Abstract: An example computing platform comprising is configured to (i) receive, via one or more cameras positioned on a construction site, a plurality of images, (ii) detect, within the plurality of images, a plurality of objects being worn by respective workers on the construction site, (iii) select, from the plurality of images, a set of images depicting a particular worker, and (iv) based on the selected set of images depicting the particular worker, determine a plurality of trade probabilities for the particular worker, each trade probability in the plurality of trade probabilities indicating a likelihood that the particular worker belongs to a particular trade from among a plurality of trades.

Abstract: In one embodiment, a method includes receiving a user request to automatically debug a natural-language understanding (NLU) model, accessing a plurality of predicted semantic representations generated by the NLU model, wherein the plurality of predicted semantic representations are associated with a plurality of dialog sessions, respectively, wherein each dialog session is between a user and an assistant xbot associated with the NLU model, generating a plurality of expected semantic representations associated with the plurality of dialog sessions based on an auto-correction model, wherein the auto-correction model is learned from dialog training samples generated based on active learning, identifying incorrect semantic representations of the predicted semantic representations based on a comparison between the predicted semantic representations and the expected semantic representations, and automatically correcting the incorrect semantic representations by replacing them with respective expected semantic repre

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: Techniques are described for automating virtual placements in video content.

Abstract: Techniques are disclosed for detecting a type of prurient activity shown by a portion of video content. In an example, a machine learning model of a computer system may receive a second portion of video content, the machine learning model including a neural network that is trained to analyze a temporal dimension of the second portion. The machine learning model determines a score indicating a likelihood that the video content shows the type of prurient activity based in part on applying a three-dimensional filter to the second portion of the video content. The computer system then generates a video clip that includes at least the portion of the video content showing the type of prurient activity based on the score, and provides the video clip for display.

Abstract: An example computing platform comprising is configured to (i) receive, via one or more cameras positioned on a construction site, a plurality of images, (ii) detect, within the plurality of images, a plurality of objects being worn by respective workers on the construction site, (iii) select, from the plurality of images, a set of images depicting a particular worker, and (iv) based on the selected set of images depicting the particular worker, determine a plurality of trade probabilities for the particular worker, each trade probability in the plurality of trade probabilities indicating a likelihood that the particular worker belongs to a particular trade from among a plurality of trades.

Abstract: In one embodiment, a method includes receiving a user request to automatically debug a natural-language understanding (NLU) model, accessing a plurality of predicted semantic representations generated by the NLU model, wherein the plurality of predicted semantic representations are associated with a plurality of dialog sessions, respectively, wherein each dialog session is between a user and an assistant xbot associated with the NLU model, generating a plurality of expected semantic representations associated with the plurality of dialog sessions based on an auto-correction model, wherein the auto-correction model is learned from dialog training samples generated based on active learning, identifying incorrect semantic representations of the predicted semantic representations based on a comparison between the predicted semantic representations and the expected semantic representations, and automatically correcting the incorrect semantic representations by replacing them with respective expected semantic repre

Abstract: A computer-implemented method and system for neural network-based recognition of trade workers present on industrial sites is presented.

Abstract: Techniques are described for automating virtual placements in video content.

Abstract: In one embodiment, a method includes receiving a user input comprising one or more words at a client system, wherein each word comprises one or more characters, inputting the words to a convolutional neural network (CNN) model stored on the client system, accessing a plurality of character-embeddings for a plurality of characters, respectively, from a data store of the client system, generating one or more word-embeddings for the one or more words, respectively, based on the accessed character-embeddings by processing the accessed character-embeddings with one or more convolutional layers and one or more gated linear units of the CNN model, determining one or more tasks corresponding to the user input for execution based on an analysis of the one or more word-embeddings by the CNN model, and providing an output responsive to the user input based on the execution of the one or more tasks at the client system.

