Abstract: A group captioning system includes computing hardware, software, and/or firmware components in support of the enhanced group captioning contemplated herein. In operation, the system generates a target embedding for a group of target images, as well as a reference embedding for a group of reference images. The system identifies information in-common between the group of target images and the group of reference images and removes the joint information from the target embedding and the reference embedding. The result is a contrastive group embedding that includes a contrastive target embedding and a contrastive reference embedding with which to construct a contrastive group embedding, which is then input to a model to obtain a group caption for the target group of images.

Abstract: Techniques related to executing a plurality of instructions by a processor comprising receiving a first instruction configured to cause the processor to output a first data value to a first address in a first data cache, outputting, by the processor, the first data value to a second address in a second data cache, receiving a second instruction configured to cause a streaming engine associated with the processor to prefetch data from the first data cache, determining that the first data value has not been outputted from the second data cache to the first data cache, stalling execution of the second instruction, receiving an indication, from the second data cache, that the first data value has been output from the second data cache to the first data cache, and resuming execution of the second instruction based on the received indication.

Abstract: The present description relates to systems, methods, and non-transitory computer readable media for generating digital responses to digital queries by utilizing a classification model and query-specific analysis models. For example, the described systems can train a classification model to generate query classifications corresponding to product queries, conversational queries, and/or recommendation/purchase queries. Moreover, the described systems can apply the classification model to select pertinent models for particular queries. For example, upon classifying a product query, the described systems can utilize a neural ranking model (trained based on a set of training product specifications and training queries) to generate relevance scores for product specifications associated with a digital query.

Abstract: An apparatus includes a central processing unit (CPU) core and a cache subsystem coupled to the CPU core. The cache subsystem includes a memory configured to store a line of data and an error correcting code (ECC) syndrome associated with the line of data, where the ECC syndrome is calculated based on the line of data and the ECC syndrome is a first type ECC. The cache subsystem also includes a controller configured to, in response to a request from a master configured to implement a second type ECC, the request being directed to the line of data, transform the first type ECC syndrome for the line of data to a second type ECC syndrome send a response to the master. The response includes the line of data and the second type ECC syndrome associated with the line of data.

Abstract: Described herein is an Autonomous Conversational AI system, which does not require any human configuration or annotation, and is used to have multi-tum dialogs with a user. A typical Conversational AI system consists of three main models: Natural Language Understanding (NLU), Dialog Manager (DM) and Natural Language Generation (NLG), which requires human provided data and configuration. The system proposed herein leverages novel Conversational AI methods which automatically generates conversational AI configuration from any historical conversation logs. The automatically generated configuration contains Auto-Topics, Auto-Subtopics, Auto-Intents, Auto-Responses and Auto-Flows which are used to automatically train NLU, DM and NLG models. Once these models are trained for given conversation logs, the system can be used to have dialog with any user.

Abstract: Systems and methods for key-phrase extraction are described. The systems and methods include receiving a transcript including a text paragraph and generating key-phrase data for the text paragraph using a key-phrase extraction network. The key-phrase extraction network is trained to identify domain-relevant key-phrase data based on domain data obtained using a domain discriminator network. The systems and methods further include generating meta-data for the transcript based on the key-phrase data.

Abstract: A system and method for natural language communication between a user and a multifunction peripheral incorporates a chatbot. The chatbot response to verbal user commands or inquiries with corresponding device reports or operation. The chatbot operates in conjunction monitored multifunction peripheral states and document processing jobs, and tenders a verbal reply accordingly, supplying information to inform the user of additional matters related to the inquiry and of likely usefulness to the user.

Abstract: A temperature detection system (10) comprising a layer of spin cross-over material (11) in thermal contact with a target surface (12); at least one first light source (13) configured to provide a first and a second illumination (13a, 33a) of at least a first portion (12a) of the layer of spin cross-over material (11); at least one first light receiver (14) configured to capture first and second return light (14b, 34b) coming from the layer of spin cross-over material (11) and resulting respectively from the first and second illuminations; generate a first signal (S1) based on the first return light (14b); and generate a second signal (S2) based on the second return light (34b); a computation circuit (15, 17) configured to determine, based at least on a correlation between the first and second signals (S1, S2), a temperature of the layer of spin cross-over material (11).

Abstract: A method and system for training a machine learning model for point of gaze prediction simultaneously analyzes the image of the scene and the image of the driver's face using the machine learning model to generate a point of gaze of a driver in traffic environments. The machine learning model comprises a camera calibration module that can compute an embedding vector that represents the spatial configuration between the driver and the camera system. The camera calibration module improves the overall model's performance, which is jointly trained end to end.

