Abstract: In implementations of systems for detecting and managing conflicts for multiple experiments, a computing device implements a management system to assign a first experiment to a first namespace and a second experiment to a second namespace. An indication is received via a network of the first experiment performed via a first channel using a first set of entities and a second set of entities from a group of entities. The management system receives a request via the network to perform the second experiment via a second channel using a third set of entities and a fourth set of entities from the group of entities. The management system detects a conflict for the second experiment based on the first namespace and the second namespace. An indication of the conflict for the second experiment is generated for display in a user interface.

Abstract: In implementations of systems for evaluating bias in generative models, a computing device implements a bias system to generate a modified digital image by processing an input digital image using a first machine learning model trained on training data to generate modified digital images based on input digital images. The bias system computes a first latent representation of the input digital image and a second latent representation of the modified digital image using a second machine learning model trained on training data to compute latent representations of digital images. A bias score is determined for a visual attribute based on the first latent representation and the second latent representation. The bias system generates an indication of the bias score for the visual attribute for display in a user interface.

Abstract: Techniques and systems for training and/or implementing a text-to-image generation model are provided. A pre-trained multimodal model is leveraged for avoiding slower and more labor-intensive methodologies for training a text-to-image generation model. Accordingly, images without associated text (i.e., bare images) are provided to the pre-trained multimodal model so that it can produce generated text-image pairs. The generated text-image pairs are provided to the text-to-image generation model for training and/or implementing the text-to-image generation model.

Abstract: Online testing data governance techniques and systems are described. These techniques support incorporation of data governance as part of online testing through use of a testing governance system implemented as part of a testing system. These techniques are configured to address technical challenges specific to online testing involving design of the online test, runtime during which the online test is executed, and reporting of test results.

Abstract: A computing system captures image data using a camera and captures spatial information using one or more sensors. The computing system receives voice data using a microphone. The computing system analyzes the voice data to identify a keyword. The computing system analyzes the image data and the spatial information to identify an object corresponding to the keyword. The computing system generates text based on the voice data and the keyword. The computing system stores the text in association with the object. The computing system generates and provides output comprising the text linked to the object or a derivative thereof.

Abstract: Embodiments are disclosed for an audio recommendation system trained to recommend music audio sequences for pairing with query video sequences using neural networks. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a query video sequence and natural language text. The disclosed systems and methods further comprise generating a fused visual-text embedding based on a visual embedding and a text embedding corresponding to the input. The disclosed systems and methods further comprise comparing audio embeddings for music audio sequences of a music audio sequences database with the fused visual-text embedding. The disclosed systems and methods further comprise determining a music audio sequence from the music audio sequences database as the recommended music audio sequence for pairing with the query video sequence based on a similarity metric calculated between an audio embedding for the music audio sequence and the fused visual-text embedding.

Abstract: In accordance with the described techniques, an image transformation system receives an input image and a text prompt, and leverages a generator network to edit the input image based on the text prompt. The generator network includes a plurality of layers configured to perform respective edits. A plurality of masks are generated based on the text prompt that define local edit regions, respectively, of the input image for respective layers of the generator network. Further, the generator network generates an edited image by editing the input image based on the plurality of masks, the respective edits of the respective layers, and the text prompt.

Abstract: 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.

Abstract: Certain embodiments involve using a machine-learning tool to generate metadata identifying segments and topics for text within a document. For instance, in some embodiments, a text processing system obtains input text and applies a segmentation-and-labeling model to the input text. The segmentation-and-labeling model is trained to generate a predicted segment for the input text using a segmentation network. The segmentation-and-labeling model is also trained to generate a topic for the predicted segment using a pooling network of the model to the predicted segment. The output of the model is usable for generating metadata identifying the predicted segment and the associated topic.

Abstract: A visual search system facilitates retrieval of provenance information using a machine learning model to generate content fingerprints that are invariant to benign transformations while being sensitive to manipulations. The machine learning model is trained on a training image dataset that includes original images, benign transformed variants of the original images, and manipulated variants of the original images. A loss function is used to train the machine learning model to minimize distances in an embedding space between benign transformed variants and their corresponding original images and increase distances between the manipulated variants and their corresponding original images.

