Google Inc.

Ying Ying Liu

Aaron Malenfant

Jiexing Gu

Wei Liu

Haidong Shao

Hongshu Liao

Vinay Damodar Shet

Jason Fedor

Edison Tan

Alan Howard Davis

Karthic Neelands Epker

Multiple image verification challenges can be used to identify the location of an object within an initial image. For instance, a first set of tiles is generated using the initial image. This first set is provided to a client computing device for display in a first verification challenge requesting that the user select tiles including the object. In response, a user selection of tiles of the first set is received. These selected tiles are then used to generate a second set of tiles corresponding to a sub-portion of the initial image. The second set of tiles is provided to a client computing device for display in a second verification challenge. In response to the second verification challenge, a user selection of tiles of the second set is received. This user selection of tiles of the second set is then used to determine a location of the object in the image.

Using multiple image verification challenges to determine object location in an image

A search system extracts, for each property known to the system, historical information comprising data for itineraries associated with a partner system associated with the property. The search system determines, for each property-itinerary combination, an update frequency comprising based on historical information data. The search system extracts a history of user impressions of itineraries comprising the property. The search system determines a relative impression weight for each itinerary, an absolute impression weight for the property, and an expected impression weight of each property-itinerary combination. For each current property-itinerary combination, the search system determines a utility value based on the expected update frequency and expected impression weight to satisfy bandwidth constraints for each partner system. The search system schedules, for each partner system, queries for property-itinerary combinations having values greater than threshold utility value.

Granular selection and scheduling of queries

Systems and methods for screening unauthorized devices are provided. More particularly, a challenge that includes a first set of data can be generated. The challenge can require a browser of a requesting device to perform a browser task with respect to the first set of data to generate a second set of data. The challenge can be provided to the requesting device and a response to the challenge can be received. The response can include the second set of data generated by the browser of the requesting device through performance of the browser task. It can be determined whether the browser of the requesting device is an authorized browser based, at least in part, on the second set of data. Whether or not the requesting device is authorized to access a resource can be based, at least in part, on whether the browser is an authorized browser.

Browser attestation challenge and response system

Methods, systems, and media for searching for video content using integrated content sources are provided. In some embodiments, a system for searching for video content is provided, the system comprising: at least one hardware processor that is configured to: receive a search query including at least one search term; identify a plurality of video segments that match the search query, wherein each of the plurality of video segments is associated with a transcript that includes the search term; select a first set of video segments from the plurality of video segments; generate a first composite video by combining the first set of video segments; and cause the first composite video to be presented.

Methods, systems, and media for searching for video content

Systems and methods of verifying a user are provided. In particular, a request to engage in a verification process to gain access to an online resource can be received. The request can be provided by a first user device associated with a user. A validation request associated with a second user device associated with the user can be received. The validation request can include a device profile associated with the second user device. It can then be determined whether to validate the second user device based at least in part on the device profile. When it is determined to validate the second user device, the first user device can be granted access to the online resource.

Controlling access to online resources using device validations

Systems and methods of determining image characteristics are provided. More particularly, a first image having an unknown characteristic can be obtained. The first image can be provided to a plurality of user devices in a verification challenge. The verification challenge can include one or more instructions to be presented to a user of each user device. The instructions being determined based at least in part on the first image. User responses can be received, and an unknown characteristic of the first image can be determined based at least in part on the received responses. Subsequent to determining the unknown characteristic of the first image, one or more machine learning models can be trained based at least in part on the determined characteristic.

Growing community of inventors

Ann Arbor, MI, United States of America

Ying Ying Liu