Abstract: Similar faces may be determined within images based on human perception of facial similarity. The user may provide an image including a query face to which the user wishes to find faces that are similar. Similar faces may be determined based on similarity information. Similarity information may be generated from information related to a human perception of facial similarity. Images that include faces determined to be similar, based on the similarity information, may be provided to the user as search result images. The user then may provide feedback to indicate the user's perception of similarity between the query face and the search result images.

Abstract: A method for personalizing content for a particular user in a computing system comprising a user interface configured to display content. The method comprises identifying a content item accessed by a user, identifying features associated with the content item; using the features of the content item to identify one or more third party profiles that substantially match a content profile of the content item, and displaying a list of the identified third party profiles.

Abstract: A method for personalizing content for a particular user in a computing system comprising a user interface configured to display content. The method comprises identifying one or more features of a short term profile of a user that are not included in a long term profile of the user, using the one or more features to identify one or more third party profiles having features that substantially match the one or more features of the user's short term profile, accessing the identified one or more third party profiles, and providing one or more content items included in the third party profile to the user, the one or more content items having associated features that match the one or more features of the short term profile. An alternative method comprises accessing one or more third party profiles that are not a profile of the user, and using the accessed third party profile to identify a plurality of content items for recommendation to the user based on a feature set of the third party profile.

Abstract: Systems and methods are disclosed for performing location-based authentication using location-aware devices. One method includes: receiving an access request comprising authentication credentials and a first location from a first location-aware device; receiving a second location from a second location-aware device associated with the authentication credentials; and upon determining that the first location and second location are within a pre-determined distance, authenticating the authentication credentials.

Abstract: In accordance with certain embodiments, a query from a client may be received at a server, and a default query range may be applied to the query. The query may be executed in a first execution using an index comprising a category of information stored in the database and subject to the default query range. If the number of query results from the first execution is outside a predetermined range, then the query range may be adjusted to obtain a number of query results closer to or within the predetermined range. Additionally, the query may be executed in a second execution using the index comprising the category of information stored in the database and subject to the adjusted query range. Thereafter, the query results obtained from the second execution of the query may be sent to the client.

Abstract: Systems and methods are disclosed for authenticating an identity of an online user. One method includes receiving from the user, through a first device, a request to access a web page associated with the user's online account; transmitting to the user an image that contains a unique ID and a URL of an authentication server; and receiving from the user, through the first device, an authentication request containing the unique ID. The method also includes receiving from the user, through a second device, a log-in ID associated with the user and the unique ID; and authenticating the identity of the user to grant the user access, through the first device, to the web page associated with the user's online account.

Abstract: Systems and methods are provided for timing message notifications to be provided to mobile device users based on their geographic locations with respect to geographic areas associated with a threshold level of content consumption. The timing of message notifications may be controlled in order to optimize the chances of delivering targeted content to a mobile device user based on the current geographic location of the user's device relative to a threshold level of content consumption area. As mobile device users may be more likely to launch a client application in a place where other users are currently consuming content, a general message notification sent to the user's device located in a geographic area associated with a threshold level of content consumption, may increase the likelihood that the user will launch the client application and thereby, allow targeted content to be delivered to the user's mobile device.

Abstract: In order to increase the efficacy of a mood-based playlisting system, a mood sensor such as a camera may be used to provide mood information to the mood model. When the mood sensor includes a camera, a camera may be used to capture an image of the user. The image is analyzed to determine a mood for the user so that content may be selected responsive to the mood of the user.

Abstract: Computerized systems and methods are disclosed for performing contextual classification of objects using supervised and unsupervised training. In accordance with one implementation, content reviewers may review training objects and submit supervised training data for preprocessing and analysis. The supervised training data may be preprocessed to identify key terms and phrases, such as by stemming, tokenization, or n-gram analysis, and form vectorized objects. The vectorized objects may be used to train one or more models for subsequent classification of objects. In certain implementations, preprocessing or training, among other steps, may be performed in parallel over multiple machines to improve efficiency. The disclosed systems and methods may be used in a wide variety of applications, such as article classification and content moderation.

Abstract: A graphical user interface between a user of a computer service and the computer service includes a list of other users of the computer service selected by the user as significant to the user and an icon associated with one of the other listed users indicating that a communication has occurred between the user and the other user.

Abstract: Computerized systems and methods are disclosed for analyzing search query relationships and managing electronic content. In accordance with one implementation, log data pertaining to a plurality of queries may be received over an electronic network. A click graph may be generated representing one or more relationships between the queries. Further, temporal similarities may be identified between the queries, for example, by looking at peaks in frequency of queries over time. A pair of search queries may be evaluated based on the generated click graph and the identified temporal similarities to determine whether the queries in the pair are related.