Abstract: System and methods for a text summarization system are described. In one example, a text summarization system receives an input utterance and determines whether the utterance should be included in a summary of the text. The text summarization system includes an embedding network, a convolution network, an encoding component, and a summary component. The embedding network generates a semantic embedding of an utterance. The convolution network generates a plurality of feature vectors based on the semantic embedding. The encoding component identifies a plurality of latent codes respectively corresponding to the plurality of feature vectors. The summary component identifies a prominent code among the latent codes and to select the utterance as a summary utterance based on the prominent code.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating harmonized digital images utilizing an object-to-object harmonization neural network. For example, the disclosed systems implement, and learn parameters for, an object-to-object harmonization neural network to combine a style code from a reference object with features extracted from a target object. Indeed, the disclosed systems extract a style code from a reference object utilizing a style encoder neural network. In addition, the disclosed systems generate a harmonized target object by applying the style code of the reference object to a target object utilizing an object-to-object harmonization neural network.

Abstract: Embodiments are disclosed for performing 3-D vectorization. The method includes obtaining a three-dimensional rendered image and a camera position. The method further includes obtaining a triangle mesh representing the three-dimensional rendered image. The method further involves creating a reduced triangle mesh by removing one or more triangles from the triangle mesh. The method further involves subdividing each triangle of the reduced triangle mesh into one or more subdivided triangles. The method further involves performing a mapping of each pixel of the three-dimensional rendered image to the reduced triangle mesh. The method further involves assigning a color value to each vertex of the reduced triangle mesh. The method further involves sorting each triangle of the reduced triangle mesh using a depth value of each triangle. The method further involves generating a two-dimensional triangle mesh using the sorted triangles of the reduced triangle mesh.

Abstract: A content generator system receives a request to generate content for a target entity, and one or more keywords. The content generator system retrieves, for the target entity, a current stage identifier linking the target entity to a current stage within a multi-stage objective. The content generator system generates an input vector including the current stage identifier, a target stage identifier, a token embedding comprising the one or more keywords, and a position embedding for each of the one or more keywords, the target stage identifier associated with a target stage within the multi-stage objective different from the current stage. The content generator system generates output text content for the target entity by applying a generative transformer network to the input vector. The content generator system transmits the output text content to a computing device associated with the target entity.

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for generating an ambient occlusion (AO) map for a 2D image that can be combined with the 2D image to adjust the contrast of the 2D image based on the geometric information in the 2D image. In embodiments, using a trained neural network, an AO map for a 2D image is automatically generated without any predefined 3D scene information. Optimizing the neural network to generate an estimated AO map for a 2D image requires training, testing, and validating the neural network using a synthetic dataset comprised of pairs of images and ground truth AO maps rendered from 3D scenes. By using an estimated AO map to adjust the contrast of a 2D image, the contrast of the image can be adjusted to make the image appear lifelike by modifying the shadows and shading in the image based on the ambient lighting present in the image.

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that utilize a drawing application technique that enables a simulation of digital spirograph designs within electronic drawing applications. In some embodiments, the disclosed systems receive a user selection of a primary shape. Moreover, in one or more implementations, the disclosed systems detect a user interaction with a contact point within a secondary shape to move the contact point from a first location to a second location. Furthermore, in one or more instances, the disclosed systems generate, for display, a digital line drawing from the first location to the second location utilizing a movement of the contact point in relation to a rotation of a secondary curve of the secondary shape along a movement path corresponding to a primary curve of the primary shape based on the user interaction with the contact point.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating marked digital images with content adaptive watermarks. In particular, in one or more embodiments, the disclosed systems intelligently evaluate a plurality of watermark configurations to select one or more content adaptive watermarks for one or more target digital images and generate one or more marked digital images by adding the selected content adaptive watermarks to the one or more target digital images.

Abstract: Real time pattern preview generation and capture techniques are described. In an example, a live stream of digital images is displayed in a user interface by a computing device. A real time preview of visual patterns in the user interface is then generated and displayed based on the digital images. The visual patterns, for instance, are generated by the computing device in real time using a combination of shape extraction and pattern generation. An option is also made available to convert the real time preview into a vector image, such as a vector pattern tile.

Abstract: Decal application techniques as implemented by a computing device are described to perform decaling of a digital image. In one example, learned features of a digital image using machine learning are used by a computing device as a basis to predict the surface geometry of an object in the digital image. Once the surface geometry of the object is predicted, machine learning techniques are then used by the computing device to configure an overlay object to be applied onto the digital image according to the predicted surface geometry of the overlaid object.

Abstract: In implementation of techniques for vectorizing by piecewise deconstruction of object strokes, a computing device implements an image processing system to receive an input to initiate the generation of a boundary of an object in a digital image, such as a raster image. The image processing system detects a set of visually separated but semantically related strokes that represent the object's boundary. Based on the set of visually separated but semantically related strokes, the image processing system forms a combined stroke and generates the boundary of the object as a path based on the combined stroke. The resulting path mimics the visual appearance of the object in the digital image in a vector space.