A first video stream comprising a first image of a first participant of a virtual meeting, a second image of a second participant, and a third image of a third participant are received from a first client device connected to a virtual meeting platform. It is determined whether an image combining condition is satisfied. Responsive to determining that the image combining condition is satisfied with respect to the first image and the second image, a first screen tile comprising the first image and the second image is generated. A first size of the first screen tile is defined based on a number of images comprised by the first screen tile. A second screen tile comprising the third image is generated. A virtual meeting user interface comprising the first screen tile and the second screen tile is provided for presentation on a second client device connected to the virtual meeting platform.
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
2.
GENERATING CUSTOMIZED CONTENT DESCRIPTIONS USING ARTIFICIAL INTELLIGENCE
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating descriptions of digital components. In one aspect, a method includes receiving data indicating a query received from a client device of a user. An initial digital component is obtained. Search history data that includes a set of related past queries received from the user is obtained. Updated text related to the first resource is generated by conditioning a language model with one or more contextual inputs that cause the language model to generate one or more outputs that include the updated text, the one or more contextual inputs characterizing one or more of the first query, data related to the initial digital component, the sequence of related past queries, or one or more tasks to be performed by the language model. An updated digital component that depicts the updated text is generated and provided.
Techniques for generating replication data from a data source to be stored in a target location are described herein. A computing system can receive, from a client device, client requirements associated with a dataflow from the data source to the target location. The client requirements can include an expected data freshness value and an expected data query latency value. Additionally, the computing system can process the expected data freshness value with one or more machine-learned models to generate an extraction framework for extracting data from the data source. Moreover, the computing system can process the expected data query latency value with the one or more machine-learned models to generate a loading framework for loading data to the target location. Furthermore, the computing system can copy the replication data from the data source to the target location based on the extraction framework and the loading framework.
G06F 16/27 - Replication, distribution or synchronisation of data between databases or within a distributed database systemDistributed database system architectures therefor
4.
Systems and Methods for Progressive Rendering of Refinement Tiles in Images
A computer-implemented method is provided. The method includes receiving, via a computing device, a plurality of bytes of an encoded image, wherein the encoded image comprises a salient portion. The method further includes determining a bounding region for the encoded image, wherein the bounding region is indicative of a location of the salient portion in the encoded image. The method also includes progressively rendering a decoded version of the encoded image, wherein the progressively rendering comprises rendering a high resolution version of the bounding region, and a low resolution version of a portion outside the bounding region.
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/46 - Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]Salient regional features
G06V 10/70 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning
H04N 19/136 - Incoming video signal characteristics or properties
H04N 19/167 - Position within a video image, e.g. region of interest [ROI]
H04N 23/61 - Control of cameras or camera modules based on recognised objects
H04N 23/63 - Control of cameras or camera modules by using electronic viewfinders
5.
GENERATING A PERSONAL DATABASE ENTRY FOR A USER BASED ON NATURAL LANGUAGE USER INTERFACE INPUT OF THE USER AND GENERATING OUTPUT BASED ON THE ENTRY IN RESPONSE TO FURTHER NATURAL LANGUAGE USER INTERFACE INPUT OF THE USER
Some implementations are directed to generating a personal database entry for a user based on free-form natural language input formulated by the user via one or more user interface input devices of a computing device of the user. The generated personal database entry may include one or more terms of the natural language input and descriptive metadata determined based on one or more terms of the natural language input and/or based on contextual features associated with receiving the natural language input. Some implementations are directed to generating, based on one or more personal database entries of a user, output that is responsive to further free-form natural language input of the user. For example, one or more entries that are responsive to further natural language input of the user can be identified based on matching content of those entries to one or more search parameters determined based on the further input.
Example embodiments of the present disclosure provide for an example method including maintaining a current version info list including version info tuples for software layers. The example method includes, upon receipt of a request for a registered version key, performing a comparison algorithm to authenticate a requested version info list including a number of version info tuples associated with software layers. The tuples can include a security version number (SVN) and a security context string for each software layer. The requested version info list can be authenticated using the comparison algorithm to determine that the requested version info list includes version info tuples with higher SVNs than the current version info list. Responsive to authenticating the requested version info list, the method include providing a portion of the requested version info list as input into a key derivation function (KDF) and obtaining a device requested version key as output.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
G06F 21/64 - Protecting data integrity, e.g. using checksums, certificates or signatures
7.
ADAPTIVE HOWLING SUPPRESSION FOR ACTIVE NOISE CONTROL SYSTEMS
Adaptive howling suppression is provided for active noise control (ANC) systems of wearable audio components (WACs), such as earbuds, based on detecting whether the WACs are presently being worn. Upon first detecting howling, embodiments can pre-suppress the howling audio signature by reducing ANC output. Then, embodiments detect whether the WAC is presently on-ear (worn) or off-ear and attempt to fully suppress the howling using different parameters, based on this detection. For example, if on-ear, embodiments use on-ear tuning settings to cycle through a set of suppression stages until ANC output can be restored without howling; if off-ear, embodiments use off-ear tuning settings to cycle through the set of suppression stages until ANC output can be restored without howling. Once ANC output can be restored without howling, the system can be released to a normal idle state.
G10K 11/175 - Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effectsMasking sound
An image capture system includes a light detection and ranging (LIDAR) device which captures images of an environment while rotating and a plurality of cameras, disposed separately from the LIDAR device, each including a rolling shutter sensor and each capturing images of the environment. The plurality of cameras include a first camera disposed to face in a first direction and a second camera disposed to face in a second direction. A time at which the first camera captures a first image is synchronized with a time at which the LIDAR device captures a second image when the LIDAR device rotates to face in the first direction, and a time at which the second camera captures a third image is synchronized with a time at which the LIDAR device captures a fourth image when the LIDAR device rotates to face in the second direction.
A word line regulator that can control an SRAM cell during a write process is disclosed. The SRAM cell is coupled to bit lines that are driven using a reduced voltage in order to conserve power. The SRAM cell includes a latch that is powered by a power supply in a power domain that is different from the bit lines. The word line regulator is configured to output a voltage that is based on the different power domains to ensure the proper operation of transistors in the SRAM cell during the write process.
G09G 3/32 - Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix using controlled light sources using electroluminescent panels semiconductive, e.g. using light-emitting diodes [LED]
G09G 3/20 - Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix
10.
