Abstract: In implementations of systems for generating indications of relationships between electronic documents, a processing device implements a relationship system to segment text of electronic documents included in a document corpus into segments. The relationship system determines a subset of the electronic documents that includes electronic document pairs having a number of similar segments that is greater than a threshold number. The similar segments are identified using locality sensitive hashing. The electronic document pairs are classified as related documents or unrelated documents using a machine learning model that receives a pair of electronic documents as an input and generates an indication of a classification for the pair of electronic documents as an output. Indications of relationships between particular electronic documents included in the subset are generated based at least partially on the electronic document pairs that are classified as related documents.

Abstract: In implementations of systems for searching for images using generated images, a computing device implements a search system to receive a natural language search query for digital images included in a digital image repository. The search system generates a set of digital images using a machine learning model based on the natural language search query. The machine learning model is trained on training data to generate digital images based on natural language inputs. The search system performs an image-based search for digital images included in the digital image repository using the set of digital images. An indication of the search result is generated for display in a user interface based on performing the image-based search.

Abstract: Systems and methods for identifying key moments, such as key moments within a livestream, are described. Embodiments of the present disclosure obtain video data and text data. In some cases, the text data is aligned with a timeline of the video data. The system then computes a moment importance score for a time of the video data using a machine learning model based on the video data and the text data, and presents content to a user at the time of the video data based on the moment importance score.

Abstract: In implementations of systems for identifying instances of digital content, a computing device implements a content system to receive input data describing attributes of an entity segment and keywords that are associated with the attributes of the entity segment. The content system determines additional keywords that are semantically similar to the keywords using a machine-learning model trained on training data to classify semantically similar keywords. A set of matchable keywords is compiled that includes the keywords and the additional keywords. The content system identifies candidate instances of digital content based on content keywords assigned to the candidate instances of digital content and the set of matchable keywords. An indication of an instance of digital content is generated for display in a user interface based on the candidate instances of digital content.

Abstract: Methods for determining optimal cloud service resource include determining a reward function for a set of resource configurations identifying cloud service resource parameters. The cloud service resource parameters include a source parameter and a target parameter of services to provide a client computing device. A source parameter dataset for the source parameter and a target parameter dataset is generated using the reward function and historical source parameter data. The matrices are then subject to SVD and clustering. A target parameter reward dataset is learned from output of the SVD and clustering. The target parameter dataset is used to determine the parameters for the target parameter for providing corresponding cloud service resources.

Abstract: Embodiments of the disclosure provide a machine learning model for generating a predicted executable command for an image. The learning model includes an interface configured to obtain an utterance indicating a request associated with the image, an utterance sub-model, a visual sub-model, an attention network, and a selection gate. The machine learning model generates a segment of the predicted executable command from weighted probabilities of each candidate token in a predetermined vocabulary determined based on the visual features, the concept features, current command features, and the utterance features extracted from the utterance or the image.

Abstract: Techniques for generation of compressed representations for digital assets are described that support computationally efficient and high fidelity rendering of digital assets with a variety of geometries under arbitrary lighting conditions and view directions. A processing device, for instance, receives a digital asset defined by a three-dimensional geometry to be included in a digital scene. The processing device generates a compressed representation of the digital asset that maintains a geometry of the digital asset and includes a precomputed light transport. The processing device then deploys the compressed representation into the digital scene, such as at a location relative to one or more digital scene elements. The content processing system renders the digital asset by applying one or more lighting effects to the compressed representation based on the precomputed light transport and the location relative to the one or more digital scene elements.

Abstract: Embodiments are disclosed for semantically organizing a graphic design document. A method of semantically organizing a graphic design document can include obtaining a document, identifying a plurality of layers associated with the document, determining a plurality of semantic labels associated with the plurality of layers, determining a semantic layer hierarchy of the plurality of layers, and organizing the plurality of layers based at least on the semantic layer hierarchy.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately enhancing optical character recognition with a machine learning approach for determining words from reverse text, vertical text, and atypically-sized text. For example, the disclosed systems segment a digital image into text regions and non-text regions utilizing an object detection machine learning model. Within the text regions, the disclosed systems can determine reverse text glyphs, vertical text glyphs, and/or atypically-sized text glyphs utilizing an edge based adaptive binarization model. Additionally, the disclosed systems can utilize respective modification techniques to manipulate reverse text glyphs, vertical text glyphs, and/or atypically-sized glyphs for analysis by an optical character recognition model.

Abstract: Methods and systems disclosed herein relate generally to systems and methods for analyzing various stroke properties determined from strokes inputted by a user to generate a new glyph set for rendering type characters. A font-generating application receives, via a stroke input on a typographic layer presented on a user interface, strokes that trace a visual appearance of a glyph set comprising one or more glyphs. The font-generating application determines stroke properties for the strokes. The font-generating application constructs a new glyph set from the stroke properties. The font-generating application applies the new glyph set to render, on a user interface, one or more type characters that match a visual appearance of the new glyph set.

