Abstract: A method includes receiving an input video stream and scaling the input video stream into two or more spatial layers. For each spatial layer, the method also includes generating a temporal layer prediction pattern by: obtaining a temporal base layer for a corresponding spatial layer; identifying, based on the temporal base layer, a plurality of temporal layers and a plurality of temporal time slots during a temporal period; and aligning the temporal base layer for the corresponding spatial layer with one of the temporal time slots during the temporal period. Each temporal time slot is associated with one of the temporal base layer or one of the plurality of temporal layers for the corresponding spatial layer. The temporal base layer for each corresponding spatial layer is aligned with a different temporal time slot than each other temporal base layer for each other corresponding spatial layer.

Abstract: Techniques and apparatuses are described that implement a smartphone-based radar system capable of detecting user gestures using coherent multi-look radar processing. Different approaches use a multi-look interferometer or a multi-look beamformer to coherently average multiple looks of a distributed target across two or more receive channels according to a window that spans one or more dimensions in time, range, or Doppler frequency. By coherently averaging the multiple looks, a radar system generates radar data with higher gain and less noise. This enables the radar system to achieve higher accuracies and be implemented within a variety of different devices. With these accuracies, the radar system can support a variety of different applications, including gesture recognition or presence detection.

Abstract: The present disclosure can select a communication identifier for a device of a content provider. A system receives a request for content for display. The system identifies a content item responsive to the request. The system determines a feature of the computing device and a feature of the content item. The system selects a type of phone number for a content provider of the content item based on both the feature of the computing device and the feature of the content item. The system identifies a phone number for the content item corresponding to the type of phone number. The system transmits the phone number for the content item for display via a computing device. The system identifies, responsive to an indication to establish a communication corresponding to the phone number for the content item, a phone number for the device of the content provider.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for receiving a plurality of web search results, the plurality of web search results generated from a web corpus; including an interface element in the plurality of web search results, the interface element specifying a particular native application and configured to, when selected at the user device, cause a plurality of native application search results responsive to the search query be provided to the user device, each native application search result deeplinking to the particular native application; providing the interface element and the plurality of web search results to the user device; receiving an indication of a selection of the interface element from the user device; and in response to receiving the indication, providing the plurality of native application search results for the particular native application to the user device.

Abstract: Selecting payment instruments for proxy card transactions comprises associating a plurality of financial accounts with a user proxy account; establishing a model for the user account based on configuration data received from a user, the model comprising identification of a particular financial account to use as a backing instrument for a transaction; receiving data associated with a pending transaction regarding the pending transaction; identifying a financial account to use as a backing instrument for the pending transaction based on a comparison of the model with the pending transaction data; receiving a selection of an alternate financial account to use instead of the identified financial account as the backing instrument; modifying the model account based on the selection of the alternate financial account and the data associated with the pending transaction; and utilizing the modified model in a subsequent selection of a financial account for a subsequent transaction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, and including a method for creating content. The method comprises receiving an indication to promote a published content item, and parsing content in the published content item to identify candidate text/video/images for inclusion in a creative. The method further comprises assigning ranks to the candidate text/video/images based on one or more criteria. The method further comprises identifying a plurality of creative formats. The method further comprises, for each of the identified creative formats, identifying a corresponding set of text/video/images from the candidate text/video/images for inclusion in a candidate creative formatted in accordance with a given creative format and based at least in part on the ranked candidate text/video/images.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

Abstract: A re-programmable wireless device can store data securely and use near field communication (NFC) to exchange functionality data and/or program code from a central server system through a mobile device. A user requests a new re-programmable wireless device or a new re-programmable wireless device function via an application on the mobile device. The central server system transmits program code and a public key used to identify the re-programmable wireless device to the mobile device, which functions as a pass-through conduit for the information, storing it until the devices are synced. A NFC communication channel is created, and the mobile device authenticates the re-programmable wireless device by cross-referencing the public key received from the central server system with the public key transmitted by the re-programmable wireless device once the communication channel is established.

Abstract: A method for identifying codemixed text includes receiving codemixed text and segmenting the codemixed text into a plurality of tokens. Each token includes at least one character and is delineated from any adjacent tokens by a space. For each token of the codemixed text, the method also includes extracting features from the token and predicting a probability distribution over possible languages for the token using a language identifier model configured to receive the extracted features from the token as feature inputs. The method also includes assigning a language to each token of the codemixed text by executing a greedy search on the probability distribution over the possible languages predicted for each respective token.

Abstract: Systems and methods for time proximity based map user interactions with a user interface are provided. In one example implementation, a method includes providing for display a user interface on a display device. The user interface can display imagery of a geographic area. The method can include obtaining data indicative of a relevant time for contextual information. The method can include obtaining contextual information associated with the geographic area. The method can include obtaining a configuration for a user interface element associated with the time based contextual information based at least in part on time proximity of the contextual information to the relevant time. The method can include providing for display the user interface element based at least in part on the configuration.