CALIBRATION ASSEMBLY FOR TELEPRESENCE VIDEOCONFERENCING SYSTEMS
Techniques include a calibration assembly for a telepresence system that includes a stereoscopic display and a set of cameras. The calibration assembly may include at least one chart having chart markers, a mirror having mirror markers, and a processor. An example calibration assembly has three charts and the mirror attached to one of the charts. During calibration, the display is configured to display a set of display markers that are imaged in the mirror. Each camera forms a respective image of the set of chart markers, the set of mirror markers, and the set of display markers. The processing circuitry then determines the poses of the cameras with respect to the display based on the images of the set of chart markers, the set of mirror markers, and the set of display markers.
Systems and methods for user-specific content generation can leverage parameter tuning based on user feedback data to tune a set of parameters for conditioning a machine-learned content generation model for the content generation. The set of parameters can be processed with the machine-learned content generation model to generate a model-generated content item that is associated with user tastes and interests. The parameter tuning can include processing user interactions associated with the model-generated content item to adjust the set of parameters.
Provided is an efficient approach to establish a foundational video-text model for tasks including open-vocabulary video classification, text-to-video retrieval, video captioning and video question-answering. Some example implementations include a model which can be referred to as VideoCoCa. Example implementations reuse a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with little or minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules (for example, cross-frame attention layer or perceiver resampler) and finetune the modified architecture on video-text data, aspects of the present disclosure leverage findings that the generative attentional pooling and contrastive attentional pooling layers in the image-text CoCa design are instantly adaptable to “flattened frame embeddings”, yielding a strong zero-shot transfer baseline for many video-text tasks.
G06V 20/40 - ScenesScene-specific elements in video content
G06F 16/583 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
13.
GENERATING INTEGRATED CIRCUIT PLACEMENTS USING NEURAL NETWORKS
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a computer chip placement. One of the methods includes training, through reinforcement learning, a node placement neural network that is configured to, at each of a plurality of time steps, receive an input representation comprising data representing a current state of a placement of a netlist of nodes on a surface of an integrated circuit chip as of the time step and process the input representation to generate a score distribution over a plurality of positions on the surface of the integrated circuit chip.
G06F 30/392 - Floor-planning or layout, e.g. partitioning or placement
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Methods, systems, and apparatus, including computer-readable media, are described for processing an input image using a convolutional neural network (CNN). The CNN includes a sequence of layer blocks. Each of a first subset of the layer blocks in the sequence is configured to perform operations that include: i) receiving an input feature map for the layer block, ii) generating an expanded feature map from the input feature map using a group convolution, and iii) generating a reduced feature map from the expanded feature map. The input feature map is an h w feature map with c1 channels. The expanded feature map is an h w feature map with c2 channels, whereas the reduced feature map is an h w feature map with c1 channels. C2 is greater than c1. An output feature map is generated for the layer block from the reduced feature map.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
G06V 10/94 - Hardware or software architectures specially adapted for image or video understanding
15.
SENDING MESSAGES FROM SMART SPEAKERS AND SMART DISPLAYS VIA SMARTPHONES
Techniques are described herein for using a smart device such as a standalone assistant-centric interactive speaker and/or a standalone assistant-centric interactive display with speaker(s) to send a message using a messaging application on a client device such as a smartphone. A method includes: receiving, by a first device, a request from a first user to send a message to a second user; determining that a messaging application corresponding to the request is unavailable on the first device; and in response to determining that the messaging application corresponding to the request is unavailable on the first device: selecting a second device on which the messaging application corresponding to the request is available; and sending, to the second device, a command that causes the second device to send the message from the first user to the second user using the messaging application on the second device.
A computing device may include camera modules and a camera enclosure configured to house the camera modules. The computing device may further include alignment wedges that each define a sloped surface configured to mechanically contact at least one of the camera enclosure or the camera modules. The alignment wedges may be configured to reposition the respective camera module of the plurality of camera modules with respect to the camera enclosure.
A base station can implement a method for configuring a multicast radio bearer (MRB) for a multicast and/or broadcast services (MBS) session. The method may include determining (1502) that the MBS session or the MRB requires uplink resources. The method may also include, based on the determining, selecting (1504) a configuration for the MRB, the configuration including configuration parameters for a user equipment (UE) to receive the MBS session. The method may further include transmitting (1506) the selected configuration to the UE.
An example method is provided. Unverified interaction data descriptive of interactions of a user with the computing device can be obtained. Feature values that embed characteristics of the unverified interaction data can be generated using a machine-learned embedding network of a machine-learned verification pipeline. A user account associated with the unverified interaction data can be determined using a verification model of the machine-learned verification pipeline.
An example method is provided for training a machine-learned student sequence processing model, the method comprising: obtaining a respective input; obtaining, from the student machine-learned sequence processing model, a respective output corresponding to the respective input; generating a multiscale refinement objective configured to jointly distill knowledge from a teacher machine-learned sequence processing model and reinforce preferred behavior of the student machine-learned sequence processing model, wherein the multiscale refinement objective comprises: a first component based on a divergence metric characterizing, for the respective input, a comparison of a plurality of predictions of the student machine-learned sequence processing model to a plurality of predictions of the teacher machine-learned sequence processing model; and a second component based on a reinforcement learning signal associated with the respective output; and updating the machine-learned student sequence processing model based on the multiscale refinement objective.
Implementations set forth herein relate to phasing-out of vehicle computing device versions while ensuring useful responsiveness of any vehicle computing device versions that are still in operation. Certain features of updated computing devices may not be available to prior versions of computing devices because of hardware limitations. The implementations set forth herein eliminate crashes and wasteful data transmissions caused by prior versions of computing devices that have not been, or cannot be, upgraded. A server device can be responsive to a particular intent request provided to a vehicle computing device, despite the intent request being associated with an action that a particular version of the vehicle computing device cannot execute. In response, the server device can elect to provide speech to text data, and/or natural language understanding data, in furtherance of allowing the vehicle computing device to continue leveraging resources at the server device.
To provide dynamic generation and suggestion of map tiles, a server device receives from a user device a request for map data for a particular geographic region. The server device obtains a set of user contextual data and a set of candidate map tiles associated with the particular geographic region. The server device then selects one or more of the set of candidate map tiles based on the set of user contextual data, and transmits the one or more selected map tile to the user device for display.
The presently disclosed technology provides methods and systems for optimally allocating power among workloads executing on a computer system through use of a power management algorithm. For example, according to the present technology a plurality of CPUs within a server can be divided into multiple groups according to application workloads. Workloads can be distributed to the CPUs as needed by a workload scheduler, and the workload scheduler can provide the CPU IDs to a power manager, enabling the power manager to optimize power settings. Each group of CPUs can be assigned an optimal power profile tailored to its respective situation.
