Google Inc.

Radhika Malpani

Charles Joseph Rosenberg

Henry Allan Rowley

Gaurav Garg

Yun Zhou

Vanessa Hodge

Yonatan Zunger

Cheng Yong Yang

Kevin Law

Krishna Asur Bharat

Paul Haahr

Erik Murphy-Chutorian

Andrea Lynn Frome

Vibhu Mittal

Yoram Singer

Jingbin Wang

Matthew D Cutts

Arcot J Preetham

Elin R Pedersen

Sarah Moussa

Marcin Kaszkiel

Omkar Mate

Noam M Shazeer

Gregory Joseph Badros

Maureen Heymans

John Piscitello

David Ariel Cohn

Abhay Puri

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for aggregating task data for multiple users. In one aspect, a method includes accessing action trail data that corresponds to a task and resources related to that task, wherein each task relates to one or more related topics and is defined by a sequence of user actions corresponding to the resources related to that task; clustering the action trails based on the action trail data such that each action trail cluster corresponds to a particular task and includes the action trails corresponding to that particular task; and for each action trail cluster, ranking the resources that correspond to the included action trails according to the topics of the particular task.

Aggregating activity data for multiple users

Methods, systems and apparatus, including computer programs encoded on a computer storage medium, for determining similar queries for image searches. In one aspect, a method includes generating, for each of a plurality of search queries, a selection vector for the search query, each selection vector including a plurality of vector elements, each vector element corresponding to a unique image, and the value of each vector element being proportional to a number of selections of its corresponding unique image in response to the unique image being presented as a search result for the search query. The method further includes selecting a first search query and a second search query from the plurality of search queries and determining, from the selection vectors for the first and second search queries, a similarity measure that is a measurement of the similarity of the first search query to the second query.

Similar search queries and images

Methods, systems and apparatus for identifying result images for a query image. One or more labels that are associated with the query image are obtained. Candidate images matching the query labels are identified. Visual similarity scores are generated for the candidate images. Each visual similarity score represents the visual similarity of a respective candidate image to the query image. Relevance scores are generated for each of the candidate images based on the visual similarity scores. Each relevance score represents a measure of relevance of the respective candidate images to the query image. The candidate images are ranked based on the relevance scores, a highest ranking subset of the candidate images being identified as result images and referenced by image search results. The result images can be candidate images that satisfy a similarity condition relative to the query image and other result images.

Query image search

A system identifies an image and determines whether the image contains inappropriate content based on first data associated with the image, second data associated with a document that contains the image or refers to the image, and/or third data associated with a group of documents with which the image is associated.

Scoring items

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting labels for a non-text content item. In one aspect, a method receives a set of initial labels for a non-text content item, wherein the set of initial labels specifies text that has been identified as descriptive of the non-text content item and a web page to which the text corresponds. Initial labels corresponding to sets of matching web pages are grouped into separate initial label groups that correspond to each set of matching web pages. Sets of matching labels are grouped into other separate initial label groups that correspond to the sets of matching labels. One or more words that are included in at least a threshold number of the separate label groups are selected as final labels for the non-text content item.

Non-text content item search

Image galleries are automatically located within documents, such as web pages. Documents that are determined to contain image galleries may be treated differently when storing the document for later retrieval by an image search engine. In one implementation, the image galleries are automatically located within a document by calculating position information indicating relative positions of images in the document. The document may be determined to contain an image gallery when the position information indicates that the images in the document are generally evenly distributed.

Automatic determination of whether a document includes an image gallery

Methods, systems, and apparatus, including computer program products, for generating visual media search results are provided. A first visual media search query in a first language is received. One or more bilingual refinements are identified for the first visual media search query. Each bilingual refinement associates an initial query in the first language and a subsequent query in a different second language. The initial query is equivalent to the first visual media search query. The subsequent query is a translation of the initial query in the second language. The subsequent query followed the initial query in a series of queries received from a user in a session. A first bilingual refinement is selected from the one or more bilingual refinements according to a first criterion. A set of visual media search results is generated based on the first search query and the selected first bilingual refinement's associated subsequent search query.

Query translation using bilingual search refinements

Methods, systems, and apparatus, including computer program products, for generating visual media search results are provided. A search query in a first language is received. A plurality of languages are identified. It is determined whether a language should be selected by translating the search query into translated terms in the language, determining a score for each translated term measuring how common the translated term is, and using the scores to determine if the language should be selected. A second language is selected from the plurality of different languages by selecting the considered language if it should be selected and otherwise selecting the second language according to a criterion. A set of one or more search results are generated based on the search query and a translation of the search query into the second language. The results are ordered based on a quality of results statistic for the translated query.

Selecting relevant languages for query translation

Methods, systems, and apparatus, including computer program products, for generating visual media search results are provided. A first search query in a first language and a second search query in a different second language are received. The first search query is a translation of the second search query into the second language. A quality of results statistic for the second search query is obtained. A final search query is created using the first search query, the second search query, and the quality of results statistic. The final search query is sent to a search engine and a final group of visual media search results responsive to the final search query are received from the search engine, where visual media search results in the final group that are responsive to the second visual media search query are assigned a ranking based in part on the quality of result statistic.

Query translation quality confidence

Methods, systems, and apparatus, including computer program products, for validating candidate translations for a phrase. A plurality of candidate translations for a phrase are received. A similarity score for each of the candidate translations is calculated. Each similarity score is an estimate of visual similarity between a group of visual media search results responsive to a visual media search query with text corresponding to the phrase and a group of visual media search results responsive to a visual media search query with text corresponding to a candidate translation. One or more of the candidate translations are selected based on the similarity scores. The selected candidate translations are associated with the phrase as valid translations for the phrase.

Validating translations using visual similarity between visual media search results

Method, system, and computer readable medium for identifying result images based on an image query

Growing community of inventors

Palo Alto, CA, United States of America

Radhika Malpani