Abstract: System and method for adjusting side mirrors capture, by a primary camera, a facial image of a driver; estimate a 3D eye location with respect to a 3D coordinate of the primary camera based on the captured facial image; map the estimated 3D eye location to a respective set of pitch and yaw of the side mirror based on a look up table; and rotate the side mirror to a target position in accordance with the respective set of pitch and yaw. The lookup table includes a plurality of rows, each containing a pair of a key and a set of values. The key is a set of three parameters of 3D line of locations where the driver can observe an optimal view behind the vehicle, and the set of values includes a set of pitch and yaw of the side mirror corresponding to the 3D line of locations.

Abstract: A method for adjusting a side mirror of a vehicle includes capturing, by a primary camera provided in front of a driver of the vehicle, a facial image of the driver; estimating a 3D eye location with respect to a 3D coordinate of the primary camera based on the captured facial image; mapping the estimated 3D eye location to a respective set of pitch and yaw angles of the side mirror based on a lookup table; and rotating the side mirror to a target position in accordance with the respective set of pitch and yaw angles. The lookup table includes a plurality of rows, each row containing a pair of a key and a set of values. The key is a 3D eye location, and the set of values includes a set of pitch and yaw angles of the side mirror corresponding to the 3D eye location.

Abstract: Software instructions are executed on a processor within a computer system to configure a steaming engine with stream parameters to define a multidimensional array. The stream parameters define a size for each dimension of the multidimensional array and a pad value indicator. Data is fetched from a memory coupled to the streaming engine responsive to the stream parameters. A stream of vectors is formed for the multidimensional array responsive to the stream parameters from the data fetched from memory. A padded stream vector is formed that includes a specified pad value without accessing the pad value from system memory.

Abstract: A streaming engine in a system receives a first set of stream parameters into a queue to define a first stream along with an indication of either a queue mode of operation or a speculative mode of operation for the first stream. Acquisition of the first stream then begins. At some point, a second set of stream parameters is received into the queue to define a second stream. When the queue mode of operation was specified for the first stream, the second set of parameters is queued and acquisition of the second stream is delayed until completion of acquisition of the first stream. When the speculative mode of operation was specified for the first stream, acquisition of the first stream is canceled upon receipt of the second set of stream parameters and acquisition of the second stream begins immediately.

Abstract: Systems and methods for color prediction are described. Embodiments of the present disclosure receive an image that includes an object including a color, generate a color vector based on the image using a color classification network, where the color vector includes a color value corresponding to each of a set of colors, generate a bias vector by comparing the color vector to teach of a set of center vectors, where each of the set of center vectors corresponds to a color of the set of colors, and generate an unbiased color vector based on the color vector and the bias vector, where the unbiased color vector indicates the color of the object.

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: Systems and methods for intent discovery and video summarization are described. Embodiments of the present disclosure receive a video and a transcript of the video, encode the video to obtain a sequence of video encodings, encode the transcript to obtain a sequence of text encodings, apply a visual gate to the sequence of text encodings based on the sequence of video encodings to obtain gated text encodings, and generate an intent label for the transcript based on the gated text encodings.

Abstract: A system includes a memory controller, multiple memories coupled to the memory controller, and multiple controlling components coupled to the memory controller. The memory controller calculates an error correction code (ECC) syndrome of a first type for a segment of data; stores the segment of data and the ECC syndrome of the first type in a first memory of the multiple memories; receives a request from a controlling component of the multiple controlling components directed to the segment of data, the controlling component implementing an ECC syndrome of a second type; transforms the ECC syndrome of the first type for the segment of data to the ECC syndrome of the second type; detects a number of errors, if any, present in the segment of data; and takes further action depending on how many errors are detected.

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: 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.