Techniques described herein enable a user to interact with an automated assistant and obtain relevant output from the automated assistant without requiring arduous typed input to be provided by the user and/or without requiring the user to provide spoken input that could cause privacy concerns (e.g., if other individuals are nearby). The assistant application can operate in multiple different image conversation modes in which the assistant application is responsive to various objects in a field of view of the camera. The image conversation modes can be suggested to the user when a particular object is detected in the field of view of the camera. When the user selects an image conversation mode, the assistant application can thereafter provide output, for presentation, that is based on the selected image conversation mode and that is based on object(s) captured by image(s) of the camera.
G06V 20/20 - ScenesScene-specific elements in augmented reality scenes
G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
G06F 3/0482 - Interaction with lists of selectable items, e.g. menus
G06F 3/04886 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
G06F 16/487 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
Designing a circuit to perform a floating point arithmetic operation by identifying a multiple of parameters that characterize circuits for performing the floating point arithmetic operation and an equation relating the plurality of parameters to a maximum relative backward error parameter, the circuits respectively corresponding to combinations of values for the parameters; specifying a target maximum relative backward error for the floating point arithmetic operation; computing a maximum relative backward error for each of one or more of the combinations of values based on the equation; and when the maximum relative backward error for a respective combination of values is less than the target maximum relative backward error, identifying the circuit corresponding to the maximum relative backward error as a circuit operable to perform the floating point arithmetic operation at a desirable output accuracy.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for query categorization based on image results. In one aspect, a method includes receiving images from image results responsive to a query, wherein each of the images is associated with an order in the image results and respective user behavior data for the image as a search result for the first query, and associating one or more of the first images with a plurality of annotations based on analysis of the selected first images' content.
Techniques and apparatuses are described that implement random modulation of charge-pump noise phases to reduce structured noise induced by the charge pump. In an example aspect, a correlated double sampling (CDS) circuit is coupled to a pixel array including at least one pixel circuit. The CDS circuit receives an input signal generated by the at least one pixel circuit from the pixel array and samples a reset component of the input signal during a first sampling time to generate a reset component sample. The first sampling time is at a first offset from a reset control signal and prior to a settling time of the at least one pixel circuit. The CDS circuit samples a signal component of the input signal during a second sampling time to generate a signal component sample and determines an output signal based on the reset component sample and the signal component sample.
H04N 25/616 - Noise processing, e.g. detecting, correcting, reducing or removing noise involving a correlated sampling function, e.g. correlated double sampling [CDS] or triple sampling
H04N 25/78 - Readout circuits for addressed sensors, e.g. output amplifiers or A/D converters
27.
THREE-DIMENSIONAL HAND AND OBJECT MOTION SYNTHESIS
A method includes determining a trajectory of an object based on a mass of the object, and determining a motion of a hand based on the mass of the object and the trajectory of the object. The method can further include generating an animation of the hand interacting with the object based on the trajectory of the object and the motion of the hand.
Various implementations are directed towards generating, based on processing language model (LM) input using a first LM, an initial response that is predicted to be responsive to natural language (NL) based input, where the LM input includes at least the NL based input. Additionally or alternatively, the system can determine whether to generate an additional response based on processing the LM input using a second LM, where determining whether to generate the additional response includes processing at least the LM input and initial response using at least one verifier to generate a verification score. In many implementations, the verification score can be processed using a meta-verifier to determine whether to render output based on the initial response or the additional response.
Implementations relate to an automated assistant that provides and manages output from one or more elements of output hardware of a computing device. The automated assistant manages dynamic adjustment of access permissions to the computing device according to, for example, a detected presence of one or more users. An active-user queue can be established each time a unique user enters a viewing window of a camera of the computing device when, up to that point, no user was considered active. Multiple image frames can be captured via the camera and processed to determine whether an initial user remains in the viewing window and/or whether another user has entered the viewing window. The initial user can be considered active as long as they are exclusively detected in the viewing window. Restricted content associated with the user may be rendered by the computing device whilst the user is active.
H04N 21/442 - Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed or the storage space available from the internal hard disk
G06T 7/70 - Determining position or orientation of objects or cameras
H04N 21/258 - Client or end-user data management, e.g. managing client capabilities, user preferences or demographics or processing of multiple end-users preferences to derive collaborative data
H04N 21/41 - Structure of clientStructure of client peripherals
H04W 12/64 - Location-dependentProximity-dependent using geofenced areas
A central unit (CU) of a distributed base station, the distributed base station including the CU and a distributed unit (DU), can implement a method for managing a radio function for communicating with a UE. The method may include determining (1202) to transmit a CU-to-DU message, related to control of data communication with the UE, to the DU, and determining (1204) whether the data communication requires the DU to perform the radio function. The method further includes, based on whether the data communication requires the DU to perform the radio function, determining (1206) whether to include an indication in the CU-to-DU message to enable the radio function at the DU. The method also includes transmitting (1208) the CU-to-DU message to the DU.
A method includes receiving a text embedding generation query from a user requesting generation of a text embedding for one or more data elements stored at a data warehouse. In response, the method includes selecting, using the text embedding generation query, a text embedding model from a plurality of different text embedding models. The method includes generating, using the selected text embedding model, the text embedding for the one or more data elements and storing the text embeddings at the data warehouse. The method includes receiving a machine learning model training query from the user device requesting training of a machine learning model using the text embeddings. In response to receiving the machine learning model training query, the method includes training the machine learning model using the text embeddings. The method includes providing, to the user device, a notification indicating that training of the machine learning model is complete.
Implementations are directed to dynamically adapting which assistant on-device model(s) are locally stored at assistant devices of an assistant device group and/or dynamically adapting the assistant processing role(s) of the assistant device(s) of the assistant device group. In some of those implementations, the corresponding on-device model(s) and/or corresponding processing role(s), for each of the assistant devices of the group, is determined based on collectively considering individual processing capabilities of the assistant devices of the group. Implementations are additionally or alternatively directed to cooperatively utilizing assistant devices of a group, and their associated post-adaptation on-device model(s) and/or post-adaptation processing role(s), in cooperatively processing assistant requests that are directed to any one of the assistant devices of the group.
