Abstract: Examples are disclosed that relate to representing recorded hand motion. One example provides a computing device comprising a logic subsystem and a storage subsystem comprising instructions executable by the logic subsystem to receive a recorded representation of hand motion determined relative to a virtual model aligned to a first instance of an object, receive image data corresponding to an environment, and recognize a second instance of the object in the environment. The instructions are further executable to align the virtual model to the second instance of the object, and output a parametric representation of hand motion for display relative to the virtual model as aligned to the second instance of the object, such that the parametric representation is spatially consistent with the recorded representation of hand motion relative to the virtual model as aligned to the first instance of the object.

Abstract: Systems, devices, methods, media, and instructions for automated image processing and content curation are described. In one embodiment a server computer system communicates at least a portion of a first content collection to a first client device, and receives a first selection communication in response, the first selection communication identifying a first piece of content of the first plurality of pieces of content. The server analyzes analyzing the first piece of content to identify a set of context values for the first piece of content, and accesses accessing a second content collection comprising pieces of content sharing at least a portion of the set of context values of the first piece of content. In various embodiments, different content values, image processing operations, and content selection operations are used to curate the content collections.

Abstract: A method and an apparatus for training a transferable vision transformer (TVT) for unsupervised domain adaption (UDA) in heterogeneous devices are provided. The method includes that a heterogeneous device including one or more graphic processing units (GPUs) loads multiple patches into the TVT which includes a transferability adaption module (TAM). Furthermore, a patch-level domain discriminator in the TAM assigns weights to the multiple patches and determines one or more transferable patches based on the weights. Moreover, the heterogeneous device generates a transferable attention output for an attention module in the TAM based on the one or more transferable patches.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a progressive refinement network to refine alpha mattes generated utilizing a mask-guided matting neural network. In particular, the disclosed systems can use the matting neural network to process a digital image and a coarse guidance mask to generate alpha mattes at discrete neural network layers. In turn, the disclosed systems can use the progressive refinement network to combine alpha mattes and refine areas of uncertainty. For example, the progressive refinement network can combine a core alpha matte corresponding to more certain core regions of a first alpha matte and a boundary alpha matte corresponding to uncertain boundary regions of a second, higher resolution alpha matte. Based on the combination of the core alpha matte and the boundary alpha matte, the disclosed systems can generate a final alpha matte for use in image matting processes.

Abstract: A method and a device for predicting food safety risk level section are provided in the present application. The method includes: obtaining risk level time series data of the food; decomposing the risk level time series data to obtain a plurality of sub-series data; performing point predictions on the plurality of sub-series data to obtain corresponding point prediction results; determining a final point prediction result corresponding to the food risk level time series data based on the point prediction results corresponding to the plurality of sub-series data; determining a prediction residual corresponding to the final point prediction result; and determining a section prediction result by performing section prediction based on the prediction residua. In the present application, more prediction information and quantitative prediction of the uncertainty of future food risks are provided by adding section prediction based on point prediction.

Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that perform language guided digital image editing utilizing a cycle-augmentation generative-adversarial neural network (CAGAN) that is augmented using a cross-modal cyclic mechanism. For example, the disclosed systems generate an editing description network that generates language embeddings which represent image transformations applied between a digital image and a modified digital image. The disclosed systems can further train a GAN to generate modified images by providing an input image and natural language embeddings generated by the editing description network (representing various modifications to the digital image from a ground truth modified image). In some instances, the disclosed systems also utilize an image request attention approach with the GAN to generate images that include adaptive edits in different spatial locations of the image.

Abstract: Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize a neural network having a long short-term memory encoder-decoder architecture to progressively modify a digital image in accordance with a natural language request. For example, in one or more embodiments, the disclosed systems utilize a language-to-operation decoding cell of a language-to-operation neural network to sequentially determine one or more image-modification operations to perform to modify a digital image in accordance with a natural language request. In some cases, the decoding cell determines an image-modification operation to perform partly based on the previously used image-modification operations. The disclosed systems further utilize the decoding cell to determine one or more operation parameters for each selected image-modification operation. The disclosed systems utilize the image-modification operation(s) and operation parameter(s) to modify the digital image (e.g.

Abstract: Disclosed are a method and an apparatus for string connecting photovoltaic modules. The method includes: acquiring position information of n photovoltaic modules to be connected; categorizing the n photovoltaic modules into m partitions based on the position information of the n photovoltaic modules; generating k candidate connection solutions of an ith partition in the m partitions, wherein the ith partition includes m photovoltaic modules, and each of the k candidate connection solutions uses one photovoltaic module in the m photovoltaic modules as a starting point, and obtaining at least one string of photovoltaic modules by simulating connection of the m photovoltaic modules according to a preset connection solution; and selecting a target connection solution from the k candidate connection solutions based on an estimated cable use amount corresponding to each of the k candidate connection solutions.

