Abstract: Digital image outline generation techniques that leverage context of a digital image are described. In one or more examples, an outline generation system detects a context of a digital image, e.g., using a machine-learning model to detect a context of an outdoor scene, indoor scene, presence of a salient object, and so on. The outline generation system then selects a context processing module from a plurality of context processing modules based on the detected context to generate candidate outlines that are then vectorized to generate an image outline.

Abstract: Embodiments are disclosed for generating fine-grain attributions for document question answering systems. The method may include receiving a question for a document. An answer generator generates an answer corresponding to the question. An attribution request associated with a portion of the answer is received. The portion of the answer includes a subset of text from the answer. An attribution generator generates one or more attributions for the portion of the answer based on sources associated with the answer. The one or more attributions are then presented for display.

Abstract: Synchronous to asynchronous digital service call conversion techniques are described. In one or more examples, a request is received at an interface module of the digital service infrastructure and a call ID is generated. A client timeout value from the request is used to set a timer. If client timeout value expires during processing of the request payload, the call ID is stored in a storage device and a timeout response is generated including the call ID for communication to the client device. A result payload is generated upon completion of the processing of the request payload by the execution module. The client device generates a continuation request which includes the call ID to obtain the result payload. The interface module utilizes the call ID to obtain the result payload from the storage device, which is then communicated as a continuation response back to the client device.

Abstract: Techniques for generation of a unified identity registry are described that support integration and analysis of non-blockchain based user data and blockchain-based user data. A processing device, for instance, monitors an interaction between a client device associated with a user and a digital service provided by a digital service provider. Based on the interaction, the processing device determines a non-blockchain based identifier as well as a blockchain based identifier associated with the user and generates an association between the identifiers. The processing device then generates an identity asset that includes the association for inclusion in an identity registry. The processing device performs a variety of analysis as part of maintaining the identity registry, such as generating segments of identity assets and generating rules to govern access and use of the identity assets. The processing device then grants access to the identity registry based on the rules.

Abstract: Systems and methods for natural language processing are described. Embodiments of the present disclosure receive an input phrase including an aspect term; generate a complement phrase based on the input phrase using a language generator model, wherein the complement phrase includes different words than the input phrase; combine a representation of the input phrase and a representation of the complement phrase to obtain an augmented representation of the input phrase; and generate sentiment information corresponding to the aspect term based on the augmented representation.

Abstract: Systems and methods for image generation include obtaining an input image and an attribute value representing an attribute of the input image to be modified; computing a modified latent vector for the input image by applying the attribute value to a basis vector corresponding to the attribute in a latent space of an image generation network; and generating a modified image based on the modified latent vector using the image generation network, wherein the modified image includes the attribute based on the attribute value.

Abstract: One or more processing devices access a scene depicting a reference object that includes an annotation identifying a target region to be modified in one or more video frames. The one or more processing devices determine that a target pixel corresponds to a sub-region within the target region that includes hallucinated content. The one or more processing devices determine gradient constraints using gradient values of neighboring pixels in the hallucinated content, the neighboring pixels being adjacent to the target pixel and corresponding to four cardinal directions. The one or more processing devices update color data of the target pixel subject to the determined gradient constraints.

Abstract: Techniques and systems are described for generating location based photo discovery suggestions. Generally, photo discovery data is generated and utilized to form discovery suggestions that identify suggested locations for capturing photographs, as well as other capture-related information that is presented to assist a user in capturing photographs of interest to the user. A discovery suggestion, for example, not only identifies a location of potential photographic interest to a user, but also includes information such as camera settings and suggested camera equipment for capturing photos at the location. A discovery suggestion thus guides a user as to how to maximize a likelihood that a digital image captured by the user includes subject matter of interest to the user and is also visually pleasing.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating anonymized digital images utilizing a face anonymization neural network. In some embodiments, the disclosed systems utilize a face anonymization neural network to extract or encode a face anonymization guide that encodes face attribute features, such as gender, ethnicity, age, and expression. In some cases, the disclosed systems utilize the face anonymization guide to inform the face anonymization neural network in generating synthetic face pixels for anonymizing a digital image while retaining attributes, such as gender, ethnicity, age, and expression. The disclosed systems learn parameters for a face anonymization neural network for preserving face attributes, accounting for multiple faces in digital images, and generating synthetic face pixels for faces in profile poses.

Abstract: A method and system for color optimization in generated images are described. The method and system include receiving an image generation prompt that includes a text description of target image content and color information describing a target color palette; encoding the image generation prompt to obtain image features that represent the target image content and the target color palette; and generating an image representing the target image content with the target color palette based on the image features.

