Abstract: The present disclosure relates to an object selection system that accurately detects and automatically selects user-requested objects (e.g., query objects) in a digital image. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of the query object. In addition, the object selection system can add, update, or replace portions of the object selection pipeline to improve overall accuracy and efficiency of automatic object selection within an image.

Abstract: The present disclosure relates to an object selection system that automatically detects and selects objects in a digital image based on natural language-based inputs. For instance, the object selection system can utilize natural language processing tools to detect objects and their corresponding relationships within natural language object selection queries. For example, the object selection system can determine alternative object terms for unrecognized objects in a natural language object selection query. As another example, the object selection system can determine multiple types of relationships between objects in a natural language object selection query and utilize different object relationship models to select the requested query object.

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: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for parsing a given input referring expression into a parse structure and generating a semantic computation graph to identify semantic relationships among and between objects. At a high level, when embodiments of the preset invention receive a referring expression, a parse tree is created and mapped into a hierarchical subject, predicate, object graph structure that labeled noun objects in the referring expression, the attributes of the labeled noun objects, and predicate relationships (e.g., verb actions or spatial propositions) between the labeled objects. Embodiments of the present invention then transform the subject, predicate, object graph structure into a semantic computation graph that may be recursively traversed and interpreted to determine how noun objects, their attributes and modifiers, and interrelationships are provided to downstream image editing, searching, or caption indexing tasks.

Abstract: The present disclosure relates to an object selection system that automatically detects and selects objects in a digital image utilizing a large-scale object detector. For instance, in response to receiving a request to automatically select a query object with an unknown object class in a digital image, the object selection system can utilize a large-scale object detector to detect potential objects in the image, filter out one or more potential objects, and label the remaining potential objects in the image to detect the query object. In some implementations, the large-scale object detector utilizes a region proposal model, a concept mask model, and an auto tagging model to automatically detect objects in the digital image.

Abstract: The invention relates to a composite material consisting of at least three constituents, a substrate material, a first fibrous reinforcing material and a second reinforcing material, wherein the first fibrous reinforcing material has a lower thermal expansion coefficient than the second reinforcing material and wherein the second reinforcing material has a lower electrical conductivity than the first reinforcing material, wherein the composite material is provided for use in building components of force and motion transmission, in particular those building components of force and motion transmission which come into contact with ultrapure water.

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: Certain embodiments involve flow-based color transfers from a source graphic to target graphic. For instance, a palette flow is computed that maps colors of a target color palette to colors of the source color palette (e.g., by minimizing an earth-mover distance with respect to the source and target color palettes). In some embodiments, such color palettes are extracted from vector graphics using path and shape data. To modify the target graphic, the target color from the target graphic is mapped, via the palette flow, to a modified target color using color information of the source color palette. A modification to the target graphic is performed (e.g., responsive to a preview function or recoloring command) by recoloring an object in the target color with the modified target color.

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: 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: Provided are systems and techniques that provide an output phrase describing an image. An example method includes creating, with a convolutional neural network, feature maps describing image features in locations in the image. The method also includes providing a skeletal phrase for the image by processing the feature maps with a first long short-term memory (LSTM) neural network trained based on a first set of ground truth phrases which exclude attribute words. Then, attribute words are provided by processing the skeletal phrase and the feature maps with a second LSTM neural network trained based on a second set of ground truth phrases including words for attributes. Then, the method combines the skeletal phrase and the attribute words to form the output phrase.

Abstract: Certain embodiments involve flow-based color transfers from a source graphic to target graphic. For instance, a palette flow is computed that maps colors of a target color palette to colors of the source color palette (e.g., by minimizing an earth-mover distance with respect to the source and target color palettes). In some embodiments, such color palettes are extracted from vector graphics using path and shape data. To modify the target graphic, the target color from the target graphic is mapped, via the palette flow, to a modified target color using color information of the source color palette. A modification to the target graphic is performed (e.g., responsive to a preview function or recoloring command) by recoloring an object in the target color with the modified target color.

Abstract: The present disclosure relates to an object selection system that accurately detects and automatically selects user-requested objects (e.g., query objects) in a digital image. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of the query object. In addition, the object selection system can add, update, or replace portions of the object selection pipeline to improve overall accuracy and efficiency of automatic object selection within an image.

Abstract: The present disclosure relates to an object selection system that accurately detects and automatically selects target instances of user-requested objects (e.g., a query object instance) in a digital image. In one or more embodiments, the object selection system can analyze one or more user inputs to determine an optimal object attribute detection model from multiple specialized and generalized object attribute models. Additionally, the object selection system can utilize the selected object attribute model to detect and select one or more target instances of a query object in an image, where the image includes multiple instances of the query object.

Abstract: The present disclosure relates to an object selection system that accurately detects and optionally automatically selects user-requested objects (e.g., query objects) in digital images. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of a query object. In particular, the object selection system can identify both known object classes as well as objects corresponding to unknown object classes.

Abstract: The present disclosure relates to a color classification system that accurately classifies objects in digital images based on color. In particular, in one or more embodiments, the color classification system utilizes a multidimensional color space and one or more color mappings to match objects to colors. Indeed, the color classification system can accurately and efficiently detect the color of an object utilizing one or more color similarity regions generated in the multidimensional color space.

Abstract: Systems and methods for efficiently absorbing, archiving, and distributing any size data sets are provided. Some embodiments provide flexible, policy-based distribution of high volume data through real time streaming as well as past data replay. In addition, some embodiments provide for a foundation of solid and unambiguous consistency across any vendor system through advanced version features. This consistency is particularly valuable to the financial industry, but also extremely useful to any company that manages multiple data distribution points for improved and reliable data availability.

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: Techniques and systems are provided for training a machine learning model using different datasets to perform one or more tasks. The machine learning model can include a first sub-module configured to perform a first task and a second sub-module configured to perform a second task. The first sub-module can be selected for training using a first training dataset based on a format of the first training dataset. The first sub-module can then be trained using the first training dataset to perform the first task. The second sub-module can be selected for training using a second training dataset based on a format of the second training dataset. The second sub-module can then be trained using the second training dataset to perform the second task.