Implementations described herein relate to determining how an automated assistant should respond to a given spoken utterance received in a vehicular environment to enforce consistency between value(s) and/or unit(s) that are displayed at a given display device of an in-vehicle computing device and value(s) and/or unit(s) that are utilized in executing a given vehicular command or that are provided for presentation to a user in response to a given vehicular request. For example, implementations can receive the given spoken utterance, identify the given vehicular command/request based on processing the given spoken utterance, and determine an original equipment manufacturer (OEM) query based on the given vehicular command/request included in the spoken utterance, and transmit the OEM query to a given OEM component. Further, implementations can determine how the automated assistant should respond to the given spoken utterance based on responsive content that is received from the given OEM component.
Implementations can receive user input during a dialog session between a user and an automated assistant at a client device of the user and via an automated assistant platform, and in response to determining that the user input requires a user interaction with a non-assistant platform: store a state of the dialog session between the user and the automated assistant, transmit a request to initiate the user interaction to the non-assistant platform that causes an additional client device of the user to render a prompt for completing the user interaction, and receive a token associated with the user interaction from the non-assistant platform. In response to receiving the token associated with the user interaction, implementations can cause the dialog session between the user and the automated assistant to be resumed based on the stored state of the dialog session and based on the token associated with the user interaction.
H04L 51/02 - User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
Systems and methods for textual replacement can include the determination of a visual intent, which can trigger an interface for selecting an image to replace visual descriptors. The visually descriptive terms can be identified, and an indicator can be provided to indicate the text replacement option may be initiated. An image can then be selected by a user to replace the visually descriptive terms.
The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.
Provided are computing systems, methods, and platforms that rank text with pairwise ranking prompting using a generative sequence processing model. A prompt comprising a query and sets of text associated with candidate results can be generated. The generative sequence processing model can be prompted with the prompt and perform pairwise comparisons between the sets of text in the prompt based on the query in the prompt. An output can be generated that ranks the sets of text in response to the query.
Implementations relate to managing multimedia content that is obtained by large language model(s) (LLM(s)) and/or generated by other generative model(s). Processor(s) of a system can: receive natural language (NL) based input that requests multimedia content, generate a response that is responsive to the NL based input, and cause the response to be rendered. In some implementations, and in generating the response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, at least multimedia content to be included in the response. Further, the processor(s) can evaluate the multimedia content to determine whether it should be included in the response. In response to determining that the multimedia content should not be included in the response, the processor(s) can cause the response, including alternative multimedia content or other textual content, to be rendered.
Techniques are disclosed for evaluating manual driving data using an AV control system based on differences between data generated using the AV control system and the manual driving data. In many implementations, manual driving data captures action(s) of a vehicle controlled by a manual driver. Additionally or alternatively, an additional AV control system can be trained using the evaluated manual driving data.
A multimodal search system is described. The system can receive image data from a user device. Additionally, the system can receive a prompt associated with the image data. Moreover, the system can determine, using a computer vision model, a first object in the image data that is associated with the prompt. Furthermore, the system can receive, from the user device, a user indication on whether the image data includes the first object. Subsequently, in response to receiving the user indication, the system can generate a response using a large language model.
Methods, systems, and apparatus, for calibration quality control using multiple magnetometers. One of the methods includes: receiving measurements by two or more magnetic field sensors of a device over a period of time, wherein each measurement measures a magnetic field at each magnetic field sensor, wherein each measurement at each time point over the period of time includes a vector in one or more spatial axes of a three-dimensional space; computing a difference between the measurements over the period of time, wherein the difference at each time point over the period of time is a result of computing a difference based on one or more pairs of the vectors at the time point; determining that the difference does not remain within a predetermined range over the period of time; and in response, classifying calibration quality of the device as unsuitable for computing a heading of the device.
Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training an audio-processing neural network that includes at least (1) a first encoder network having a first set of encoder network parameters and (2) a decoder network having a set of decoder network parameters. The system obtains a set of un-labeled audio data segments, and generates, from the set of un-labeled audio data segments, a set of encoder training examples. The system performs training of a second encoder neural network that includes at least the first encoder neural network on the set of generated encoder training examples. The system also obtains one or more labeled training examples, and performs training of the audio-processing neural network on the labeled training examples.
A wireless communication system employs DNNs or other neural networks to provide for RACH techniques. A TX DNN at user equipment (UE) generates and provides for wireless transmission of a Random Access (RA) signal to a base station (BS). A BS receives the RA signal as input, and from this input generates and provides for wireless transmission of an RA Response signal to the UE.
According to an embodiment, a computing device can include one or more processors and one or more computer-readable media that store instructions that, when executed by the processor(s), cause the computing device to perform operations. The operations can include obtaining a plurality of sleep stages associated with a sleep session of a user. The sleep session can be at least partially defined by an estimated bedtime of the user. The operations can further include identifying, in the plurality of sleep stages, one or more defined sleep stages indicative of a defined sleep state of the user. The operations can further include calculating a time before sound sleep (TBSS) metric based at least in part on the estimated bedtime of the user and a start time of the defined sleep stage(s). The operations can further include performing one or more operations based at least in part on the TBSS metric.
Methods and systems for media trend identification of content sharing platforms are provided herein. A set of audiovisual embeddings that represent audiovisual features of a media item is obtained. A set of textual embeddings that represent textual features of the media item is obtained. The obtained set of audiovisual embeddings and the obtained set of textual embeddings are provided as an input to an artificial intelligence (AI) model trained to predict whether a respective media item is associated with one or more media trends of a platform based on given embeddings for the media item. One or more outputs of the AI model are obtained. A determination is made, based on the one or more outputs of the AI model, whether the media item is associated with the one or more media trends of the platform.
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/40 - ScenesScene-specific elements in video content
G10L 15/02 - Feature extraction for speech recognitionSelection of recognition unit
G10L 25/18 - Speech or voice analysis techniques not restricted to a single one of groups characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
G10L 25/57 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination for processing of video signals
Encoding using chroma intra prediction with filtering includes encoding a current block from a current frame, which includes obtaining a first chroma prediction value for a current chroma pixel using a current spatial intra prediction mode, obtaining a current luma prediction value for a current luma pixel collocated with the current chroma pixel, obtaining a second chroma prediction value for the current chroma pixel for the current chroma component by applying derived filter coefficients to the current luma prediction value, obtaining, as a third chroma prediction value for the current chroma pixel for the current chroma component, a weighted average of the first chroma prediction value and the second chroma prediction value, obtaining encoded chroma pixel data for the current chroma pixel by encoding the current chroma pixel using the third chroma prediction value, and including the encoded chroma pixel data in the encoded block data.