Abstract: Systems and methods for sorting electronic messages using attributes of senders or of sender addresses. An electronic messaging server sorts electronic messages using attributes associated with the senders or sender addresses of the electronic messages. The sender addresses and associated attributes are stored in an accept list. A sorting module uses the accept list to sort the electronic messages into various folders. The sorting module can also access other data sources, such as a contact list, to assist in sorting the electronic messages. The attributes can be determined independently of the user or can be set directly by the user. The attributes can also identify a status of a sender such as whether the sender is authorized, unauthorized, or unconfirmed.

Abstract: Computerized systems and methods are disclosed for scheduling events. In accordance with one implementation, a computerized method comprises receiving an indication of a gesture via a multi-touch display of a computing device, wherein the indication of the gesture comprises data representing a starting location and data representing a directional vector. The method also includes identifying a first graphical object associated with the gesture. In addition, the method includes displaying an event context menu in response to the received gesture and receiving a selection of an event from the event context menu, the selected event corresponding to a second graphical object. The method also includes replacing, on the multi-touch display, the first graphical object with the second graphical object to confirm the event selection.

Abstract: Systems and methods are provided for syndicating slideshow content in a web feed. Data is obtained for a content feed associated with a web page in response to a request by a user of a content feed reader. A slideshow within the web page is identified based on analysis of the obtained data according to a schema definition for syndication of slideshow content. A first set of properties for the slideshow is extracted from the obtained data, based on the schema definition. A set of slides of the slideshow is identified based on the first set of properties. A second set of properties for the set of slides is also extracted from the obtained data. The content feed including the set of slides of the slideshow and one or more properties of the second set are displayed to the user via the content feed reader.

Abstract: Systems and methods are disclosed for electronic distribution of electronic content. The method includes receiving, from an advertiser or content provider, a request to transmit electronic content to a plurality of electronic devices of a desired subset of individuals, wherein the electronic content relates to a target location of the advertiser or content provider; identifying a geographical zone extending between an inner boundary around the target location and an outer boundary around the target location; receiving an indication that one of the plurality of electronic devices of the subset of individuals is present in the geographical zone based on determining that the one of the plurality of electronic devices is located within the outer boundary but not within the inner boundary; and transmitting electronic content to the electronic device of the one of the subset of individuals in the population, the electronic content relating to the target location.

Abstract: The present disclosure relates to systems and methods customizing electronic communications. A future event associated with a first user may be determined, and a second user that is associated with the first user may be identified. A plurality of communications involving the first user and the second user may be analyzed. A selection rule may be applied based on the analyzed plurality of communications, the selection rule identifying content from the database. Content from the database may be selected based on the application of the selection rule. An electronic message may be provided to the first user identifying the future event, and the selected content may be provided to the first user.

Abstract: Systems and methods are provided for timing message notifications to be provided to mobile device users based on their respective geographic locations with respect to a targeted content area. The timing of message notifications may be controlled in order to optimize the chances of delivering targeted content to a mobile device user based on the current geographic location of the user's device relative to a targeted content area. As the particular client application may not be actively executing at a time when the user's device happen to be located within a targeted content area, a general message notification sent to the user's device, which may be displayed at any time, may increase the likelihood that the user will launch the client application when it is not already executing at the device and thereby, allow targeted content to be delivered to the user's mobile device at the appropriate time and location.

Abstract: A system and method are disclosed that enable an email service provider to implement an email forwarding service without losing associated page views. In one embodiment, rather than forwarding the entire email message, the email forwarding service generates a summary email message, and sends this summary email message to the forwarding email address pre-specified by the subscriber. This summary email message includes a link that is selectable by the user to view the original email message on a web site of the email service provider. Thus, even if the forwarding email address is hosted externally, the subscriber still views the full email message on a web site of the provider of the email forwarding service.

Abstract: Systems and methods are disclosed for enabling sharing of audio feeds. One method includes receiving, from a user over a network, a request to add an audio feed to a collection managed by the user; storing, in a database, a URL of the audio feed in relation to the collection; receiving, from the user over the network, a request to share the collection; and generating an RSS URL of the collection by searching the database for URLs of audio feeds stored in relation to the collection.

Abstract: Access to content may be enabled by receiving an instruction indicating a client request to access content, accessing a list of content sources capable of rendering the content for which access is requested by the client, determining a performance metric for at least two of the content sources, and selecting among the content sources based on the performance metric to identify a content source to be accessed by the client.