Abstract: Methods and systems are provided for facilitating document collaboration in accordance with collaboration controls. In embodiments, an indication of a collaboration control for a collaborator of a document is obtained. The collaboration control generally indicates an edit permission for a document section of the document in relation to the collaborator. Thereafter, a set of collaboration control data for the document is generated. In embodiments, the set of collaboration control data includes the collaboration control indicating the edit permission for the document section of the document in relation to the collaborator. Based on an input (e.g., edit) by the collaborator to the document section of the document, a determination is made, using the set of collaboration control data, as to whether to enable an edit to the document section of the document.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For instance, in one or more embodiments, the disclosed systems generate utilizing a segmentation neural network, an object mask for each object of a plurality of objects of a digital image. The disclosed systems detect a first user interaction with an object in the digital image displayed via a graphical user interface. The disclosed systems surface, via the graphical user interface, the object mask for the object in response to the first user interaction. The disclosed systems perform an object-aware modification of the digital image in response to a second user interaction with the object mask for the object.

Abstract: The present disclosure relates to generating proposed digital actions in high-dimensional action spaces for client devices utilizing reinforcement learning models. For example, the disclosed systems can utilize a supervised machine learning model to train a latent representation decoder to determine proposed digital actions based on latent representations. Additionally, the disclosed systems can utilize a latent representation policy gradient model to train a state-based latent representation generation policy to generate latent representations based on the current state of client devices. Subsequently, the disclosed systems can identify the current state of a client device and a plurality of available actions, utilize the state-based latent representation generation policy to generate a latent representation based on the current state, and utilize the latent representation decoder to determine a proposed digital action from the plurality of available actions by analyzing the latent representation.

Abstract: Embodiments provide systems, methods, and computer storage media for a Nonsymmetric Determinantal Point Process (NDPPs) for compatible set recommendations in a setting where data representing entities (e.g., items) arrives in a stream. A stream representing compatible sets of entities is received and used to update a latent representation of the entities and a compatibility distribution indicating likelihood of compatibility of subsets of the entities. The probability distribution is accessed in a single sequential pass to predict a compatible complete set of entities that completes an incomplete set of entities. The predicted complete compatible set is provided a recommendation for entities that complete the incomplete set of entities.

Abstract: The present technology provides for facilitating efficient identification of relevant metrics. In one embodiment, a set of candidate metrics for which to determine relevance to a user is identified. For each candidate metric, a set of distribution parameters is determined, including a first distribution parameter based on implicit positive feedback associated with the metric and usage data associated with the metric and a second distribution parameter based on the usage data associated with the metric. Such usage data can efficiently facilitate identifying relevance even with an absence of negative feedback. Using the set of distribution parameters, a corresponding distribution is generated. Each distribution can then be sampled to identify a relevance score for each candidate metric indicating an extent of relevance of the corresponding metric. Based on the relevance scores for each candidate metric, a candidate metric is designated as relevant to the user.

Abstract: An image search system uses a multi-modal model to determine relevance of images to a spoken query. The multi-modal model includes a spoken language model that extracts features from spoken query and a language processing model that extract features from an image. The multi-model model determines a relevance score for the image and the spoken query based on the extracted features. The multi-modal model is trained using a curriculum approach that includes training the spoken language model using audio data. Subsequently, a training dataset comprising a plurality of spoken queries and one or more images associated with each spoken query is used to jointly train the spoken language model and an image processing model to provide a trained multi-modal model.

Abstract: Techniques are described that support automated generation of a digital document from digital videos using machine learning. The digital document includes textual components that describe a sequence of entity and action descriptions from the digital video. These techniques are usable to generate a single digital document based on a plurality of digital videos as well as incorporate user-specified constraints in the generation of the digital document.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating image mattes for detected objects in digital images without trimap segmentation via a multi-branch neural network. The disclosed system utilizes a first neural network branch of a generative neural network to extract a coarse semantic mask from a digital image. The disclosed system utilizes a second neural network branch of the generative neural network to extract a detail mask based on the coarse semantic mask. Additionally, the disclosed system utilizes a third neural network branch of the generative neural network to fuse the coarse semantic mask and the detail mask to generate an image matte. In one or more embodiments, the disclosed system also utilizes a refinement neural network to generate a final image matte by refining selected portions of the image matte generated by the generative neural network.

Abstract: Digital image synthesis techniques are described that leverage splatting, i.e., forward warping. In one example, a first digital image and a first optical flow are received by a digital image synthesis system. A first splat metric and a first merge metric are constructed by the digital image synthesis system that defines a weighted map of respective pixels. From this, the digital image synthesis system produces a first warped optical flow and a first warp merge metric corresponding to an interpolation instant by forward warping the first optical flow based on the splat metric and the merge metric. A first warped digital image corresponding to the interpolation instant is formed by the digital image synthesis system by backward warping the first digital image based on the first warped optical flow.

Abstract: Systems and methods for machine learning based controllable animation of still images is provided. In one embodiment, a still image including a fluid element is obtained. Using a flow refinement machine learning model, a refined dense optical flow is generated for the still image based on a selection mask that includes the fluid element and a dense optical flow generated from a motion hint that indicates a direction of animation. The refined dense optical flow indicates a pattern of apparent motion for the at least one fluid element. Thereafter, a plurality of video frames is generated by projecting a plurality of pixels of the still image using the refined dense optical flow.