Adobe, Inc.

University System of Maryland

Christopher Alan Tensmeyer

Curtis Michael Wigington

Vlad Ion Morariu

Brian Lynn Price

Tong Sun

Varun Manjunatha

Handong Zhao

Rajiv Jain

Nikolaos Barmpalios

Kai Li

Brian Lafayette Davis

Jiuxiang Gu

Ani Nenkova

Scott David Cohen

Nedim Lipka

Tong Yu

Zhicheng Liu

Ruiyi Zhang

Hao Tan

Danilo Neves Ribeiro

Yufan Zhou

Yuexi Chen

Lars Niklas Emanuel Elmqvist

Shijie Geng

Michael Brodie

Fuxiao Liu

Embodiments are disclosed for reflowing documents to display semantically related content. The method may include receiving a request to view a document that includes body text and one or more images. A trimodal document relationship model identifies relationships between segments of the body text and the one or more images. A linearized view of the document is generated based on the relationships and the linearized view is caused to be displayed on a user device.

Reflowing documents to display semantically related content

Systems and methods for performing Document Visual Question Answering tasks are described. A document and query are received. The document encodes document tokens and the query encodes query tokens. The document is segmented into nested document sections, lines, and tokens. A nested structure of tokens is generated based on the segmented document. A feature vector for each token is generated. A graph structure is generated based on the nested structure of tokens. Each graph node corresponds to the query, a document section, a line, or a token. The node connections correspond to the nested structure. Each node is associated with the feature vector for the corresponding object. A graph attention network is employed to generate another embedding for each node. These embeddings are employed to identify a portion of the document that includes a response to the query. An indication of the identified portion of the document is be provided.

Enhanced document visual question answering system via hierarchical attention

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.

Simulated handwriting image generator

The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback. Moreover, the disclosed systems can persist these semantically meaningful features throughout a refinement process and across generated images.

Utilizing a generative neural network to interactively create and modify digital images based on natural language feedback

Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

Domain adaptation for machine learning models

Systems and techniques for generating responsive documents are described. Digital content is organized into a structure that defines how content is presented when a document is displayed by a computing device. To generate the responsive document, relationships are defined among different digital content objects, such as groups of content objects to be presented together and content objects that are to be presented as alternatives of one another. Responsive patterns are assigned to grouped content objects, where each responsive pattern defines different layout configurations for displaying grouped content objects based on computing device display characteristics. In some implementations, multiple responsive patterns are assigned to a single content group and individual responsive patterns are associated with activation ranges for display characteristics that activate the responsive pattern. For groups of digital content objects that are assigned multiple responsive patterns, responsive patterns are prioritized to create a hierarchy dictating display of the responsive document.

Responsive document authoring

This disclosure describes one or more embodiments of systems, non-transitory computer-readable media, and methods that can learn or identify a learned-initialization-latent vector for an initialization digital image and reconstruct a target digital image using an image-generating-neural network based on a modified version of the learned-initialization-latent vector. For example, the disclosed systems learn a learned-initialization-latent vector from an initialization image utilizing a high number (e.g., thousands) of learning iterations on an image-generating-neural network (e.g., a GAN). Then, the disclosed systems can modify the learned-initialization-latent vector (of the initialization image) to generate modified or reconstructed versions of target images using the image-generating-neural network. For instance, the disclosed systems utilize the learned-initialization-latent vector as a starting point to learn a learned-latent vector for a target image that an image-generating-neural network converts into a high-fidelity reconstruction of the target image (with a reduced number of learning iterations).

Initializing a learned latent vector for neural-network projections of diverse images

Embodiments are disclosed for performing fact correction of natural language sentences using data tables. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input sentence, tokenizing elements of the input sentence, and identifying, by a first machine learning model, a data table associated with the input sentence. The systems and methods further comprise a second machine learning model identifying a tokenized element of the input sentence that renders the input sentence false based on the data table and masking the tokenized element of the tokenized input sentence that renders the input sentence false. The systems and method further includes a third machine learning model predicting a new value for the masked tokenized element based on the input sentence with the masked tokenized element and the identified data table and providing an output including a modified input sentence with the new value.

Fact correction of natural language sentences using data tables

A domain alignment technique for cross-domain object detection tasks is introduced. During a preliminary pretraining phase, an object detection model is pretrained to detect objects in images associated with a source domain using a source dataset of images associated with the source domain. After completing the pretraining phase, a domain adaptation phase is performed using the source dataset and a target dataset to adapt the pretrained object detection model to detect objects in images associated with the target domain. The domain adaptation phase may involve the use of various domain alignment modules that, for example, perform multi-scale pixel/path alignment based on input feature maps or perform instance-level alignment based on input region proposals.

Domain alignment for object detection domain adaptation tasks

A table layout determination system implemented on a computing device obtains an image of a table having multiple cells. The table layout determination system includes a row prediction machine learning system that generates, for each of multiple rows of pixels in the image of the table, a probability of the row being a row separator, and a column prediction machine learning system generates, for each of multiple columns of pixels in the image of the table, a probability of the column being a column separator. An inference system uses these probabilities of the rows being row separators and the columns being column separators to identify the row separators and column separators for the table. These row separators and column separators are the layout of the table.

Growing community of inventors

Provo, UT, United States of America

Christopher Alan Tensmeyer