Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing multiple computer vision tasks using a shared computer vision neural network. In one aspect, one of the methods includes obtaining an input image; processing the input image and a prompt sequence using a shared computer vision neural network to generate an output sequence that comprises respective token at each of a plurality of time steps, wherein each token is selected from a shared vocabulary of tokens that is shared between the plurality of computer vision tasks, wherein the shared vocabulary comprises (i) a first set of tokens that each represent a respective discrete number from a set of discretized numbers and (ii) a second set of tokens that each represent a natural language text token.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for object detection using neural networks. In one aspect, one of the methods includes obtaining an input image; processing the input image using an object detection neural network to generate an output sequence that comprises respective token at each of a plurality of time steps, wherein each token is selected from a vocabulary of tokens that comprises (i) a first set of tokens that each represent a respective discrete number from a set of discretized numbers and (ii) a second set of tokens that each represent a respective object category from a set of object categories; and generating, from the tokens in the output sequence, an object detection output for the input image.

Abstract: A system for monitoring the condition of vehicle tires is disclosed. A method for monitoring the state of vehicle tires is also disclosed. The system includes a sensor unit, a sensor hub connected to the sensor unit, a processing unit and a power management unit. The sensor unit further includes plurality of sensors, an analog front end for processing and converting the analog signals to digital data, and a communication unit. A signal thresholding circuit is part of the analog front end. The condition of vehicular tires are monitored by determining the revolutions per minute (RPM) as well as the absolute number of revolutions of the tires. This facilitates in detecting bad road conditions, air leakage from tire, temperature and pressure of the tire and issue warnings to the user.

Abstract: A method and an apparatus for assessing participation in a multi-party communication are provided and the method includes receiving, from multimedia devices corresponding to multiple participants of a multimedia event including a multi-party communication, multi-modal data for each of the multiple participants, the multi-modal data including video data and audio data, where the multimedia devices are remote to the analytics server, extracting, for each of the plurality of participants, vision information from the video data, at least one of tonal information or text information from the audio data, determining a representative participation score (RPS) based on the vision information and the at least one of the tonal information or the text information for each of the plurality of participants for a predefined time interval, and sending at least one of the vision information, the tonal information, the text information, or the RPS for display.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating images. In one aspect, a method includes: receiving an input text prompt including a sequence of text tokens in a natural language; processing the input text prompt using a text encoder neural network to generate a set of contextual embeddings of the input text prompt; and processing the contextual embeddings through a sequence of generative neural networks to generate a final output image that depicts a scene that is described by the input text prompt.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating images. In one aspect, a method includes: receiving an input text prompt including a sequence of text tokens in a natural language; processing the input text prompt using a text encoder neural network to generate a set of contextual embeddings of the input text prompt; and processing the contextual embeddings through a sequence of generative neural networks to generate a final output image that depicts a scene that is described by the input text prompt.

Abstract: The present disclosure involves systems, software, and computer implemented methods for an artificial intelligence work center for ERP data. One example method includes receiving scenario and model settings for an artificial intelligence model for a predictive scenario. A copy of the dataset is processed based on settings to generate a prepared dataset that is provided with the settings to a predictive analytical library. A trained model trained and evaluation data for the trained model is received from the predictive analytical library. A request is received to generate a prediction for the predictive scenario for a target field for a record of the dataset. The record of the dataset is provided to the trained model and a prediction for the target field for the record the dataset is received from the model. The prediction is included for presentation in a user interface that displays information from the dataset.

Abstract: The present disclosure involves systems, software, and computer implemented methods for intelligent document processing in enterprise resource planning. One example method includes automatically determining that a document file is ready to be processed in an ERP (Enterprise Resource Planning) system. The document file is automatically processed and a request is sent to the ERP system to automatically create or update ERP data in the ERP system based on the document file. Status information is received from the ERP system regarding the request to create or update ERP data in the ERP system. The status information received from the ERP system is logged and information indicating that the document file has been processed in the ERP system is automatically recorded.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating images. In one aspect, a method includes: receiving an input text prompt including a sequence of text tokens in a natural language; processing the input text prompt using a text encoder neural network to generate a set of contextual embeddings of the input text prompt; and processing the contextual embeddings through a sequence of generative neural networks to generate a final output image that depicts a scene that is described by the input text prompt.

Abstract: A method for controlling the switching frequency of a switching regulator operating in a pulse skip mode, the method including: altering, by a digital logic block, a magnitude of a hysteresis voltage with a load current and an output ripple voltage of the switching regulator; and controlling, by a comparator, an average pulse skip mode frequency of the switching regulator, using the magnitude of the altered hysteresis voltage.

