Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.

Abstract: A curable silicone adhesive having improved elongation-at-break and adhesive properties to various substrates, in particular synthetic textiles used in the manufacture of air bags, to be used, for example, as a joint sealer. These silicone compositions provide excellent adhesive properties such as peel strength and cohesive failure when used to seal joints/seams between two pieces of textile fabric. Airbag fabrics using such novel addition curable adhesive silicone compositions are also provided.

Abstract: The present invention relates to an article useful for circular economy which comprises of a substrate S in contact with a cured silicone elastomer Z which is peelable with clean-releasing properties and which can be easily removed by human force. The invention also relates to a recycling method comprised of peeling off the cured silicone elastomer Z from the support S of the article according to the invention and then recycling or re-using said article.

Abstract: Techniques are described for white balancing an input image by determining a color transformation for the input image based on color transformations that have been computed for training images whose color characteristics are similar to those of the input image. Techniques are also described for generating a training dataset comprising color information for a plurality of training images and color transformation information for the plurality of training images. The color information in the training dataset is searched to identify a subset of training images that are most similar in color to the input image. The color transformation for the input image is then computed by combining color transformation information for the identified training images. The contribution of the color transformation information for any given training image to the combination can be weighted based on the degree of color similarity between the input image and the training image.

Abstract: An oil-based slurry that includes oil, a suspension package, a dispersion agent, a surfactant, and a dry water-soluble polymer.

Abstract: Described techniques for multi-label classification, in which sequential data includes characters that have two or more aspects that require classification, are capable of providing separate classifications for different categories of components. Using an appropriately-trained neural network, the described techniques perform aligning and otherwise combining two or more classifications (e.g., categories, or types of labels) to obtain multi-label characters.

Abstract: Computing systems and computer-implemented methods can be used for automatically generating a digital line drawing of the contents of a photograph. In various examples, these techniques include use of a neural network, referred to as a generator network, that is trained on a dataset of photographs and human-generated line drawings of the photographs. The training data set teaches the neural network to trace the edges and features of objects in the photographs, as well as which edges or features can be ignored. The output of the generator network is a two-tone digital image, where the background of the image is one tone, and the contents in the input photographs are represented by lines drawn in the second tone. In some examples, a second neural network, referred to as a restorer network, can further process the output of the generator network, and remove visual artifacts and clean up the lines.

Abstract: A two-part curable liquid silicone rubber composition is provided in which the first liquid composition and the second liquid composition yield, upon mixing, a curable liquid silicone rubber composition which, when cured, yields a silicone elastomer having an elongation-at-break value of at least 800%. The silicone elastomers of the invention comprise at least one alkenyl group-containing organopolysiloxane having two silicon-bonded alkenyl groups per molecule, at least one diorganohydrogensiloxy-terminated polydiorganosiloxane, at least one organosilicon crosslinker containing at least 3 silicon-bonded hydrogen atoms per molecule, at least one addition reaction catalyst, and at least one filler. Also provided are silicone elastomers having an elongation-at-break value of at least 800% and withstand elongation without breaking. An article for a medical device comprising a cured product of the two-part curable liquid silicone rubber compositions or the silicone elastomers of the invention are also provided.

Abstract: A temporal object segmentation system determines a location of an object depicted in a video. In some cases, the temporal object segmentation system determines the object's location in a particular frame of the video based on information indicating a previous location of the object in a previous video frame. For example, an encoder neural network in the temporal object segmentation system extracts features describing image attributes of a video frame. A convolutional long-short term memory neural network determines the location of the object in the frame, based on the extracted image attributes and information indicating a previous location in a previous frame. A decoder neural network generates an image mask indicating the object's location in the frame. In some cases, a video editing system receives multiple generated masks for a video, and modifies one or more video frames based on the locations indicated by the masks.

Abstract: Techniques are described for white balancing an input image by determining a color transformation for the input image based on color transformations that have been computed for training images whose color characteristics are similar to those of the input image. Techniques are also described for generating a training dataset comprising color information for a plurality of training images and color transformation information for the plurality of training images. The color information in the training dataset is searched to identify a subset of training images that are most similar in color to the input image. The color transformation for the input image is then computed by combining color transformation information for the identified training images. The contribution of the color transformation information for any given training image to the combination can be weighted based on the degree of color similarity between the input image and the training image.

Abstract: Computing systems and computer-implemented methods can be used for automatically generating a digital line drawing of the contents of a photograph. In various examples, these techniques include use of a neural network, referred to as a generator network, that is trained on a dataset of photographs and human-generated line drawings of the photographs. The training data set teaches the neural network to trace the edges and features of objects in the photographs, as well as which edges or features can be ignored. The output of the generator network is a two-tone digital image, where the background of the image is one tone, and the contents in the input photographs are represented by lines drawn in the second tone. In some examples, a second neural network, referred to as a restorer network, can further process the output of the generator network, and remove visual artifacts and clean up the lines.

Abstract: A temporal object segmentation system determines a location of an object depicted in a video. In some cases, the temporal object segmentation system determines the object's location in a particular frame of the video based on information indicating a previous location of the object in a previous video frame. For example, an encoder neural network in the temporal object segmentation system extracts features describing image attributes of a video frame. A convolutional long-short term memory neural network determines the location of the object in the frame, based on the extracted image attributes and information indicating a previous location in a previous frame. A decoder neural network generates an image mask indicating the object's location in the frame. In some cases, a video editing system receives multiple generated masks for a video, and modifies one or more video frames based on the locations indicated by the masks.

Abstract: A powder composition includes a plurality of thermoplastic particles and a plurality of flow promoting particles having an optimized flow, coalescence, or both; and methods of preparing three-dimensional articles and methods of preparing a powder coating, and articles prepared by the methods are described herein.

Abstract: Systems and techniques are described that provide for question answering using data visualizations, such as bar graphs. Such data visualizations are often generated from collected data, and provided within image files that illustrate the underlying data and relationships between data elements. The described techniques analyze a query and a related data visualization, and identify one or more spatial regions within the data visualization in which an answer to the query may be found.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.

Abstract: Provided are systems and methods for additive manufacturing, which systems and methods yield parts having improved interlayer adhesion. In the disclosed technology, additional heating steps are applied on the upper surface of the already printed workpiece so as to offset the dropping temperature of that surface during part fabrication. These heating steps elevate the temperature of the surface to a value that results in a molten interface with subsequently-applied build material, leading to improved interlayer adhesion. This technology is applicable to a variety of additive manufacturing processes, including but not limited to selective laser sintering, fused filament fabrication, and large format additive manufacturing approaches.