Abstract: A system and method is provided that displays cursors for street level images, where the cursor changes appearance based on the objects in the image, such as the geographic distance between the objects and the camera position and the surface of the objects. For example, the cursor may appear to lie flat against the objects in the image change size based on the distance between the camera and object's surface.

Abstract: Implementations described herein utilize an independent server for facilitating secure exchange of data between multiple disparate parties. The independent server receives client data, via an automated assistant application executing at least in part at a client device, that is to be transmitted to a given third-party application. The independent server processes the client data, using a first encoder-decoder model, to generate opaque client data, and transmits the opaque client data to the given third-party application and without transmitting any of the client data. Further, the independent server receives response data, via the given third-party application, that is generated based on the opaque client data and that is to be transmitted back to the client device. The independent server processes the response data, using a second encoder-decoder model, to generate opaque response data, and transmits the opaque response data to the client device and without transmitting any of the response data.

Abstract: A computer-implemented method for decomposing videos into multiple layers (212, 213) that can be re-combined with modified relative timings includes obtaining video data including a plurality of image frames (201) depicting one or more objects. For each of the plurality of frames, the computer-implemented method includes generating one or more object maps descriptive of a respective location of at least one object of the one or more objects within the image frame. For each of the plurality of frames, the computer-implemented method includes inputting the image frame and the one or more object maps into a machine-learned layer Tenderer model. (220) For each of the plurality of frames, the computer-implemented method includes receiving, as output from the machine-learned layer Tenderer model, a background layer illustrative of a background of the video data and one or more object layers respectively associated with one of the one or more object maps.

Abstract: Systems and methods for routing in mixture-of-expert models. In some aspects of the technology, a transformer may have at least one Mixture-of-Experts (“MoE”) layer in each of its encoder and decoder, with the at least one MoE layer of the encoder having a learned gating function configured to route each token of a task to two or more selected expert feed-forward networks, and the at least one MoE layer of the decoder having a learned gating function configured to route each task to two or more selected expert feed-forward networks.

Abstract: Methods, systems, and computer readable media related to generating a combined search query based on search parameters of a current search query of a user and search parameters of one or more previously submitted search quer(ies) of the user that are determined to be of the same line of inquiry as the current search query. Two or more search queries may be determined to share a line of inquiry when it is determined that they are within a threshold level of semantic similarity to one another. Once a shared line of inquiry has been identified and a combined search query generated, users may interact with the search parameters and/or the search results to update the search parameters of the combined search query.

Abstract: The present disclosure is generally related to a data processing system to process data packets in a voice activated computer network environment. The data processing system can improve the efficiency of the network by generating non-video data responses to voice commands received from a client device if a display associated with a client device is in an OFF state. A digital assistant application executed on the client device can send to the data processing system client device configuration data, which includes the state of the display device, among status data of other components of the client device. The data processing system can receive a current volume of speakers associated with the client device, and set a volume level for the client device based on the current volume level and a minimum response volume level at the client device.

Abstract: Systems, methods and apparatus for invoking actions at a second user device from a first user device. A method includes determining that a first user device has an associated second user device; accessing specification data that specifies a set of user device actions that the second user device is configured to perform; receiving command inputs for the first user device; for each command input, determining whether the command input resolves to one of the user device actions; for each command input not determined to resolve any of the user device actions, causing the command input to be processed at the first user device; and for each command input determined to resolve one of the user device actions causing the first user device to display in a user interface a dialog by which a user may either accept or deny invoking the user device action at the second user device.

Abstract: Implementations can reduce the time required to obtain responses from an automated assistant through proactive caching, locally at a client device, of proactive assistant cache entries—and through on-device utilization of the proactive assistant cache entries. Different proactive cache entries can be provided to different client devices, and various implementations relate to technique(s) utilized in determining which proactive cache entries to provide to which client devices. In some of those implementations, in determining which proactive cache entries to provide (proactively or in response to a request) to a given client device, a remote system selects, from a superset of candidate proactive cache entries, a subset of the cache entries for providing to the given client device.

Abstract: Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

Abstract: Implementations relate to processing media content, and/or associated metadata, to classify the media content into a first category, of a plurality of predefined categories. Versions of those implementations further relate to extracting target content from the media content; generating, based on the extracted target content, an action that corresponds to an application; and generating, based on the generated action, a selectable suggestion including a textual portion that describes the action. Some of those versions further relate to causing the selectable suggestion to be displayed at a display of a client device, along with rendering of the media content. The selectable suggestion, when selected, causes the application to perform the action. The target content can be extracted based on the first category and can be extracted based on the first category in response to the media content being classified into the first category.

