Abstract: A clustering procedure for grouping a set of images is selected from amongst plural clustering procedures. A predetermined categorization of objects such as images is input, and image features are extracted from each image in the set of images. A comparison measure is determined, by which to compare respective features of the set of images. Respective features between the images in the set of images are compared, based on the comparison measure, and a group of measures representing the differences between features of respective images is output. The plural clustering procedures are applied to the set of images to cluster the images based in part on the calculated group of measures. A clustering quality score is generated for each clustering procedure, based on the clusters created by the clustering procedure and the predetermined categorization of images. The clustering procedure with a high clustering quality score is selected.

Abstract: Systems and methods for displaying an object determine a display time of a first object, wherein the display time of the first object is determined based on one or more attributes of objects in a collection of objects, generate a display that includes at least part of the first object in a first portion of the display for the display time of the first object, wherein the display is configured for rendering on a display device, and remove the first object from the first portion of the display after the display time of the first object has elapsed.

Abstract: A clustering procedure for grouping a set of images is selected from amongst plural clustering procedures. A predetermined categorization of objects such as images is input, and image features are extracted from each image in the set of images. A comparison measure is determined, by which to compare respective features of the set of images. Respective features between the images in the set of images are compared, based on the comparison measure, and a group of measures representing the differences between features of respective images is output. The plural clustering procedures are applied to the set of images to cluster the images based in part on the calculated group of measures. A clustering quality score is generated for each clustering procedure, based on the clusters created by the clustering procedure and the predetermined categorization of images. The clustering procedure with a high clustering quality score is selected.

Abstract: Representative images are selected for display from a group. A dissimilarity measure is selected, by which to compute dissimilarities between features of respective images in the group. Dissimilarities between the images in the group are computed, based on the selected dissimilarity measure. A relative dissimilarity between each image and the other images in the group is determined, based on the relative dissimilarity between the feature of the image and the features of the other images in the group. An image in the group is selected as a representative image for display, using the relative dissimilarity of the image as a probability bias in the selection.