Abstract: The efficient allocation of advertisements, also known as creatives, on one or more web sites is provided for while ensuring that guarantees to advertisers are honored. In one embodiment, a linear program solver allocates creatives to advertising slots according to an optimizing function designed to maximize revenue for the site. The linear program solver takes as input a set of creatives, creative performance data, constraints, and slot identifiers. The output of the linear program solver is an optimized schedule not violative of any of the input constraints.

Abstract: The subject matter of this specification can be embodied in, among other things, a computer-implemented method that includes receiving a plurality of images having human faces. The method further includes generating a data structure having representations of the faces and associations that link the representations based on similarities in appearance between the faces. The method further includes outputting a first gender value for a first representation of a first face that indicates a gender of the first face based on one or more other gender values of one or more other representations of one or more other faces that are linked to the first representation.

Abstract: Methods, systems, and computer program products, including computer programs encoded on a computer readable storage medium, for providing content to a user based on the mode of the user. A method includes: identifying a user for targeting content; evaluating usage information for the user to determine targeting information for a plurality of modes associated with the user; receiving a request to deliver content to the user including an identifier associated with the user and information to determine which mode of the plurality of modes the user is operating in; and providing content to the user based on the mode and associated targeting information.

Abstract: Systems and processes for data presentation may be implemented with a variety of operations and techniques. In particular aspects, a system and process for data presentation may include the ability to receive a data request at a data distribution device and determine data responsive to the data request, the responsive data including textual data. The system and process may also include the ability to modify the textual responsive data based on a user interface for visually presenting the textual responsive data and generate a data response including the modified textual responsive data.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes generating content-based keywords based on content generated by users of a social network. The method includes labeling nodes comprising user nodes, which are representations of the users, with advertising labels comprising content-based keywords that coincide with advertiser-selected keywords that are based on one or more terms specified by an advertiser. The method also includes outputting, for each node, weights for the advertising labels based on weights of advertising labels associated with neighboring nodes, which are related to the node by a relationship.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting keywords for resources. In one aspect, a method includes identifying a particular online resource that includes non-text content. Co-visitation data are obtained for the particular resource. The co-visitation data specify one or more co-requested online resources for the particular online resource. Each of the co-requested online resources were requested by a user device within a threshold period of the request for the particular online resource by the user device. Keywords are identified for each of the co-requested online resources, and can include keywords that were selected based on text content of the co-requested online resource. One or more of the identified keywords are selected as keywords for the particular resource.

Abstract: The efficient allocation of advertisements, also known as creatives, on one or more web sites is provided for while ensuring that guarantees to advertisers are honored. In one embodiment, a linear program solver allocates creatives to advertising slots according to an optimizing function designed to maximize revenue for the site. The linear program solver takes as input a set of creatives, creative performance data, constraints, and slot identifiers. The output of the linear program solver is an optimized schedule not violative of any of the input constraints.

Abstract: A computer-implemented method may include presenting to a user one or more images, receiving a rotational reorientation of the one or more images by the user, and providing access to a computing service based on a comparison of the orientations of the one or more images after reorientation by the user to a standard for each image.

Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.

Abstract: In general, the subject matter described in this disclosure can be embodied in methods, systems and program products. A computing device receives user input that submits a search query. The computing device provides, by way of a search engine server system, the search query. The computing device receives, from the search engine server system, information that identifies search results that the search engine server system has determined are responsive to the search query. The computing device presents, in a first view of a search results page that is provided on a screen of the computing device in response to receiving the information identifying the search results, a portion of the search results page that includes a list of the search results, the search results page having been pre-scrolled to the portion of the search results page.

Abstract: A computer-implemented method of providing personalized route information involves gathering a plurality of past location indicators over time for a wireless client device, determining a future driving objective using the plurality of previously-gathered location indicators, obtaining real-time traffic data for an area proximate to the determined driving objective, and generating a suggested route for the driving objective using the near real-time traffic data.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes inferring labels for videos, users, advertisements, groups of users, and other entities included in a social network system. The inferred labels can be used to generate recommendations such as videos or advertisements in which a user may be interested. Inferred labels can be generated based on social or other relationships derived from, for example, profiles or activities of social network users. Inferred labels can be advantageous when explicit information about these entities is not available. For example, a particular user may not have clicked on any online advertisements, so the user is not explicitly linked to any advertisements.

Abstract: An exemplar dictionary is built from example image blocks for determining predictor blocks for encoding and decoding images. The exemplar dictionary comprises a hierarchical organization of example image blocks. The hierarchical organization of image blocks is obtained by clustering a set of example image blocks, for example, based on k-means clustering. Performance of clustering is improved by transforming feature vectors representing the image blocks to fewer dimensions. Principal component analysis is used for determining feature vectors with fewer dimensions. The clustering performed at higher levels of the hierarchy uses fewer dimensions of feature vectors compared to lower levels of hierarchy. Performance of clustering is improved by processing only a sample of the image blocks of a cluster. The clustering performed at higher levels of the hierarchy uses lower sampling rates as compared to lower levels of hierarchy.

Abstract: A method includes receiving search queries. Images are generated that represent the volume of each search query relative to all search queries over a period of time. The images are processed to generate wavelets for each image. Related queries having similar increases or decreases in volume are identified by comparing at least some of the wavelets corresponding to a first query to wavelets corresponding to other queries.

Abstract: Methods, systems, and apparatus, including computer program products are provided for ranking distinct book content items based on implicit links to other distinct book content items. The implicit links are defined based on the identification of matching features in the distinct book content items. In some implementations, the matching features are uncommon phrases in textual content of the distinct book content items. Edges representing implicit links are generated between distinct nodes representing distinct book content items in a weighted graph. Search results for distinct book content items can be ordered based on the edges connected to the distinct nodes in the weighted graph that represent the distinct book content items.

Abstract: A method including training a plurality of learning systems, each learning system implementing a learning function and having an input and producing an output, initializing one or more data structures, and evaluating a target sample is described. Also described are methods that include initializing one or more data structures and evaluating a target sample for a best match.

Abstract: A method including training a plurality of learning systems, each learning system implementing a learning function and having an input and producing an output, initializing one or more data structures, and evaluating a target sample is described. Also described are methods that include initializing one or more data structures and evaluating a target sample for a best match.

Abstract: Implementations consistent with the principles described herein relate to ranking a set of images based on features of the images determine the most representative and/or highest quality images in the set. In one implementation, an initial set of images is obtained and ranked based on a comparison of each image in the set of images to other images in the set of images. The comparison is performed using at least one predetermined feature of the images.

Abstract: A method of initiating a telecommunication session for a communication device include submitting to one or more telecommunication carriers a proposal for a telecommunication session, receiving from at least one of the one or more of telecommunication carriers a bid to carry the telecommunications session, and automatically selecting one of the telecommunications carriers from the carriers submitting a bid, and initiating the telecommunication session through the selected telecommunication carrier.

Abstract: Systems and methods for socially-based correction of tilted images. In an embodiment, the present invention levels tilted images by (1) receiving an image; (2) rotating the image by a random angle; (3) requesting at least one user rotate the image to level the image; (4) determining a collective user-suggested angle based on the rotations of each user; and (5) transmitting, over a communication network, a correction angle, where the correction angle is based on the random angle and the collective user-suggested angle.