Abstract: Systems and methods are described for providing an interface and facilitating selection of sponsored content networks that provide sponsored content items. This may include providing, by a mediation server, a user interface to a publisher server, the user interface configured to provide access to data stored on the mediation server; receiving a metric associated with a rule for filtering content items associated with the publisher; applying the metric to a content network list associated with the publisher using the user interface to generate an updated content network list; and transmitting mediation code including the updated content network list to the publisher server, wherein the mediation code, when executed by a user device, (i) causes the user device to control display of content items according to the updated content network list and (ii) allows the user device to flag at least one content item for modifying the updated content network list.

Abstract: A motion vector for a current block of a current frame is decoded from a compressed bitstream. A location of a reference block within an un-generated reference frame is identified. The reference block is generated using a forward reference frame and a backward reference frame without generating the un-generated reference frame. The reference block is generated by identifying an extended reference block by extending the reference block at each boundary of the reference block by a number of pixels related to a filter length of a filter used in sub-pixel interpolation; and generating pixel values of only the extended reference block by performing a projection using the forward reference frame and the backward reference frame without generating the whole of the un-generated reference frame. The current block is then decoded based on the reference block and the motion vector.

Abstract: Provided are computing systems, methods, and platforms for generating training and testing data for machine-learning models. The operations can include receiving signal extraction information that has instructions to query a data store. Additionally, the operations can include accessing, using Structured Query Language (SQL) code generated based on the signal extraction information, raw data from the data store. Moreover, the operations can include processing the raw data using signal configuration information to generate a plurality of signals. The signal configuration information can have instructions on how to generate the plurality of signals from the raw data. Furthermore, the operations can include joining, using SQL code, the plurality of signals with a first label source to generate training data and testing data. Subsequently, the operations can include processing the training data and the testing data to generate the input data. The input data being an ingestible for a machine-learning pipeline.

Abstract: A wearable device can include a first sensor configured to sense first data, a second sensor configured to sense second data, an energy utilization of the first sensor being less than an energy utilization of the second sensor, and a processor configured to perform a comparison between the first data and a threshold value, if the comparison passes the threshold value, cause the second sensor to sense the second data and process the second data, and if the comparison fails the threshold value, cause the second sensor not to sense the second data.

Abstract: A display device based on micro light emitting diodes (microLEDs) includes a plurality of chiplets. Each chiplet includes one or more raxels, each raxel including a plurality of microLEDs supported on a substrate. The chiplet also includes a micro integrated circuit (microIC) electronically connected with the one or more raxels. MicroIC includes a plurality of interconnects supported on a backplane such that, when connected with the raxel, microIC may be used to electrically drive each one of the MicroLED of the raxel. In an embodiment, a plurality of chiplets are disposed on a display substrate to for an auto-view horizontal parallax only 3D display.

Abstract: The present disclosure is directed to methods and systems for generating a geodetic datum. The geodetic datum can establish a coordinate system and/or a set of reference points that describe the respective locations of a portion or all of Earth and/or objects located thereon. In general, a computing system can generate the geodetic datum using various sensor data from one or more sources including: satellite imagery, aerial imagery, aerial light detection and ranging data (LIDAR), ground-level imagery, ground-level LIDAR, and/or other forms of sensor data. This data can be used as a reference dataset that can be combined with additional sensor data (e.g., a second dataset) to determine correspondences between overlapping areas represented in the datasets. Continuing this process for regions that collectively cover the Earth can be used to create a geodetic datum of the entire Earth, without using a mathematic abstraction of the Earth surface.

Abstract: For a coding block of an image, a luma prediction block is generated, a luma residual block is generated, a quantized luma block is generated after transforming the luma residual block using a luma transform type, and the quantized luma block is entropy encoded. A chroma prediction block is generated, a chroma residual block is generated, an initial chroma transform type for the chroma residual block is determined as the luma transform type, a quantized chroma block is generated using the chroma residual block transformed by a final chroma transform type, and the quantized chroma block is entropy encoded. When the initial chroma transform type is other than a default transform type, the final chroma transform type is the initial chroma transform type or the default transform type, and quantized coefficients of the quantized chroma block depend upon quantized coefficients of the quantized luma block.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for handing off a user conversation between computer-implemented agents. One of the methods includes receiving, by a computer-implemented agent specific to a user device, a digital representation of speech encoding an utterance, determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with another computer-implemented agent, and establishing, by the computer-implemented agent, a communication between the other computer-implemented agent and the user device.

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.