Abstract: An apparatus for generating a cumulative performance score for a salesperson, and a memory storing instructions that, when executed by the processor, configure the apparatus to perform a method. The method includes receiving audio data for at least the sal esperson from a first event having multiple participants including a salesperson, extracting one or more of tonal information or text information from the audio data for the salesperson, and extracting therefrom, behavioral parameters for the salesperson for one or more time intervals during the first event. The behavioral parameters include two or more of empathy, stress, politeness, or hesitation. The method further includes determining a first performance score for the salesperson based on the behavioral parameters, and sending the first performance score for display.

Abstract: An apparatus for identifying an episode in a multi-party multimedia communication includes a processor, and a memory storing instructions that, when executed by the processor, configure the apparatus to perform a method. The method includes receiving multi-modal data including video data and audio data for each of multiple participants. Vision information and at least one of tonal information or text information is used to determine a representative participation score (RPS) for one or more participants. An episode is identified during or proximate to pronounced RPS movement, and sent for display.

Abstract: A method and an apparatus for generating a cumulative sentiment score includes a method comprising receiving, at an analytics server, for a first event having a first plurality of participants includes a customer, video data and audio data for the customer, extracting, for the customer, at least one of tonal information or text information from the audio data, and facial expression information from video data, determining, from the at least one of the facial expression information, the tonal information or the text information, a first sentiment score for the customer for the first event, and generating a first event graphic displaying an association between the first sentiment score and at least one deal parameter for the first event, where the at least one deal parameter is associated with a deal includes the first event.

Abstract: An apparatus for identifying key information in a multi-party multimedia communication includes a processor, and a memory storing instructions that, when executed by the processor, configure the apparatus to perform a method. The method includes receiving multi-modal data including video data and audio data for each of multiple participants, and presentation data presented on one or more multimedia devices. Vision information and at least one of tonal information or text information is used to determine a representative participation score (RPS) for one or more participants. Content from presentation data presented during or proximate to pronounced RPS movement is identified and sent for display.

Abstract: An apparatus for generating multi-signaling output voltage may include at least one output buffer, wherein the at least one the output buffer may include a first PMOS transistor, a second PMOS transistor, a first NMOS transistor, a second NMOS transistor, and a Zener diode along with a switchable current source. The apparatus may further include first logic circuitry, second logic circuitry, first voltage down level shifter circuitry, second voltage down level shifter circuitry, and a first voltage up level shifter circuitry. Outputs of the first voltage down level shifter circuitry, the second voltage down level shifter circuitry, and the first voltage up level shifter circuitry are combined using the output buffer to generate the desired output. The second NMOS transistor acts as isolation transistor for reducing and/or preventing diode current between a first supply voltage and the third supply voltage.

Abstract: An apparatus for generating multi-signaling output voltage may include at least one output buffer, wherein the at least one the output buffer may include a first PMOS transistor, a second PMOS transistor, a first NMOS transistor, a second NMOS transistor, and a Zener diode along with a switchable current source. The apparatus may further include first logic circuitry, second logic circuitry, first voltage down level shifter circuitry, second voltage down level shifter circuitry, and a first voltage up level shifter circuitry. Outputs of the first voltage down level shifter circuitry, the second voltage down level shifter circuitry, and the first voltage up level shifter circuitry are combined using the output buffer to generate the desired output. The second NMOS transistor acts as isolation transistor for reducing and/or preventing diode current between a first supply voltage and the third supply voltage.

Abstract: A help system includes receives a request from the application running on an end-user device over a data communication network. The request may be transmitted in response to a command by a user to receive help related to the application. The server receives context information associated with the request from the application. According to one embodiment, the context information includes information gathered by the application as the user interacts with the application. The server selects information to be output based on the received context information, and transmits the selected information to the application.

Abstract: An organic electroluminescence device is disclosed which includes: a substrate; a thin film transistor formed on the substrate; a first electrode formed on the substrate provided with the thin film transistor; an organic light emission layer and a second electrode sequentially formed on the first electrode; and a first light absorption layer formed over the thin film transistor and configured to shield light emitted from the organic light emission layer. As such, the organic electroluminescence device employing the oxide thin film transistor can secure reliability against light.

Abstract: A method for managing a plurality of financial documents using a financial management application (FMA). The method includes performing a plurality of activities of the FMA, recording, in an activity feed, the plurality of activities and metadata describing characteristics of performing the plurality of activities, selecting, in response to a user request to undo a first activity of the plurality of activities, the first activity from the activity feed, selecting, based on the metadata and from the plurality of financial documents, a first financial document that was accessed by the FMA when performing the first activity, identifying, based on the metadata, a first result of the first activity on the first financial document, and modifying the first financial document to remove the first result of the first activity.

Abstract: An organic electroluminescence device is disclosed which includes: a substrate; a thin film transistor formed on the substrate; a first electrode formed on the substrate provided with the thin film transistor; an organic light emission layer and a second electrode sequentially formed on the first electrode; and a first light absorption layer formed over the thin film transistor and configured to shield light emitted from the organic light emission layer. As such, the organic electroluminescence device employing the oxide thin film transistor can secure reliability against light.