Abstract: Disclosed here are methods and systems that relate to determining a moving direction of a mobile device user. The methods and systems relate to using an inertial navigation system such as an accelerometer and gyroscope to aid in the determination of the moving direction of the user. The methods and systems may receive an acceleration reading associated with the mobile device, and determine a step frequency of the user based on the acceleration reading. The methods and systems may determine a theoretical model to fit the acceleration reading, and may determine the moving direction of the user based on the theoretical model.

Abstract: In one implementation, a computer-implemented method includes receiving at a server a request from an advertiser to target an ad to users of a computer-implemented social network, the request comprising data representing characteristics of the users that the advertiser desires to target. The method further includes ranking the users based on how similar the users' characteristics are to the received characteristics and an influence score for each user that indicates how influential the user is within the social network. The method also includes scoring the advertiser's request based on a bid from the advertiser for an opportunity to display the ad to one or more of the users and assigning the opportunity to display the ad to the one or more users based on a correlation between a score of the advertiser's request and one or more rankings of the one or more users.

Abstract: A computer-implemented method can include receiving, at a computing device having one or more processors, a plurality of textual inputs. Each of the textual inputs can be received in association with an input field. The method can also include receiving, at the computing device, a plurality of unique identifiers. Each unique identifier can be associated one of the plurality of textual inputs and identify a type of the input field. The method can also include building, at the computing device, a language model associated with each particular unique identifier. Each language model can be based on the textual inputs associated with the particular unique identifier. Further, the method can include storing, at the computing device, the language models such that each particular language model can be retrieved based on its associated particular unique identifier.

Abstract: A computer-implemented technique for feature extraction includes obtaining an electronic image of an object and performing an edge detection algorithm on the electronic image. The technique further includes performing an edge pooling algorithm and sampling the electronic image edge patches, color patches and texture patches. A set of patches is selected from the edge patches, color patches and texture patches by selecting an (ith+1) patch to be within the set of patches based on a Euclidean distance from an ith patch of the set of patches for each of the set of edge patches, the set of color patches and the set of texture patches. A part selection algorithm and a part pooling algorithm is performed to obtain parts that are registered to the object.

Abstract: A surveillance system is provided that includes at least one sensor disposed in a security area of a surveillance region to sense an occurrence of a potential security breach event; a plurality of cameras is disposed in the surveillance region; at least one camera thereof has a view of the security area and can be configured to automatically gather biometric information concerning at least one subject person in the vicinity of the security area in response to the sensing of a potential security breach event; one or more other of the plurality of cameras can be configured to search for the at least one subject person; a processing system is programmed to produce a dossier corresponding to the at least one subject person to match biometric information of one or more persons captured by one or more of the other cameras with corresponding biometric information in the dossier.

Abstract: Disclosed here are methods and systems that relate to determining an orientation of an object. The orientation of the object may be represented by an Euler angle which identifies a rotation of the object from a reference frame. The methods and systems may rely on readings collected from two or more barometric pressure sensors to estimate an altitude difference between the pressure sensors. The methods and systems may calculate the Euler angle based on the altitude difference.

Abstract: Aspects of the present disclosure provide techniques for constructing a scalable model of an indoor space using crowd-sourced inertial navigation system (INS) signals from mobile devices. By tracking INS signals from a number of participating users, the user's trajectories can be estimated as they move their mobile devices indoors. The estimated trajectories can be scored against similar routes taken by other users. Routes with the highest scores are then laid out over a map of the indoor space to identify areas most often traveled to and from landmarks and distances between the landmarks.

Abstract: Disclosed here are methods and systems that relate to determining a moving direction of a mobile device user. The methods and systems relate to using an inertial navigation system such as an accelerometer and gyroscope to aid in the determination of the moving direction of the user. The methods and systems may receive an acceleration reading associated with the mobile device, and determine a step frequency of the user based on the acceleration reading. The methods and systems may determine a theoretical model to fit the acceleration reading, and may determine the moving direction of the user based on the theoretical model.

Abstract: Disclosed here are methods and systems that relate to determining a moving direction of a mobile device user. The methods and systems relate to using an inertial navigation system such as an accelerometer and gyroscope to aid in the determination of the moving direction of the user. The methods and systems may receive an acceleration reading associated with the mobile device, and determine a step frequency of the user based on the acceleration reading. The methods and systems may determine a theoretical model to fit the acceleration reading, and may determine the moving direction of the user based on the theoretical model.

Abstract: Disclosed here are methods and systems that relate to determining a moving direction of a mobile device user. The methods and systems relate to using an inertial navigation system such as an accelerometer and gyroscope to aid in the determination of the moving direction of the user. The methods and systems may receive an acceleration reading associated with the mobile device, and determine a step frequency of the user based on the acceleration reading. The methods and systems may determine a theoretical model to fit the acceleration reading, and may determine the moving direction of the user based on the theoretical model.