H04N 19/593 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial prediction techniques
H04N 19/11 - Selection of coding mode or of prediction mode among a plurality of spatial predictive coding modes
H04N 19/117 - Filters, e.g. for pre-processing or post-processing
H04N 19/119 - Adaptive subdivision aspects e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
H04N 19/136 - Incoming video signal characteristics or properties
H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
A computer implemented method includes providing a user interface to a user that includes an original image and an option to generate a high-resolution portion of the original image. The method includes receiving a selection of the option to generate the high-resolution portion of the original image and dimensions of a portion of the original image. The method includes providing the portion of the original image as input to a machine-learning model. The method includes generating, with the machine-learning model, the high-resolution image. The method includes updating the user interface to include the high-resolution portion of the original image.
G06T 3/4053 - Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
G06T 3/4046 - Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
49.
UTILIZING LARGE LANGUAGE MODEL (LLM) IN RESPONDING TO MULTIFACETED QUERIES
Implementations leverage a generative model (e.g., a large language model (LLM)) to generate a plurality of candidate subqueries for multifaceted natural language (NL) based input, where each of the candidate subqueries is potentially directed to a facet or problem of the multifaceted NL based input. Those implementations further select, from the plurality of candidate subqueries and using one or more evaluation metrics, a subset of the candidate queries. Those implementations further, in response to selecting the subset of the candidate queries, obtain, for each of the candidate subqueries of the selected subset, at least one corresponding search result. Those implementations further generate a response to the NL based input based on the corresponding search results for the candidate subqueries of the subset, and cause the response to be rendered responsive to the NL based input.
An example computer-implemented method for self-supervised training of an image processing model for histopathology images is provided. The example method includes obtaining a reference histopathology image; generating an augmented histopathology image, wherein generating the augmented histopathology image comprises performing, for an input image, at least one of the following augmentations: applying a blur to the input image and injecting noise artifacts into the blurred input image; or cropping a plurality of portions from the input image, wherein the plurality of portions are determined based on a minimum overlap criterion that has been updated over one or more iterations; and training the image processing model based on a similarity of latent representations generated by the image processing model respectively for the reference histopathology image and the augmented histopathology image.
An electronic device includes a wireless charging receive coil configured to transduce, into an alternating current (AC) power signal, a magnetic field generated by a wireless charging transmit coil of an external device; an active rectifier configured to convert the AC signal received at an AC side of the active rectifier into a direct current (DC) power signal output at a DC side of the active rectifier, the active rectifier comprising a plurality of switches; a first modulation capacitor connected to an upper rail of the AC side; a second modulation capacitor connected to a lower rail of the AC side; and a controller configured to adjust an impedance of the computing device to communicate with the external device by at least controlling the plurality of switches to cause the first modulation capacitor and the second modulation capacitor to charge during separate time periods.
H02J 50/80 - Circuit arrangements or systems for wireless supply or distribution of electric power involving the exchange of data, concerning supply or distribution of electric power, between transmitting devices and receiving devices
H02J 50/12 - Circuit arrangements or systems for wireless supply or distribution of electric power using inductive coupling of the resonant type
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output image. In one aspect, one of the methods includes generating the output image intensity value by intensity value according to a generation order of pixel-color channel pairs from the output image, comprising, for each particular generation order position in the generation order: generating a current output image representation of a current output image, processing the current output image representation using a decoder neural network to generate a probability distribution over possible intensity values for the pixel—color channel pair at the particular generation order position, wherein the decoder neural network includes one or more local masked self-attention sub-layers; and selecting an intensity value for the pixel—color channel pair at the particular generation order position using the probability distribution.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06F 18/21 - Design or setup of recognition systems or techniquesExtraction of features in feature spaceBlind source separation
G06F 18/213 - Feature extraction, e.g. by transforming the feature spaceSummarisationMappings, e.g. subspace methods
G06F 18/28 - Determining representative reference patterns, e.g. by averaging or distortingGenerating dictionaries
G06N 3/04 - Architecture, e.g. interconnection topology
G06N 3/084 - Backpropagation, e.g. using gradient descent
G06T 3/4053 - Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
G06V 10/56 - Extraction of image or video features relating to colour
G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
53.
SELECTIVELY RENDERING A KEYBOARD INTERFACE IN RESPONSE TO AN ASSISTANT INVOCATION IN CERTAIN CIRCUMSTANCES
Implementations set forth herein relate to an automated assistant that can adapt to circumstances in which a user may invoke an automated assistant with an intention of interacting with the automated assistant via a non-default interface. For example, in some instances, a user may invoke an automated assistant by selecting a selectable GUI element. In response, the automated assistant can determine that, in the current context, spoken utterances may not be suitable for providing to the automated assistant. Based on this determination, the automated assistant can cause a keyboard interface to be rendered and/or initialized for receiving typed inputs from the user. Should the user subsequently change contexts, the automated assistant can determine that voice input is now suitable for user input and initialize an audio interface in response to the user providing an invocation input in the subsequent context.
G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
G06F 3/04886 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface prediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).
A method for managing cloud infrastructure includes receiving, from a user of a user device, a cloud infrastructure modification request requesting modification to cloud infrastructure. The cloud infrastructure modification request includes abstract configuration data derived from a user interaction with a graphical user interface (GUI) executing on the user device. The method includes translating the abstract configuration data into a configuration command. The configuration command describes a configuration of the cloud infrastructure. The method includes updating a configuration file with the configuration command. The configuration file includes one or more cloud infrastructure specifications for the cloud infrastructure and is controlled by a source control management system. The method includes provisioning, using the updated configuration file, the cloud infrastructure.
This disclosure relates to using additive and subtractive noise for preserving the privacy of users. In one aspects, a method includes obtaining a first set of genuine user group identifiers that identify user groups that include a user as a member. A second set of user group identifiers is generated for the user by removing zero or more genuine user group identifiers from the first set to generate the second set and adding, to the second set, one or more fake user group identifiers for user groups that do not include the user as a member. A probabilistic data structure is generated based on the second set of user group identifiers. The probabilistic data structure is transmitted to a recipient computing system. Data indicating a set of digital components including at least one digital component selected based on the probabilistic data structure is received. A given digital component is presented.