Abstract: Examples are disclosed that relate to representing recorded hand motion. One example provides a computing device comprising a logic subsystem and a storage subsystem comprising instructions executable by the logic subsystem to receive a recorded representation of hand motion determined relative to a virtual model aligned to a first instance of an object, receive image data corresponding to an environment, and recognize a second instance of the object in the environment. The instructions are further executable to align the virtual model to the second instance of the object, and output a parametric representation of hand motion for display relative to the virtual model as aligned to the second instance of the object, such that the parametric representation is spatially consistent with the recorded representation of hand motion relative to the virtual model as aligned to the first instance of the object.

Abstract: Systems and methods are described for determining a first media item related to an event, of a plurality of stored media items each comprising video content related to the event, that was captured in a device orientation corresponding to a first device orientation detected for the first computing device; providing, to the first computing device, the first media item to be displayed on the first computing device; in response to a detected change to a second device orientation for the first computing device, determining a second media item that was captured in a device orientation corresponding to the second device orientation detected for the first computing device; and providing, to the first computing device, the second media item to be displayed on the first computing device.

Abstract: Sentiment classification can be implemented by an entity-level multimodal sentiment classification neural network. The neural network can include left, right, and target entity subnetworks. The neural network can further include an image network that generates representation data that is combined and weighted with data output by the left, right, and target entity subnetworks to output a sentiment classification for an entity included in a network post.

Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.

Abstract: An acoustic environment identification system is disclosed that can use neural networks to accurately identify environments. The acoustic environment identification system can use one or more convolutional neural networks to generate audio feature data. A recursive neural network can process the audio feature data to generate characterization data. The characterization data can be modified using a weighting system that weights signature data items. Classification neural networks can be used to generate a classification of an environment.

Abstract: Examples are disclosed that relate to representing recorded hand motion. One example provides a computing device comprising a logic subsystem and a storage subsystem comprising instructions executable by the logic subsystem to receive a recorded representation of hand motion determined relative to a virtual model aligned to a first instance of an object, receive image data corresponding to an environment, and recognize a second instance of the object in the environment. The instructions are further executable to align the virtual model to the second instance of the object, and output a parametric representation of hand motion for display relative to the virtual model as aligned to the second instance of the object, such that the parametric representation is spatially consistent with the recorded representation of hand motion relative to the virtual model as aligned to the first instance of the object.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize a neural network having a long short-term memory encoder-decoder architecture to progressively modify a digital image in accordance with a natural language request. For example, in one or more embodiments, the disclosed systems utilize a language-to-operation decoding cell of a language-to-operation neural network to sequentially determine one or more image-modification operations to perform to modify a digital image in accordance with a natural language request. In some cases, the decoding cell determines an image-modification operation to perform partly based on the previously used image-modification operations. The disclosed systems further utilize the decoding cell to determine one or more operation parameters for each selected image-modification operation. The disclosed systems utilize the image-modification operation(s) and operation parameter(s) to modify the digital image (e.g.

Abstract: Systems and methods are described for determining a first media item related to an event, of a plurality of stored media items each comprising video content related to the event, that was captured in a device orientation corresponding to a first device orientation detected for the first computing device; providing, to the first computing device, the first media item to be displayed on the first computing device; in response to a detected change to a second device orientation for the first computing device, determining a second media item that was captured in a device orientation corresponding to the second device orientation detected for the first computing device; and providing, to the first computing device, the second media item to be displayed on the first computing device.

Abstract: An image data annotation system automatically annotates a physical object within individual images frames of an image sequence with relevant object annotations based on a three-dimensional (3D) model of the physical object. Annotating the individual image frames with object annotations includes updating individual image frames within image input data to generate annotated image data that is suitable for reliably training a DNN object detection architecture. Exemplary object annotations that the image data annotation system can automatically apply to individual image frames include, inter alia, object pose, image pose, object masks, 3D bounding boxes composited over the physical object, 2D bounding boxes composited over the physical object, and/or depth map information.

Abstract: Embodiments of the present disclosure provide a method, a computer program product and apparatus for processing transactions in a synchronized replication system, wherein the method comprises, at a source site in the synchronized replication system: serializing commits of transactions in the synchronized replication system so that only one of the transactions can be committed at the same time; in response to initiating the commit of the one transaction, generating a log for each of transactions that are ongoing in the synchronized replication system, so as to record impact of all operations of a respective transaction on the synchronized replication system; marking transactions for which the logs have been generated; and completing commits of the marked transactions.