Abstract: Embodiments are disclosed for identifying and modifying overlapping glyphs in a text layout. A method of identifying and modifying overlapping glyphs includes detecting a plurality of overlapping glyphs in a text layout, modifying a geometry of one or more of the overlapping glyphs based on an aesthetic score, updating a rendering tree based on the modified geometry of the one or more overlapping glyphs, and rendering the text layout using the rendering tree.

Abstract: Systems and methods that enable the efficient and adaptive allocation of resources dedicated to a virtualized resource-based computation (e.g., one or more information processing tasks) are provided. In one embodiment, a reward model is generated based on a set of statistical distributions, for example, in response to receiving a request to launch a set of VCRs. Thereafter, an expected reward is predicting for each configuration of a set of configurations based on the reward model and one or more parameters of the corresponding configuration. The expected reward indicates an efficiency in distribution or allocation of physical computation resources to the set of VCRs. A configuration of the set of configurations is selected based on the predicted expected reward for the configuration. The set of VCRs are then configured with the selected configuration.

Abstract: Reference based digital content stylization techniques are described that enable generation of stylized digital content from a plain text input based on visual style attributes of reference digital content. A content processing system, for instance, receives input digital content including text and reference digital content with a particular visual style. The content processing system determines visual style attributes of the reference digital content, such as a text size, color, font, etc. The content processing system generates an input content classification scheme that includes semantic structure identifiers to classify text of the input digital content, e.g., as a header, subheader, paragraph, and so forth. Based on the input content classification scheme, the content processing system generates stylized digital content by applying the visual style attributes of the reference digital content to the text of the input digital content.

Abstract: In implementation of techniques for translating images based on semantic information, a computing device implements a translation system to receive an input image in a first format, encoded semantic information describing a domain of the input image, and a selection of a second format. The translation system decodes the encoded semantic information using a machine learning model. The translation system then generates an output image in the second format by translating the input image from the first format to the second format using the machine learning model, the machine learning model guided by the decoded semantic information. The translation system then displays the output image in the second format in a user interface.

Abstract: Embodiments are disclosed for merging misidentified text structures. The method may include receiving a document including a plurality of text elements. The method may further include determining, by a machine learning model, a likelihood of merging a first text element of the plurality of text elements with a second text element of the plurality of text elements based on structure data and context data associated with the first and second text elements. The method may further include determining whether the likelihood of merging the first text element with the second text element satisfies a threshold. The method further includes responsive to determining that the likelihood of merging the first text element with the second text element satisfies the threshold, merging the first text element with the second text element.

Abstract: Embodiments are disclosed for a digital design system trained to segment unstructured text into topically coherent segments. The method may include receiving unstructured text, the unstructured text including a sequence of sentences. The disclosed systems and methods further comprise generating, by a neural network, a hierarchically segmented tree structure representing the unstructured text. The tree structure comprises a plurality of tree structure nodes, where a node of the tree structure nodes represents a sentence from the sequence of sentences. The segments and sub-segments of the unstructured text can then be determined based on node data for nodes of the hierarchically segmented tree structure. Using the determined segments and sub-segments of the unstructured text, a modified representation of the unstructured text can be displayed.

Abstract: Embodiments are disclosed for long document question answering using large language models. The method may include receiving a question for a document. A representation of the document may then be obtained. A large language model (LLM) is used to identify one or more sections of the document that are relevant to the question using the representation of the document. A document question answering model determines an answer to the question using the one or more sections of the document.

Abstract: Technology is disclosed herein for enhanced similarity search. In an implementation, a search environment includes one or more computing hardware, software, and/or firmware components in support of enhanced similarity search. The one or more components identify a modality for a similarity search with respect to a query object. The components generate an embedding for the query object based on the modality and based on connections between the query object and neighboring nodes in a graph. The embedding for the query object provides the basis for the search for similar objects.

Abstract: Techniques for generating a novel image using tokenized image representations are disclosed. In some embodiments, a method of generating the novel image includes generating, via a first machine learning model, a first sequence of coded representations of a first image having one or more features; generating, via a second machine learning model, a second sequence of coded representations of a sketch image having one or more edge features associated with the one or more features; predicting, via a third machine learning model, one or more subsequent coded representations based on the first sequence of coded representations and the second sequence of coded representations; and based on the subsequent coded representations, generating, via the third machine learning model, a first portion of a reconstructed image having one or more image attributes of the first image, and a second portion of the reconstructed image associated with the one or more edge features.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images using an intelligent user interface tool that determines the intent of a user interaction. For instance, in some embodiments, the disclosed systems receive, via a graphical user interface of a client device, a user interaction with a set of pixels within a digital image. The disclosed systems determine, based on the user interaction, a user intent for targeting one or more portions of the digital image for deletion, the one or more portions including an additional set of pixels that differs from the set of pixels. Based on the user intent, the disclosed systems modify the digital image to delete the one or more portions from the digital image.