Aspects of the disclosed technology include techniques and mechanisms for using a customizable and programmable control mechanism for single and multicore processors to schedule and execute one or more sets of instructions associated with different workloads. The customizable control mechanism may manage the one or more sets of instructions to be executed and may dynamically determine a priority order in which the one or more sets of instructions should be executed. The priority order may be based on workload-specific preferences and workload-specific requirements associated with each set of instructions. The customizable control mechanism may instruct one or more processors to execute the one or more sets of instructions in accordance with the determined priority order.
Techniques include using a generative model to make changes to content such that the mechanisms used to guide the user into a decision become plain to the user and/or minimizes the perceived urgency. Implementations can operate as part of the browser or as an extension to the browser. Implementations may identify a targeted UI element in browser content (a web page) and use the generative model to modify the targeted UI element before presenting the browser content to the user. In some implementations, the identification of the targeted UI element may be performed by the generative model.
G06F 40/40 - Processing or translation of natural language
G06F 3/0483 - Interaction with page-structured environments, e.g. book metaphor
G06F 3/0484 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
G06F 40/109 - Font handlingTemporal or kinetic typography
G06F 40/169 - Annotation, e.g. comment data or footnotes
Implementations relate to a drafting assistant that assists users in generating prompts for a language model that generates responses for text boxes for a web page. Implementations may receive a prompt from a user regarding an input for the text box, generate a modified prompt by incorporating contextual information identified from the web page, and provide the modified prompt to a generative language model, which generates a response for the modified prompt. The response is presented to the user and can be used as the input for the text box. Implementations dynamically engineer/enhance prompts based on the context of the web page, thereby facilitating more accurate and relevant responses from the generative language model.
A computer-implemented method includes receiving a natural language command from a user that requests a digital assistant to provide a notification to a user device associated with the user upon occurrence of a particular event. The method also includes processing the natural language command using a natural language understanding module to determine one or more event conditions that each indicate the occurrence of the particular event and obtaining event information of the particular event. While the user device is in a notification silencing mode, the method includes determining that at least one of the one or more event conditions is satisfied and providing the notification for output from the user device in response to determining that at least one of the one or more event conditions is satisfied. The notification, when output from the user device, notifies the user of the occurrence of the particular event.
Disclosed implementations allow for the customization of text size in displayable content via a nonlinear text scaling, which provides users with enhanced readability and accessibility options. Nonlinear text scaling includes adjusting the text size of displayable content using a fixed font size, a zoom level, and a uniformity level. User interface elements can be provided that allow manipulation of the zoom level and the uniformity level. User interface elements can be provided that add bolding and word/line/character spacing.
This document describes systems and techniques for presenting intermediate media to a user that has presented a media request. In aspects, a media request for requested media is received from an input device. The media request is provided to a media service to serve the requested media to a requested device. The media request is processed to identify attributes of the media request indicative of a subject matter of the requested media. Based on the identified attributes of the media request, intermediate media is accessed including one or more images related to the identified attributes. The intermediate media is delivered to the requested device. Accordingly, the intermediate media provides content to engage the user while the user waits for the requested media to be delivered.
H04N 21/25 - Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication or learning user preferences for recommending movies
A method includes obtaining labeled training data including a plurality of spoken terms spoken during a conversation. For each respective spoken term, the method includes generating a corresponding sequence of intermediate audio encodings from a corresponding sequence of acoustic frames, generating a corresponding sequence of final audio encodings from the corresponding sequence of intermediate audio encodings, generating a corresponding speech recognition result, and generating a respective speaker token representing a predicted identity of a speaker for each corresponding speech recognition result. The method also includes training the joint speech recognition and speaker diarization model jointly based on a first loss derived from the generated speech recognition results and the corresponding transcriptions and a second loss derived from the generated speaker tokens and the corresponding speaker labels.
A method includes receiving an audible response to a query, and prior to playing back the audible response, providing, for output from an acoustic speaker, an alignment output audio stream that encodes an audio watermark. The method also includes receiving an alignment input audio stream captured by a microphone array and encoding an acoustic echo of the audio watermark, processing the alignment input audio stream to detect the acoustic echo, and determining a time alignment value between the alignment output audio stream and the alignment input audio stream. The method also includes playing back a response output audio stream that encodes the audible response and receiving an input audio stream. The input audio stream includes acoustic echo corresponding to the audible response played back. The method also includes processing the input audio stream to generate a respective target audio signal that cancels the acoustic echo.
A method includes receiving a conversational training dataset including a plurality of conversational training samples, each training sample associated with a corresponding conversation and including: corresponding audio data characterizing a corresponding current utterance spoken by a user during a current turn in the corresponding conversation; a corresponding context for the corresponding current utterance including a transcript of a previous turn in the corresponding conversation that precedes the current turn; a corresponding ground-truth transcription of the corresponding current utterance; and a CoT annotation representing a corresponding logical relationship between the corresponding current utterance and the previous turn. The method also includes, for each corresponding conversational training sample in the conversational training dataset, training a speech model on the corresponding conversational training sample to teach the speech model to learn how to predict the corresponding logical relationship from the corresponding audio data and the corresponding context.
G10L 25/30 - Speech or voice analysis techniques not restricted to a single one of groups characterised by the analysis technique using neural networks
This document describes systems and techniques for implementing personalized suggestions for a user interacting with a facility management system based on contextual metadata to assist the user in controlling the facility management system. For example, a system includes a request module configured to receive a request from a user. A metadata module is configured to access and identify metadata related to a content or context of the request. A large language model (LLM) module is configured to receive the request and the metadata and to generate a suggestion relevant to the content or context of the request. A suggestion module is configured to present the suggestion to the user.
A media application obtains a video that includes an audio portion. The media application separates the audio portion into a plurality of channels, where each channel corresponds to a particular audio source. An on-screen classifier model obtains an indication of whether the particular audio source for each channel is depicted in the video. An audio-type classifier model determines, an auditory object classification for each channel. The media application determines a respective gain for each channel based on the indication of whether the particular audio source for the channel is depicted in the video and the auditory object classification for the channel. The media application modifies each channel by applying the respective gain. The media application mixes the modified channels with the audio portion to generate a combined audio.
In a general aspect, a display panel includes a plurality of pixel groups. A pixel group of the plurality of pixel groups includes a plurality of light emitters of different colors, and a single current source that is multiplexed to sequentially activate light emitters of the plurality of light emitters using a first plurality of selector switches, The display panel further includes a single driver switch for coupling the single current source with the first plurality of selector switches, and a memory for controlling the single driver switch.