Abstract: In one embodiment, a method includes receiving a user input by the first user from a client system associated with a first user, parsing the user input to identify one or more n-grams associated with the user input, accessing a user profile associated with the first user, wherein the user profile is stored in a first data store, accessing ontology data based on the one or more identified n-grams from one or more information graphs, wherein the one or more information graphs are stored in one or more second data stores, respectively, determining contextual information associated with the user input, generating semantic information by aggregating the user profile, ontology data, and contextual information, generating a feature representation for the identified one or more n-grams based on the semantic information, and resolving one or more entities associated with the one or more n-grams based on the feature representation.

Abstract: In one embodiment, a method includes receiving, by a first client system, from one or more remote servers, a current version of a global neural network model including multiple federated model parameters, accessing, from a local data store, multiple examples and a local personalization model including multiple local model parameters, wherein each of the examples includes one or more features and one or more labels, training the global neural network model and the local personalization model together on the examples to generate multiple updated federated model parameters and multiple updated local model parameters, storing, in the local data store, the trained local personalization model including the updated local model parameters, and sending, to one or more of the remote servers, the trained global neural network model including the updated federated model parameters.

Abstract: In one embodiment, a method includes receiving a user input comprising one or more words at a client system, wherein each word comprises one or more characters, inputting the words to a convolutional neural network (CNN) model stored on the client system, accessing a plurality of character-embeddings for a plurality of characters, respectively, from a data store of the client system, generating one or more word-embeddings for the one or more words, respectively, based on the accessed character-embeddings by processing the accessed character-embeddings with one or more convolutional layers and one or more gated linear units of the CNN model, determining one or more tasks corresponding to the user input for execution based on an analysis of the one or more word-embeddings by the CNN model, and providing an output responsive to the user input based on the execution of the one or more tasks at the client system.

Abstract: A computer-implemented method and system for neural network-based recognition of trade workers present on industrial sites is presented.

Abstract: A method and a system for patch-based scene segmentation using neural networks are presented. In an embodiment, a method comprises: using one or more computing devices, receiving a digital image comprising test image; using the one or more computing devices, creating, based on the test image, a plurality of grid patches; using the one or more computing devices, receiving a plurality of classifiers that have been trained to identify one or more materials of a plurality of materials; using the one or more computing devices, for each patch of the plurality of grid patches, labelling each pixel of a patch with a label obtained by applying, to the patch, one or more classifiers from the plurality of classifiers; using the one or more computing devices, generating, based on labels assigned to pixels of the plurality of grid patches, a grid of labels for the test image.

Abstract: A computer-implemented method and system for neural network-based recognition of trade workers present on industrial sites is presented.

Abstract: Systems and methods for security in power systems are provided. A security-aware distributed control framework for resilient operation of power systems can detect and mitigate different types of attacks that might target power systems. The framework can discover a change in the features of transmitted data from neighbor agents, discard an infected agent, and achieve an updated consensus protocol agreement while satisfying a control system objective.

Abstract: A method and a system for patch-based scene segmentation using neural networks are presented. In an embodiment, a method comprises: using one or more computing devices, receiving a digital image comprising test image; using the one or more computing devices, creating, based on the test image, a plurality of grid patches; using the one or more computing devices, receiving a plurality of classifiers that have been trained to identify one or more materials of a plurality of materials; using the one or more computing devices, for each patch of the plurality of grid patches, labelling each pixel of a patch with a label obtained by applying, to the patch, one or more classifiers from the plurality of classifiers; using the one or more computing devices, generating, based on labels assigned to pixels of the plurality of grid patches, a grid of labels for the test image.

Abstract: A computer-implemented method and system for neural network-based recognition of trade workers present on industrial sites is presented.

Abstract: This disclosure describes techniques that relate generally to the collection, processing, storage, and graphical representation of medical imaging data associated with patient care. Medical imaging data may be processed using object recognition algorithms to help determined pertinent medical characteristics. Further, a graphical fusion application may generate a graphical representation of medical data that is based at least in part on a combination of medical imaging data and corresponding interpretation data. The graphical representation may overlay a schematic diagram of a relevant organ system, so as to provide a medical practitioner with a visual, more specifically graphical, indication of the medical imaging data. Interpretation data of pertinent medical characteristics may be generated by an automated analysis of the medical imaging data.