Abstract: In implementations of systems for stylizing digital content, a computing device implements a style system to receive input data describing digital content to be stylized based on visual styles of example content included in a digital template. The style system generates embeddings for content entities included in the digital content using a machine learning model. Classified content entities are determined based on the embeddings using the machine learning model. The style system generates an output digital template that includes portions of the digital content having the visual styles of example content included in the digital template based on the classified content entities.

Abstract: Techniques for modeling secondary motion based on three-dimensional models are described as implemented by a secondary motion modeling system, which is configured to receive a plurality of three-dimensional object models representing an object. Based on the three-dimensional object models, the secondary motion modeling system determines three-dimensional motion descriptors of a particular three-dimensional object model using one or more machine learning models. Based on the three-dimensional motion descriptors, the secondary motion modeling system models at least one feature subjected to secondary motion using the one or more machine learning models. The particular three-dimensional object model having the at least one feature is rendered by the secondary motion modeling system.

Abstract: In implementations of systems for estimating temporal occurrence of a binary state change, a computing device implements an occurrence system to compute a posterior probability distribution for temporal occurrences of binary state changes associated with client computing devices included in a group of client computing devices. The occurrence system determines probabilities of a binary state change associated with a client computing device included in the group of client computing devices based on the posterior probability distribution, and the probabilities correspond to future periods of time. A future period of time is identified based on a probability of the binary state change associated with the client computing device. The occurrence system generates a communication based on a communications protocol for transmission to the client computing device via a network at a period of time that correspond to the future period of time.

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

Abstract: In implementations of systems for time-series anomaly detection, a computing device implements an anomaly system to receive, via a network, time-series data describing continuously observed values separated by a period of time. The anomaly system computes updated estimated parameters of a predictive model for the time-series data by performing a rank one update on previously estimated parameters of the predictive model. An uncertainty interval for a future observed value is generated using the predictive model with the updated estimated parameters. The anomaly system determines that an observed value corresponding to the future observed value is outside of the uncertainty interval. An indication is generated that the observed value is an anomaly.

Abstract: Embodiments are disclosed for warping artwork. The artwork is warped to fit an existing image of a cylinder. A method of warping artwork may include receiving a request to wrap an image onto a cylindrical surface. In response to the request, a set of adjacent warping patches are generated. The set of adjacent warping patches includes a first zero-width patch corresponding to a left edge of the image and a second zero-width patch corresponding to a right edge of the image. The image is mapped to the set of adjacent warping patches based on a viewing perspective of the cylindrical surface. User control handles are provided to adjust the warp to fit the existing image of the cylinder, including its position, curvature, and perspective.

Abstract: Embodiments are disclosed for generating continuous curve textures based on an input exemplar. A method of generating continuous curve textures may include receiving an input exemplar which represents a repetitive pattern as a plurality of vector curves, generating an input graph representation of the input exemplar which represents a geometry and a topology of the input exemplar, synthesizing an output graph based on the input graph representation, and reconstructing output vector curves from the output graph.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that provides to a user a subset of digital design templates as recommendations based on a creative segment classification and template classifications. For instance, in one or more embodiments, the disclosed systems generate the creative segment classification for the user and determines geo-seasonal intent data. Furthermore, the disclosed system generates template classifications using a machine learning model based on geo-seasonality and creative intent. In doing so, the disclosed system identifies a subset of digital design templates based on the template classifications, geo-seasonal intent data, and the creative segment classification of the user.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize weakly supervised graph matching to align an ungrounded label graph and a visual graph corresponding to a digital image. Specifically, the disclosed system utilizes a label embedding model to generate label graph embeddings from the ungrounded label graph and a visual embedding network to generate visual graph embeddings from the visual graph. Additionally, the disclosed system determines similarity metrics indicating the similarity of pairs of label graph embeddings and visual graph embeddings. The disclosed system then generates a semantic scene graph by utilizing a graph matching algorithm to align the ungrounded label graph and the visual graph based on the similarity metrics. In some embodiments, the disclosed system utilizes contrastive learning to modify the embedding models.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that generate and render a varied-scale-topological construct for a multidimensional dataset to visually represent portions of the multidimensional dataset at different topological scales. In certain implementations, for example, the disclosed systems generate and combine (i) an initial topological construct for a multidimensional dataset at one scale and (ii) a local topological construct for a subset of the multidimensional dataset at another scale to form a varied-scale-topological construct. To identify a region from an initial topological construct to vary in scale, the disclosed systems can determine the relative densities of subsets of multidimensional data corresponding to regions of the initial topological construct and select one or more such regions to change in scale.