G09G 3/20 - Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix
G09G 3/32 - Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix using controlled light sources using electroluminescent panels semiconductive, e.g. using light-emitting diodes [LED]
69.
USING SEMANTIC NATURAL LANGUAGE PROCESSING MACHINE LEARNING ALGORITHMS FOR A VIDEO GAME APPLICATION
Game decisions are coordinated using a semantic natural language processing (NLP) machine learning (ML) algorithm, which is stored in a memory in some cases. In response to a game event, a processor records a text string that represents the game event in a text log that includes a sequence of text strings that represent game events that have transpired during a portion of the game. The processor also generates, using the semantic NLP ML algorithm, scores for labeled actions or content based on the text log and a curve that represents a target player experience as a function of progress through the game. The processor further serves one or more of the labeled actions or content that is selected based on the scores. The labeled actions or content are served to a display associated with the processor.
Spatial audio is rendered at a companion device or server connected to a wearable device, where the spatial audio is rendered based on a first pose estimate of the wearable device that is estimated at the companion device or server. The rendered spatial audio is then transmitted to the wearable device. The rendered spatial audio is refined at the wearable device based on a second pose estimate of the wearable device that is estimated at the wearable device. The refined spatial audio is then provided for playback via speakers of the wearable device.
A hosted storage system receives a storage request that includes a single object and conforms to an API implemented by the hosted storage system. The API is designed to only support a single object in a storage request. The hosted storage system, in response to determining that the single object is an archive file, extracts each of the bundled files from the archive file and stores each of the extracted files in the hosted storage system such that each of the extracted files is separately accessible by the client system over the network.
A method for distributing encryption keys includes receiving a table associated with a particular user, the table including a plurality of data blocks and splitting the table into a plurality of tablets including a corresponding portion of data blocks. The method also includes generating a resource key uniquely associated with the table and for each tablet generating a unique data encryption key for the corresponding tablet to encrypt with the unique data encryption key. The method also includes encrypting each data encryption key with the resource key and distributing control of each encrypted tablet and each corresponding encrypted data encryption key to a plurality of tablet servers, each controlling one or more of the encrypted tablets. The resource key transmits to a remote entity causing the remote entity to encrypt the resource key with a user key associated with the particular user and transmit the encrypted resource key.
The technology is generally directed to reordering packets received by a network to reduce the unfairness in transmitting and receiving data. The packets may be reordered based on a timestamp appended to the packet. The timestamp may correspond to a time when the sender loses control of the packet and the receiving network gains control. A packet reorder structure may receive the packets with the appended timestamps during a sample interval. The packet reorder structure may compare the timestamp to a time interval for a plurality of timeslots. The packets may be reordered based on the timeslot the packet is allocated to. In some examples, the duration of the timeslot may be dynamically adjusted such that the number of out of order packets received during the sample interval corresponds to a threshold.
A first computing device signed into a user account may determine a management action to be performed by a second computing device signed into the user account to manage one or more applications installed at the second computing device. The first computing device may select a communication channel for sending a request to perform the management action to the second computing device. The first computing device may send, to the second computing device via the communication channel, the request to perform the management action to manage the one or more applications installed at the second computing device.
H04L 67/125 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
This disclosure is directed to a method for performing a quantum computation. A set of qubits may be allocated for the quantum computation. The qubits of the set of the qubits may be calibrated in parallel with the execution of the quantum computation. The method may include subdividing the set of qubits into a first calibration group and a first computation group. The first calibration group and the first computation group may be complementary subsets of the set of qubits. A first portion of the quantum computation may be executed with qubits included in the first computation group. During execution of the first portion of the quantum computation with the qubits included in the first computation group, qubits included in the first calibration group may be calibrated. A second portion of the quantum computation may be executed with the calibrated qubits included in the first calibration group.
A fluid sample collection unit may include a pod configured to receive a plurality of assay pads and a metering stack. The metering stack defines a channel extending longitudinally between an inlet end and dispensing portions. In some instances, the dispensing portions are movable relative to the assay pads, but a support feature within the pod vertically spaces apart the dispensing portions from the assay pads when less than a threshold vertical pressure is applied. In one instance, the pod defines a collection volume, a dispensing volume, and a passage portion, the passage portion connecting the collection and dispensing volumes. The metering stack is at least partially received within the pod, with the inlet end being positioned at the collection volume, the dispensing portions positioned within the dispensing volume above the assay pads, and an air gap being formed within the passage portion around the metering stack.
A method includes receiving, for presentation to a user of a user device, image data representing an image. The method also includes generating, using a textual story generative model, based on the image data, a textual story for the image, and generating, based on the textual story for the image, textual story audio data representing the textual story for the image. The method further includes providing, for audible output from the user device, the textual story audio data.
G10L 13/08 - Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
According to an aspect, a method may include rendering, by a television application executing on a computing device, a first user interface that provides a fitness goal setup option associated with an account of a user of the television application. The method may include receiving, by the television application, fitness goal criteria for the fitness goal setup option. The method may include sending, by the computing device, the fitness goal criteria to a server computer for use in generating a media content recommendation directed towards achieving the fitness goal criteria. The method may include receiving a sequence of selectable information items that correspond to media content items sourced by a plurality of different media content providers based on the media content recommendation. The method may include displaying, by the television application, a second user interface that includes the sequence of selectable information items.
A first computing device may receive a request to install an application at the first computing device from a second computing device signed into a same user account as the first computing device. The first computing device may, in response to receiving the request and based on the first computing device not having sufficient available storage space to install the application, download a stub associated with the application from a computing system. The first computing device may install the stub associated with the application.
A display system comprises a first frame structure housing one or more processors and wearable proximate to a user's eye, and a second frame structure coupled to a light engine and various optical elements. The light engine generates display light indicative of graphical content, with the optical elements channeling the display light to the user's eye. The processors of the first frame structure control operations of the light engine via a selectively detachable connection between an electromechanical interface of the first frame structure and a corresponding electromechanical interface of the second frame structure.
An augmented reality (AR) or mixed reality (MR) eyewear display utilizes an antenna arrangement for eyewear that optimizes the performance of the antenna without sacrificing the functionality or modularity of the eyewear. In one implementation, the antenna arrangement includes a first conductor that functions as a ground for the antenna, a second conductor configured to help retain a lens, and an antenna feed configured to excite the second conductor, causing the second conductor to act as an antenna. The first and/or second conductor additionally acts as a lens retention feature by interfacing with a groove in a lens and the use of a locking clip that prevents the lens from becoming dislodged from the second conductor, thus enabling quick and easy installation or removal of the lens.
