Abstract: Disclosed herein are arrangements that facilitate the transfer of knowledge from models for a source data-processing domain to models for a target data-processing domain. A convolutional neural network space for a source domain is factored into a first classification space and a first reconstruction space. The first classification space stores class information and the first reconstruction space stores domain-specific information. A convolutional neural network space for a target domain is factored into a second classification space and a second reconstruction space. The second classification space stores class information and the second reconstruction space stores domain-specific information. Distribution of the first classification space and the second classification space is aligned.

Abstract: Techniques are disclosed for deep neural network (DNN) based interactive image matting. A methodology implementing the techniques according to an embodiment includes generating, by the DNN, an alpha matte associated with an image, based on user-specified foreground region locations in the image. The method further includes applying a first DNN subnetwork to the image, the first subnetwork trained to generate a binary mask based on the user input, the binary mask designating pixels of the image as background or foreground. The method further includes applying a second DNN subnetwork to the generated binary mask, the second subnetwork trained to generate a trimap based on the user input, the trimap designating pixels of the image as background, foreground, or uncertain status. The method further includes applying a third DNN subnetwork to the generated trimap, the third subnetwork trained to generate the alpha matte based on the user input.

Abstract: An electrostatic discharge protection structure for a nitride-based device having an active region, an electrostatic discharge protection region outside the active region for forming the electrostatic discharge protection structure, and a field plate formed in the active region is provided. The electrostatic discharge protection structure includes a channel layer, and a barrier layer, a first p-type nitride layer and a metal layer formed on the channel layer in such order. The metal layer is electrically connected to the field plate in the active region. A nitride-based device having the electrostatic discharge protection structure and a method for manufacturing a nitride-based device is also disclosed.

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: 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: Remote distribution of multiple neural network models to various client devices over a network can be implemented by identifying a native neural network and remotely converting the native neural network to a target neural network based on a given client device operating environment. The native neural network can be configured for execution using efficient parameters, and the target neural network can use less efficient but more precise parameters.

Abstract: An immersion fluid recovery system and an immersion fluid recovery method using said system.

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 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: Systems, methods, devices, media, and computer readable instructions are described for local image tagging in a resource constrained environment. One embodiment involves processing image data using a deep convolutional neural network (DCNN) comprising at least a first subgraph and a second subgraph, the first subgraph comprising at least a first layer and a second layer, processing, the image data using at least the first layer of the first subgraph to generate first intermediate output data; processing, by the mobile device, the first intermediate output data using at least the second layer of the first subgraph to generate first subgraph output data, and in response to a determination that each layer reliant on the first intermediate data have completed processing, deleting the first intermediate data from the mobile device. Additional embodiments involve convolving entire pixel resolutions of the image data against kernels in different layers if the DCNN.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that generate inpainted digital images utilizing class-specific cascaded modulation inpainting neural network. For example, the disclosed systems utilize a class-specific cascaded modulation inpainting neural network that includes cascaded modulation decoder layers to generate replacement pixels portraying a particular target object class. To illustrate, in response to user selection of a replacement region and target object class, the disclosed systems utilize a class-specific cascaded modulation inpainting neural network corresponding to the target object class to generate an inpainted digital image that portrays an instance of the target object class within the replacement region.

Abstract: A semiconductor device includes a substrate and a semiconductor structure that is located on the substrate and that includes a device portion including a semiconductor element, and a seal ring portion. The semiconductor element includes a first electrode and a second electrode. The seal ring portion surrounds the device portion and includes a conducting element. The conducting element includes an enhanced-High-Electron-Mobility-Transistor (eHEMT) that includes a first gate electrode electrically connected to the first electrode, a first source electrode electrically connected to the second electrode, and a first drain electrode electrically connect to the first electrode. A method for making the semiconductor device and a seal ring structure are also provided.

Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that generate inpainted digital images utilizing a cascaded modulation inpainting neural network. For example, the disclosed systems utilize a cascaded modulation inpainting neural network that includes cascaded modulation decoder layers. For example, in one or more decoder layers, the disclosed systems start with global code modulation that captures the global-range image structures followed by an additional modulation that refines the global predictions. Accordingly, in one or more implementations, the image inpainting system provides a mechanism to correct distorted local details. Furthermore, in one or more implementations, the image inpainting system leverages fast Fourier convolutions block within different resolution layers of the encoder architecture to expand the receptive field of the encoder and to allow the network encoder to better capture global structure.

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: An Internet-of-Things management and control system for an intelligent orchard includes a server, agricultural machinery equipment, an image acquisition apparatus disposed on the site, and various sensors. The agricultural machinery equipment, the image acquisition apparatus and the various sensors are in communication connection with the server. The server includes an orchard management subsystem and an information monitoring subsystem. The orchard management subsystem includes a fruit tree planting planning module, a task management module and various information management modules, and the information monitoring subsystem includes a meteorological environment monitoring module, a soil moisture monitoring module and a disease and pest monitoring module. According to the Internet-of-Things management and control system, all-round management for an orchard from planning to picking can be achieved.

Abstract: Embodiments of the present disclosure are directed towards improved models trained using unsupervised domain adaptation. In particular, a style-content adaptation system provides improved translation during unsupervised domain adaptation by controlling the alignment of conditional distributions of a model during training such that content (e.g., a class) from a target domain is correctly mapped to content (e.g., the same class) in a source domain. The style-content adaptation system improves unsupervised domain adaptation using independent control over content (e.g., related to a class) as well as style (e.g., related to a domain) to control alignment when translating between the source and target domain. This independent control over content and style can also allow for images to be generated using the style-content adaptation system that contain desired content and/or style.

Abstract: A method, apparatus and computer program product are provided for generating a registered certified seal, sealing an asset, and verifying a sealed asset. In an example embodiment, a method is provided for receiving a request to generate a registered certified seal from an entity, accessing certifier entity data via a uniform resource locator of a certification authority identified by a certifying certificate, and verifying a digitally signed entity certifying certificate. The method further comprises upon verifying the digitally signed entity certifying certificate, receiving seal data comprising a seal data key for a certified seal, and saving the seal data for the entity within a digital seal registry, wherein the digital seal registry is searchable based at least in part on at least a portion of the seal data key.

Abstract: The present disclosure provided a lateral field-effect transistor and its preparing method, relating to semiconductor technological field. A gate pad and a source pad configured by the lateral field transistor in a passive region extend from a first surface of a device functional layer to a surface of substrate respectively. The gate pad is isolated from the device functional layer and the substrate respectively. The source pad is shorted to the substrate. Therefore, through a capacitance structure formed between the gate pad and the source pad shorted to the substrate, the capacitance of a device that formed between the gate pad and source pad may be increased, thereby effectively alleviating the generated oscillation, reducing the loss of a power device, and avoiding the false turn-on of the lateral field-effect transistor.

Abstract: A method, apparatus and computer program product are provided for encrypting and decrypting data using multiple authority keys including receiving, from a first computing device, a data decrypt request to decrypt encrypted data, the data decrypt request comprising a user key, determining that the user key is associated with a key hierarchy that comprises a server key, decrypting the server key using the user key, decrypting the encrypted data using the decrypted server key and permitting access to the decrypted data by the first computing device.