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: The present disclosure relates to systems, non-transitory computer-readable media, and methods for expanding a digital document including a sequence of informational data via supplemental multimodal digital content. In particular, the system expands digital documents with multimodal granular details to dynamically integrate supplemental in-depth information to the digital document. For example, in response to a selection of a specific portion of a digital document, the system generates expanded multimodal content (e.g., text and image content) for the selected portion of the digital document from external text and image sources. Indeed, the system uses existing content from the digital document to select images and combine the selected images with text into image-text pairs that are textually and visually consistent with the digital document. Moreover, the system expands the digital document by inserting the image-text pairs in connection with the selected portion of the digital document.

Abstract: Techniques are described for object insertion via scene graph. In implementations, given an input image and a region of the image where a new object is to be inserted, the input image is converted to an intermediate scene graph space. In the intermediate scene graph space, graph convolutional networks are leveraged to expand the scene graph by predicting the identity and relationships of a new object to be inserted, taking into account existing objects in the input image. The expanded scene graph and the input image are then processed by an image generator to insert a predicted visual object into the input image to produce an output image.

Abstract: An illustrator system determines, for each feature of a set of features, a feature representation for an electronic document displayed via a user interface, based on a plurality of elements of the electronic document. The system receives a selection from among the set of features of (1) a query feature and of (2) a target feature and determines, for each replacement template of a set of replacement templates, a compatibility score based on the feature representation for the electronic document determined for the query feature and a target feature representation of the replacement template determined for the target feature, the representations being determined in a joint representation space. The system selects one or more replacement electronic documents based on the determined compatibility scores. The system displays a preview for each replacement electronic document and displays a particular replacement electronic document responsive to receiving a selection of a preview.

Abstract: Systems and methods for automatically generating graphic design documents are described. Embodiments include identifying an input text that includes a plurality of phrases; obtaining one or more images based on the input text; encoding an image of the one or more images in a vector space using a multimodal encoder to obtain a vector image representation; encoding a phrase from the plurality of phrases in the vector space using the multimodal encoder to obtain a vector text representation; selecting an image text combination including the image and the phrase by comparing the vector image representation and the vector text representation; selecting a design template from a plurality of candidate design templates based on the image text combination; and generating a document based on the design template, wherein the document includes the at least one image and the at least one phrase.

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: 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: 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: Systems and methods for machine learning are described. The systems and methods include receiving target training data including a training image and ground truth label data for the training image, generating source network features for the training image using a source network trained on source training data, generating target network features for the training image using a target network, generating at least one attention map for training the target network based on the source network features and the target network features using a guided attention transfer network, and updating parameters of the target network based on the attention map and the ground truth label data.

Abstract: Certain embodiments involve a template-based redesign of documents based on the contents of documents. For instance, a computing system selects a template for modifying an input document. To do so, the computing system uses a generative adversarial network to generate an interpolated layout image from an input layout image, which represents the input document, and a template layout image, which represents the selected template. The computing system matches the input element to an interpolated element from the interpolated layout image. The computing system generates an output document by, for example, modifying a layout of the input document to match the interpolated layout image, such as by fitting the input element into a shape of the interpolated element.

Abstract: Certain embodiments involve a template-based redesign of documents based on the contents of documents. For instance, a computing system selects a template for modifying an input document. To do so, the computing system uses a generative adversarial network to generate an interpolated layout image from an input layout image, which represents the input document, and a template layout image, which represents the selected template. The computing system matches the input element to an interpolated element from the interpolated layout image. The computing system generates an output document by, for example, modifying a layout of the input document to match the interpolated layout image, such as by fitting the input element into a shape of the interpolated element.