Google Inc.

Mihai Badoiu

Shanmugavelayutham Muthukrishnan

Simon Ratner

Igor Kofman

Jasson Schrock

Michael Fink

Julian Frumar

Ryan Junee

Leora Ruth Wiseman

Virginia Wang

Ankur Bhargava

Sigalit Bar

Ran Tavory

Isaac Elias

Herbert Ho

Aviad Barzilai

Nir Kerem

Leora Wiseman

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for distributed nearest-neighbor search for image retrieval are disclosed. An example distributed image retrieval system includes a root server and a plurality of leaf servers. The root server controls the clustering of images in the image corpus, and determines the assignment of image clusters to a collection of leaf servers. Each leaf server is independently configured to perform a two-stage nearest-neighbor search in a locality-sensitive hash space for a received query image within the leaf server's assigned images clusters. Thus, the distributed image retrieval system is modular and amendable to tuning, modifications, duplication, and replacement on a per-server basis. In addition, the design of the image retrieval system allows flexible load balancing among the leaf servers.

Distributed image search

A system and method is provided for managing and displaying annotations in online hosted videos. To determine related annotations associated with a video, a plurality of annotations for one or more intervals of the video are collected and organized into a plurality of groups. Each group includes annotations for intervals of the video that are similar to each other. A group having related annotations is identified, and an annotated clip of the video is formed based upon the intervals in the group. This process can be used to determine any number of groups in a given video having related annotations, forming the respective annotated intervals within a single video, and can also identify and organize annotated intervals within a large number of different videos.

Annotating video intervals

Systems and methods are provided for adding and displaying interactive annotations for existing online hosted videos. A graphical annotation interface allows the creation of annotations and association of the annotations with a video. Annotations may be of different types and have different functionality, such as altering the appearance and/or behavior of an existing video, e.g. by supplementing it with text, allowing linking to other videos or web pages, or pausing playback of the video. Authentication of a user desiring to perform annotation of a video may be performed in various manners, such as by checking a uniform resource locator (URL) against an existing list, checking a user identifier against an access list, and the like. As a result of authentication, a user is accorded the appropriate annotation abilities, such as full annotation, no annotation, or annotation restricted to a particular temporal or spatial portion of the video.

Web-based system for collaborative generation of interactive videos

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for calculating a location relevance score for search results is disclosed. In one aspect, a location relevance score is calculated for each search result based on three distances to a physical address associated with the search result. The first distance is measured from a polygon approximating the boundary of a specified region of interest. The second distance is measured from a combined area associated with the associated zip codes of the specified region of interest. The third distance is measured from a central location determined according to criteria independent of geometry of the specified region of interest. The search results are ranked according to their associated location relevance scores.

Ranking location search results based on multiple distance measures

A system and method is provided for identifying popular intervals in online hosted videos. To determine popular intervals associated with a video, a plurality of votes for one or more intervals of the video are collected and organized into a plurality of groups. Each group includes votes for intervals of the video that are similar to each other. A group having the highest number of votes is identified, and a most popular clip of the video is formed based upon the intervals in the group with the highest number of votes. This process can be carried out to determine the groups having the second and third highest number of votes in a single video to form the second and third most popular clips in that video, as well as across numerous videos to identify the most popular clips within different videos.

System and method for voting on popular video intervals

Growing community of inventors

New York, NY, United States of America

Mihai Badoiu