Abstract: The technology described herein is directed to a self-learning application scheduler for improved scheduling distribution of resource requests, e.g., job and service scheduling requests or tasks derived therefrom, initiated by applications on a shared compute infrastructure. More specifically, the self-learning application scheduler includes a reinforcement learning agent that iteratively learns a scheduling policy to improve scheduling distribution of the resource requests on the shared compute infrastructure. In some implementations, the reinforcement learning agent learns inherent characteristics and patterns of the resource requests initiated by the applications and orchestrates placement or scheduling of the resource requests on the shared compute infrastructure to minimize resource contention and thereby improve application performance for better overall user-experience.

Abstract: Embodiments of provide systems, methods, and computer storage media for scaling raster content using pre-computed scalar fields, such as images or textures. In an example implementation, an initial raster image is processed to generate a representation of three scalar fields: an unsigned distance field, an adjacency field, and a color plane (also called a color field or a color texture). These three fields are pre-computed prior to scaling (e.g., outside of a rendering loop), and then subsequently used (e.g., by a GPU as textures) to render a scaled version of the initial raster image.

Abstract: Embodiments are disclosed for determining scene-based editing recommendations for video content. A method of determining scene-based editing recommendations for video content includes receiving an input video comprising video content, dividing the input video into the plurality of scenes based on the video content, identifying a representative frame for each scene, determining a plurality of editing settings for each representative frame, determining editing settings for each scene based on an effectiveness score, and generating an output video using the input video and the editing settings for each scene.

Abstract: This disclosure generally covers systems and methods that create sequential segments from analytics data to enable investigation of events that occurred before or after a certain sequence of events—that is, pre-sequence or post-sequence events. In particular, certain embodiments of the disclosed systems and methods receive a segment query of certain analytics data to identify events that occurred before or after a defined sequence of events within a network and—in response to the segment query—provide a query result that identifies pre-sequence events or post-sequence events. By providing such query results, the disclosed systems and methods enable users to examine correlations between a sequence of events and any pre-sequence or post-sequence events, including any data associated with those events at a granular level.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating enriched light sources by utilizing surface-centric representations of three-dimensional surfaces. Specifically, the disclosed system utilizes a surface-centric re-parameterization that combines geometric and algebraic components of a sphere to model different light source types in a continuous range of lighting configurations. The disclosed systems utilize a set of intuitive parameters to determine a shape and emission parameters for generating an enriched light source. Additionally, the disclosed system provides a set of interactive light source controls to modify a position, orientation, shape, emittance, and lighting attenuation over distance of a light source within a three-dimensional environment. The disclosed system determines the light source controls based on sets of three-dimensional interaction primitives to control one or more parameters of the light source.

Abstract: In implementations of image-based searches for templates, a computing device implements a search system to generate an embedding vector that represents an input digital image using a machine learning model. The search system identifies templates that include a candidate digital image to be replaced by the input digital image based on distances between embedding vector representations of the templates and the embedding vector that represents the input digital image. A template of the templates is determined based on a distance between an embedding vector representation of the candidate digital image included in the template and the embedding vector that represents the input digital image. The search system generates an output digital image for display in a user interface that depicts the template with the candidate digital image replaced by the input digital image.

Abstract: Embodiments are disclosed for predicting, using neural networks, editing operations for application to a video sequence based on processing conversational messages by a video editing system. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a video sequence and text sentences, the text sentences describing a modification to the video sequence, mapping, by a first neural network content of the text sentences describing the modification to the video sequence to a candidate editing operation, processing, by a second neural network, the video sequence to predict parameter values for the candidate editing operation, and generating a modified video sequence by applying the candidate editing operation with the predicted parameter values to the video sequence.

Abstract: Embodiments are disclosed for performing a filler word detection process on input audio by a media editing system using trained neural networks. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including an audio sequence, analyzing the audio sequence to determine filler word candidates, classifying, by a filler word classification model, each filler word candidate of the filler word candidates into one of a set of categories, and generating an output audio sequence, the output audio sequence including an identification of a subset of the filler word candidates in a filler words category of the set of categories as identified filler words.

Abstract: Curve offset operations as implemented by a digital image editing system are described. Input points are received via a user interface and a determination is made that a first set of the input points satisfy a condition for use as part of a curve offset operation with respect to a curve. A first segment is added to a path using the curve offset operation. The first segment is generated by aligning the first set of input points using an offset value based on the curve. A determination is then made that a second set of the input points do not satisfy the condition for use as part of the curve offset operation and a second segment is added to the first segment of the path. The second segment is generated using the second set of points and the path is displayed.

Abstract: Embodiments are disclosed for generating a gesture reenactment video sequence corresponding to a target audio sequence using a trained network based on a video motion graph generated from a reference speech video. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a first input including a reference speech video and generating a video motion graph representing the reference speech video, where each node is associated with a frame of the reference video sequence and reference audio features of the reference audio sequence. The disclosed systems and methods further comprise receiving a second input including a target audio sequence, generating target audio features, identifying a node path through the video motion graph based on the target audio features and the reference audio features, and generating an output media sequence based on the identified node path through the video motion graph paired with the target audio sequence.