Abstract: Systems and methods for entity-based searching with content selection include receiving a search query and determining that the search query corresponds to a search entity. The search entity may be associated with an online action, thereby forming an entity-action pair. Auction parameters that specify the entity-action pair may be used to select third-party content. A visual layout for the third-party content may be generated based on the relationship between a search query and the entity-action pair and used as part of the presentation of the third-party content on a search result screen.

Abstract: Keyword suggestions that are category-aware (and field-proven) may be used to help advertisers better target the serving of their ads, and may reduce unused ad spot inventory. The advertiser can enter ad information, such as a creative, a landing Webpage, other keywords, etc. for example. A keyword facility may use this entered ad information as seed information to infer one or more categories. It may then request that the advertiser confirm or deny some basic feedback information (e.g., categories, Webpage information, etc.). For example, an advertiser may be provided with candidate categories and may be asked to confirm (e.g., using checkboxes) which of the categories are relevant to their ad. Keywords may be determined using at least the categories. The determined keywords may be provided to the advertiser as suggested keywords, or may automatically populate ad serving constraint information as targeting keywords.

Abstract: A method for presenting content items includes receiving, by a user device, a request for a media content item hosted by a content sharing platform, and providing, by the user device, a graphical user interface (GUI) comprising a first GUI portion having a first media player to play the requested media content item, and a second GUI portion having a second media player to play an additional media content item associated with a particular portion of the requested media content item. The method further includes in response to the first media player beginning to play the particular portion of the requested media content item, causing the second media player to play the additional media content item.

Abstract: A system and method are disclosed for motion-based feature correspondence. A method may include detecting a first motion of a first feature across two or more first frames of a first video clip captured by a first video camera and a second motion of a second feature across two or more second frames of a second video clip captured by a second video camera. The method may further include determining, based on the first motion in the first video clip and the second motion in the second video clip, that the first feature and the second feature correspond to a common entity, the first motion in the first video clip and the second motion in the second video clip corresponding to one or more common points in time in the first video clip and the second video clip.

Abstract: Systems and methods described herein may relate to image transformation utilizing a plurality of deep neural networks. An example method includes receiving, at a mobile device, a plurality of image processing parameters. The method also includes causing an image sensor of the mobile device to capture an initial image and receiving, at a coefficient prediction neural network at the mobile device, an input image based on the initial image. The method further includes determining, using the coefficient prediction neural network, an image transformation model based on the input image and at least a portion of the plurality of image processing parameters. The method additionally includes receiving, at a rendering neural network at the mobile device, the initial image and the image transformation model. Yet further, the method includes generating, by the rendering neural network, a rendered image based on the initial image, according to the image transformation model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, and including a computer-implemented method for providing creatives. The method comprises identifying, using one or more processors, a creative for processing, the creative including a title portion and a body portion, where the body portion includes a visual uniform resource locator (URL), the visual URL comprising a visual portion and a link to a resource. The method further comprises evaluating the visual URL for inclusion in the title portion, including determining when promotion of the visual URL satisfies one or more promotion criterion, and if so, promoting the visual URL for inclusion in the title portion. The method further comprises providing the creative including the title portion with the promoted visual URL.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to synthetic call status updates. In some implementations, a method includes determining, by a task manager module, that a triggering event has occurred to provide a current status of a user call request. The method may then determine, by the task manager module, the current status of the user call request. A representation of the current status of the user call request is generated. Then, the generated representation of the current status of the user call request is provided to the user.

Abstract: A computer-implemented method includes running a background element that is an invisible element in a browser application, where the background element includes a declared association with an application and includes instructions related to one or more visible elements of the application in the browser application and executing the instructions on the background element to perform a function related to the one or more visible elements of the application in the browser application.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes generating, by a speech recognition system, a matrix from a predetermined quantity of vectors that each represent input for a layer of a neural network, generating a plurality of sub-matrices from the matrix, using, for each of the sub-matrices, the respective sub-matrix as input to a node in the layer of the neural network to determine whether an utterance encoded in an audio signal comprises a keyword for which the neural network is trained.

Abstract: Systems, methods and computer readable media for live interactions in persistent conversations are described. In some implementations, a method can include receiving a communication message sent from a first user to a second user, wherein the communication message includes initiation of a live interaction. The method can also include generating a live interaction user interface element for display as part of a persistent conversation interface. The method can further include storing a representation of the live interaction in a conversation content section of a persistent conversation object when the live interaction ends. The method can include updating conversation state information of the persistent conversation object to reflect the receiving of the communication message and the storing of the representation.