said image. The method includes displaying the received image on the user device and receiving a single user input indicating a desired zoom location. The method further includes enlarging the displayed image in response to said input, wherein the vertical height of the image matches the vertical height of the user device display screen. The method further includes downloading from the remote device a high resolution version of the image and displaying the high resolution version in place of the enlarged image.