Microsoft Technology Licensing, LLC

Ravi Theja Yada

Arun Sacheti

Yan Wang

Parthasarathy Govindarajen

Surendra Ulabala

Sarvesh Nagpal

Nikita Astrakhantsev

Wallace Earl Greathouse

Swaathee Radhakrishnan

Various embodiments discussed herein are directed to improving existing technologies by extracting or detecting identifiers from a page, regardless of the device or platform a user is using, and then anonymizing such identifiers to determine if the same user accessed different pages or if the current user of a current computer session is a same user as in past computer sessions.

Privacy preserving identity resolution via page content

A computer-implemented technique is described herein for performing an image-based search that allows a user to create a custom query image that expresses the user's search intent. The technique generates the query image based on one or more input images and/or one or more information items that describe at least one desired characteristic of the query image. The technique then submits the query image to a search engine, and, in response, receives a set of candidate images that match the query image. In one implementation, the technique constructs the query image using a decoder neural network that operates on a mixed latent variable vector. In one approach, the technique uses a generative adversarial network (GAN) to produce the decoder neural network.

Techniques for modifying a query image

This document relates to using input images to selectively trigger skills. For example, the input images can be analyzed using a machine learning model, which can output image metadata characterizing content of the input images. Different skills can be selectively triggered based on the image metadata. For example, a given skill can register to be triggered when the image metadata matches one or more triggering conditions specified by that skill.

Image-based skill triggering

Growing community of inventors

Newcastle, WA, United States of America

Ravi Theja Yada