A waveguide includes a set of grating structures forming a component on the surface of the waveguide. The set of grating structures is configured to direct light received at the component based on a parameter of one or more grating structures of the set of grating structures. Further, the waveguide includes a first transition area disposed adjacent to a first side of the component wherein the parameter is modulated across the grating structures of the first transition area. Additionally, the waveguide includes a second transition area disposed adjacent to a second, opposite side of the component wherein the parameter is also modulated across the grating structures of the second transition area.
The present disclosure provides systems and methods for transmitting data to a pair of truly wireless devices. A first device, which may be considered the primary device, may determine a first data packet was received. The first device may also determine the first data packet was not received by a second device of the pair of truly wireless devices. In response to determining the second device did not receive the first data packet, the first device may request the first data packet be retransmitted.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing data about a medical encounter using neural networks. One of the methods includes obtaining features for a medical encounter associated with the patient, each feature representing a corresponding health event associated with the medical encounter and each of the plurality of features belonging to a vocabulary of possible features that each represent a different health event; and generating respective final embeddings for each of the features for the medical encounter by applying a sequence of one or more self-attention blocks to the features for the medical encounter, wherein each of the one or more self-attention blocks receives a respective block input for each of the features and applies self-attention over the block inputs to generate a respective block output for each of the features.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
85.
Display screen or portion thereof with transitional graphical user interface
Methods and apparatus related to identifying a video for completing a task and determining a plurality of video segments of the identified video based on one or more attributes of the task. A task and a plurality of how-to videos related to the task may be identified. A how-to video may be selected and a plurality of video segments of the selected how-to video may be determined. One or more video segments may be associated with one or more task attributes that relate to performing the task. The selected video may be provided to a user and segmented, indexed, and/or annotated based on the associated video segments. In some implementations a given object utilized in performing the task may be identified and one or more video segments corresponding to the given object may be identified and/or provided to the user.
G06F 16/783 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for distributing digital contents to client devices are described. The system obtains, for each user in a set of users, user attribute data and, for a subset of the users, consent data for controlling usage of the user attribute data. The system partitions, based at least on the consent data for the subset of users, the set of users into a first group of users and a second group of users. The system generates a respective training dataset based on the data for each group of user, and uses the datasets to train a machine learning model configured to predict information about one or more users. In particular, the system applies differential privacy to the second training dataset without applying differential privacy to the first training dataset during training.
Methods and systems for media trend detection and maintenance are provided herein. A set of media items each having common media characteristics is identified. A set of pose values is determined for each respective media item of the set of media items. Each pose value is associated with a particular predefined pose for objects depicted by the set of media items. A set of distance scores is calculated. Each distance score represents a distance between the respective set of pose values determined for a media item and a respective set of pose values determined for an additional media item. A coherence score is determined for the set of media items based on the calculated set of distance scores. Responsive to a determination that the coherence score satisfies one or more coherence criteria, a determination is made that the set of media items corresponds to a media trend of a platform.
G06V 20/40 - ScenesScene-specific elements in video content
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks through contrastive learning. In particular, the contrastive learning is modified to use a relative margin to adjust a training pair's contribution to optimization.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task. One of the methods includes obtaining data specifying a pre-trained neural network; obtaining a plurality of training examples for one or more new machine learning tasks; and generating a new neural network for the one or more new machine learning tasks.
G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/32 - Normalisation of the pattern dimensions
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
95.
RELATIVE POSITION BIASES IN ATTENTION NEURAL NETWORKS USING FUNCTIONAL INTERPOLATION
Systems and methods for processing inputs using attention neural networks. In particular, one or more of the attention layers within the attention neural network compute relative position biases using functional interpolation.
A machine-learned model includes an encoder having a feature block configured to embed input data into a plurality of features in an embedding space. The input data includes multiple components such as covariate, treatment, and output components. The encoder includes one or more encoding layers, each including a temporal attention block and a feature-wise attention block. The temporal attention block is configured to obtain the embedded input data and apply temporal causal attention along a time dimension in parallel for each feature of the plurality of features to generate temporal embeddings. The feature-wise attention block is configured to obtain the temporal embeddings and generate component representations such as a covariate representation, a treatment representation, and an output representation.
A lightguide for a head-wearable display or near-eye display includes an incoupler configured to direct display light representative of an image to the eye of a user. To direct the display light, the lightguide includes an incoupler that has reflectors configured to first direct the display light into the lightguide such that the display light propagates through the body lightguide and is received at a combined exit pupil expansion and outcoupling structure of the lightguide. This combined exit pupil expansion and outcoupling structure includes an array of louver retroreflectors that expands the eyebox of the image and also directs at least a portion of the display light out of the lightguide and toward the eye of the user. The louver retroreflectors in the array of louver retroreflectors each includes a first reflective surface and a second reflective surface arranged substantially orthogonal to each other.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for implementing a neural network that can perform one or more machine learning tasks on an input that includes data that represents a given data structure. In particular, implementing a language model to encode the data and a foundation neural network with an attention-based architecture to generate the task output. Because of how language model generated embeddings are defined and cached, the described techniques demonstrate significant improvements in required computational resources for training and inference while also exceeding prediction performance on a variety of prediction tasks over conventional approaches.
A media application receives a set of images that include a source image and a target image, the source image and the target image including at least a subject. The media application determines whether to use one or more editors selected from a group of a head editor, a face editor, or combinations thereof. Responsive to determining to use the head editor, the media application generates a compositive image by replacing at least a portion of head pixels associated with a target head of the subject in the target image with head pixels from a source head of the subject in the source image and replacing neck pixels associated with a target neck and shoulder pixels associated with target shoulders that include an area between the target head and a target torso with an interpolated region that is generated from an interpolation of the source image and the target image.
Systems and methods for guided text generation in task-based dialogue. In some aspects of the technology, an automated assistant system is configured to receive a user request, call multiple APIs, generate dialogue acts based on data received from each API, replace any slot names in the dialogue acts with natural language descriptions of the slots, concatenate the modified dialogue acts, and pass the concatenated result to an NLG model for generation of a natural language response. In some aspects of the technology, the automated assistant may be configured to generate simple templated responses based on the data received from each API, concatenate the simple templated responses, and pass the concatenated sequence to an NLG model trained as a sequence-to-sequence transformer for generation of a final natural language response.
patents