Abstract: Systems and methods for detecting an attitude of a device are disclosed. The system includes a processing system including at least a sensor processor and an application processor, which are distinct. The system further includes a memory system including one or more computer-readable media. The computer-readable media contains instructions that, if executed by the processing system, cause the system to perform operations. The operations include executing an application using the application processor, and receiving raw sensor readings from one or more sensors, using the sensor processor. The operations also include determining, using the sensor processor, a processed sensor metric comprising attitude data, and transmitting the processed sensor metric to the application.

Abstract: Aspects of the present disclosure provide techniques for constructing a scalable model of an indoor space using crowd-sourced inertial navigation system (INS) signals from mobile devices. By tracking INS signals from a number of participating users, the user's trajectories can be estimated as they move their mobile devices indoors. The estimated trajectories can be scored against similar routes taken by other users. Routes with the highest scores are then laid out over a map of the indoor space to identify areas most often traveled to and from landmarks and distances between the landmarks.

Abstract: A surveillance system is provided that includes at least one sensor disposed in a security area of a surveillance region to sense an occurrence of a potential security breach event; a plurality of cameras is disposed in the surveillance region; at least one camera thereof has a view of the security area and can be configured to automatically gather biometric information concerning at least one subject person in the vicinity of the security area in response to the sensing of a potential security breach event; one or more other of the plurality of cameras can be configured to search for the at least one subject person; a processing system is programmed to produce a dossier corresponding to the at least one subject person to match biometric information of one or more persons captured by one or more of the other cameras with corresponding biometric information in the dossier.

Abstract: A surveillance system is provided that includes at least one sensor disposed in a security area of a surveillance region to sense an occurrence of a potential security breach event; a plurality of cameras is disposed in the surveillance region; at least one camera thereof has a view of the security area and can be configured to automatically gather biometric information concerning at least one subject person in the vicinity of the security area in response to the sensing of a potential security breach event; one or more other of the plurality of cameras can be configured to search for the at least one subject person; a processing system is programmed to produce a dossier corresponding to the at least one subject person to match biometric information of one or more persons captured by one or more of the other cameras with corresponding biometric information in the dossier.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for analyzing quality of user-generated content involve identifying interactions between users through an electronic network and assigning a weighting factor to each interaction representing a quality of the interaction. A user credential score is generated for each user based on the weighting factors for each interaction. The user credential scores are stored in association with a user identifier on a computer-readable storage device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enhanced parallel latent Dirichlet allocation (PLDA+). A PLDA+ system is a system of multiple processors that are configured to generate topics from multiple documents. The multiple processors are designated as two types: document processors and matrix processors. The documents are distributed among the document processors. Generated topics are distributed among the matrix processors. Tasks performed on the document processors and matrix processors are segregated into two types of tasks: computation-bound tasks and communication-bound tasks. Computation-bound tasks are CPU intensive tasks; communication-bound tasks are network intensive tasks. Data placement and pipeline strategies are employed such that the computation-bound tasks and the communication-bound tasks are distributed to the processors in a balanced manner, and performed in parallel.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for labeling images. In one aspect, a method includes automatically identifying an object in an image using a deep model-based and data-driven hybrid architecture.

Abstract: Systems, methods, and machine-readable media for monitoring the locations of a number of entities are provided. The system may be configured to track the locations of a multitude of entities by grouping entities together into clusters of entities based on their geographic proximity and trajectories. A member of a cluster may be identified as a leader or a follower. The system may receive a number of location reports for the entities and update the locations of the entities based on whether the entity is a leader or a follower. For example, the system may update a back-end location database with the location information for a leader while location updates for followers may be converted into locations that are relative to the corresponding leader's and cached at the system.

Abstract: A computer-implemented technique for feature extraction includes obtaining an electronic image of an object and performing an edge detection algorithm on the electronic image. The technique further includes performing an edge pooling algorithm and sampling the electronic image edge patches, color patches and texture patches. A set of patches is selected from the edge patches, color patches and texture patches by selecting an (ith+1) patch to be within the set of patches based on a Euclidean distance from an ith patch of the set of patches for each of the set of edge patches, the set of color patches and the set of texture patches. A part selection algorithm and a part pooling algorithm is performed to obtain parts that are registered to the object.

Abstract: Systems and methods for detecting an attitude of a device are disclosed. The system includes a processing system including at least a sensor processor and an application processor, which are distinct. The system further includes a memory system including one or more computer-readable media. The computer-readable media contains instructions that, if executed by the processing system, cause the system to perform operations. The operations include executing an application using the application processor, and receiving raw sensor readings from one or more sensors, using the sensor processor. The operations also include determining, using the sensor processor, a processed sensor metric comprising attitude data, and transmitting the processed sensor metric to the application.