(57) ABSTRACT A method of modelling data, comprising: training an objec tive function of a
linear classifier, based on a set of labeled data, to derive a set of classifier weights; defining …

BACKGROUND Automated image annotation may be done using neural networks. The
neural networks used for image annotation are trained to determine the most appropriate …

US10169686B2 - Systems and methods for image classification by correlating contextual
cues with images - Google Patents US10169686B2 - Systems and methods for image …

An approach is provided for providing quality assurance for training a feature prediction
model. The approach involves training the feature prediction model to label one or more …

BACKGROUND Image matching is a technique being used in computer vision, object
recognition, motion tracking, three-dimen sional (3D) modeling, and the like, which can be …

Computationally efficient accelerated D2-clustering algorithms are disclosed for clustering
discrete distributions under the Wasserstein distance with improved scalability. Three first …

Various embodiments may increase scalability of image representations stored in a
database for use in image matching and retrieval. For example, a system providing image …

An information processing apparatus includes a selector and an extending unit. The selector
selects a word in question training data corresponding to a topic. The extending unit extends …

A matching record set with respect to a particular data record of a stream is identified based
on output values produced by a particular band of locality sensitive hash functions. Using …

Example embodiments that analyze images to characterize aspects of the images rely on a
same neural network to characterize multiple aspects in parallel. Because additional neural …