Abstract: Techniques for training a first neural network (NN) model using a pre-trained second NN model are disclosed. In an example, training data is input to the first and second models. The training data includes masked tokens and unmasked tokens. In response, the first model generates a first prediction associated with a masked token and a second prediction associated with an unmasked token, and the second model generates a third prediction associated with the masked token and a fourth prediction associated with the unmasked token. The first model is trained, based at least in part on the first, second, third, and fourth predictions. In another example, a prediction associated with a masked token, a prediction associated with an unmasked token, and a prediction associated with whether two sentences of training data are adjacent sentences are received from each of the first and second models. The first model is trained using the predictions.

Abstract: Systems and methods for natural language processing are described. One or more aspects of a method, apparatus, and non-transitory computer readable medium include receiving a text phrase; encoding the text phrase using an encoder to obtain a hidden representation of the text phrase, wherein the encoder is trained during a first training phrase using self-supervised learning based on a first contrastive loss and during a second training phrase using supervised learning based on a second contrastive learning loss; identifying an intent of the text phrase from a predetermined set of intent labels using a classification network, wherein the classification network is jointly trained with the encoder in the second training phase; and generating a response to the text phrase based on the intent.

Abstract: A computer-implemented method is disclosed for determining one or more characteristics of a dialog between a computer system and user. The method may comprise receiving a system utterance comprising one or more tokens defining one or more words generated by the computer system; receiving a user utterance comprising one or more tokens defining one or more words uttered by a user in response to the system utterance, the system utterance and the user utterance forming a dialog context; receiving one or more utterance candidates comprising one or more tokens; for each utterance candidate, generating an input sequence combining the one or more tokens of each of the system utterance, the user utterance, and the utterance candidate; and for each utterance candidate, evaluating the generated input sequence with a model to determine a probability that the utterance candidate is relevant to the dialog context.

Abstract: A system and method for natural language communication between a user and a multifunction peripheral incorporates a chatbot. The chatbot response to verbal user commands or inquiries with corresponding device reports or operation. The chatbot operates in conjunction monitored multifunction peripheral states and document processing jobs, and tenders a verbal reply accordingly, supplying information to inform the user of additional matters related to the inquiry and of likely usefulness to the user.

Abstract: A system and method is provided for voice activated or touchless file transfer between connected devices. User input for device transfer setup is received identifying a device of interest for file transfer, along with a friendly device name, along with user credentials for device access. Transfer of electronic documents, including scan files or download files, may be initiated by a device such as a multifunction peripheral by a verbal command by a user corresponding to the setup information.

Abstract: The technology described herein is directed to a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.

Abstract: Provided herein are nucleic acid constructs, host insect cells, and methods for producing recombinant AAV capsids with high potency at high yield.

Abstract: The present disclosure describes a model for large scale color prediction of objects identified in images. Embodiments of the present disclosure include an object detection network, an attention network, and a color classification network. The object detection network generates object features for an object in an image and may include a convolutional neural network (CNN), region proposal network, or a ResNet. The attention network generates an attention vector for the object based on the object features, wherein the attention network takes a query vector based on the object features, and a plurality of key vector and a plurality of value vectors corresponding to a plurality of colors as input. The color classification network generates a color attribute vector based on the attention vector, wherein the color attribute vector indicates a probability of the object including each of the plurality of colors.

Abstract: The present invention relates generally to the field of providing a computer-implemented system and method that supports ad hoc multilingual Natural Language database questions that are transformed in realtime to Database queries using a suite of cascading Deep Neural Networks which are initially and continuously trained through schema information and question-query examples.

Abstract: The dual inlet exhaust design for the flying device incorporates easy-to-assemble designs with low number of components, suitable for limited space and small volume requirements, good performance. The exhaust is designed as a three-chamber cylinder with two coaxial inlet pipes running through the two chambers on both sides, extending into the middle compartment. The width of the two inlet tubes in the middle compartment is different. The inlet pipe at the two compartments on both sides has a bore. The outlet tube is located in the middle compartment, deviating to the side with a smaller expansion inlet, with the longitudinal axis of the outlet tube passing through the inlet tube.

Abstract: Devices and methods for treatment of a patient's vasculature are described. Embodiments may include an implant having multiple mesh layers. A first and second layer of the implant may be formed by folding over a single mesh and the third layer may be formed from a different mesh. The first, second, and third layers may be either a stasis or a structural layer and may be arranged in different orders. Embodiments may also include structures to assist in the expansion of the device. These structures may include an expandable loop or reinforcing finger extensions. Embodiments may also include a corrugation or ridge around a middle section of the implant to assist in deployment.