Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for guided visual search. A visual search query can be represented as a sketch sequence that includes ordering information of the constituent strokes in the sketch. The visual search query can be encoded into a structural search encoding in a common search space by a structural neural network. Indexed visual search results can be identified in the common search space and clustered in an auxiliary semantic space. Sketch suggestions can be identified from a plurality of indexed sketches in the common search space. A sketch suggestion can be identified for each semantic cluster of visual search results and presented with the cluster to guide a user towards relevant content through an iterative search process. Selecting a sketch suggestion as a target sketch can automatically transform the visual search query to the target sketch via adversarial images.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating difference captions indicating detected differences in digital image pairs. The disclosed system generates a first feature map of a first digital image and a second feature map of a second digital image. The disclosed system converts, utilizing a linear projection neural network, the first feature map to a first modified feature map in a feature space corresponding to a large language machine-learning model. The disclosed system also converts, utilizing the linear projection neural network layer, the second feature map to a second modified feature map in the feature space corresponding to the large language machine-learning model.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize a deep visual fingerprinting model with parameters learned from robust contrastive learning to identify matching digital images and image provenance information. For example, the disclosed systems utilize an efficient learning procedure that leverages training on bounded adversarial examples to more accurately identify digital images (including adversarial images) with a small computational overhead. To illustrate, the disclosed systems utilize a first objective function that iteratively identifies augmentations to increase contrastive loss. Moreover, the disclosed systems utilize a second objective function that iteratively learns parameters of a deep visual fingerprinting model to reduce the contrastive loss.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize deep learning to map query videos to known videos so as to identify a provenance of the query video or identify editorial manipulations of the query video relative to a known video. For example, the video comparison system includes a deep video comparator model that generates and compares visual and audio descriptors utilizing codewords and an inverse index. The deep video comparator model is robust and ignores discrepancies due to benign transformations that commonly occur during electronic video distribution.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize deep learning to map query videos to known videos so as to identify a provenance of the query video or identify editorial manipulations of the query video relative to a known video. For example, the video comparison system includes a deep video comparator model that generates and compares visual and audio descriptors utilizing codewords and an inverse index. The deep video comparator model is robust and ignores discrepancies due to benign transformations that commonly occur during electronic video distribution.

Abstract: Systems and methods for managing rights for creative work are provided. One aspect of the systems and methods includes receiving, at a rights contract on a distributed virtual machine operated based on a public blockchain, input data including an ownership token identifier for an ownership token, where the ownership token indicates ownership of a creative work. Another aspect of the systems and methods includes obtaining, at the rights contract, an indication of usage rights for the creative work corresponding to the ownership token. Yet another aspect of the systems and methods includes minting, via the rights contract, a rights token corresponding to the ownership token, where the rights token includes a reference to the indication of the usage rights for the creative work.

Abstract: Techniques and systems are provided for configuring neural networks to perform certain image manipulation operations. For instance, in response to obtaining an image for manipulation, an image manipulation system determines the fitness scores for a set of neural networks resulting from the processing of a noise map. Based on these fitness scores, the image manipulation system selects a subset of the set of neural networks for cross-breeding into a new generation of neural networks. The image manipulation system evaluates the performance of this new generation of neural networks and continues cross-breeding this neural networks until a fitness threshold is satisfied. From the final generation of neural networks, the image manipulation system selects a neural network that provides a desired output and uses the neural network to generate the manipulated image.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize deep learning to map query videos to known videos so as to identify a provenance of the query video or identify editorial manipulations of the query video relative to a known video. For example, the video comparison system includes a deep video comparator model that generates and compares visual and audio descriptors utilizing codewords and an inverse index. The deep video comparator model is robust and ignores discrepancies due to benign transformations that commonly occur during electronic video distribution.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize deep learning to identify regions of an image that have been editorially modified. For example, the image comparison system includes a deep image comparator model that compares a pair of images and localizes regions that have been editorially manipulated relative to an original or trusted image. More specifically, the deep image comparator model generates and surfaces visual indications of the location of such editorial changes on the modified image. The deep image comparator model is robust and ignores discrepancies due to benign image transformations that commonly occur during electronic image distribution. The image comparison system optionally includes an image retrieval model utilizes a visual search embedding that is robust to minor manipulations or benign modifications of images. The image retrieval model utilizes a visual search embedding for an image to robustly identify near duplicate images.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly identifying digital images with similar style to a query digital image using fine-grain style determination via weakly supervised style extraction neural networks. For example, the disclosed systems can extract a style embedding from a query digital image using a style extraction neural network such as a novel two-branch autoencoder architecture or a weakly supervised discriminative neural network. The disclosed systems can generate a combined style embedding by combining complementary style embeddings from different style extraction neural networks. Moreover, the disclosed systems can search a repository of digital images to identify digital images with similar style to the query digital image.

Abstract: Embodiments are disclosed for learning structural similarity of user experience (UX) designs using machine learning. In particular, in one or more embodiments, the disclosed systems and methods comprise generating a representation of a layout of a graphical user interface (GUI), the layout including a plurality of control components, each control component including a control type, geometric features, and relationship features to at least one other control component, generating a search embedding for the representation of the layout using a neural network, and querying a repository of layouts in embedding space using the search embedding to obtain a plurality of layouts based on similarity to the layout of the GUI in the embedding space.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize a deep visual fingerprinting model with parameters learned from robust contrastive learning to identify matching digital images and image provenance information. For example, the disclosed systems utilize an efficient learning procedure that leverages training on bounded adversarial examples to more accurately identify digital images (including adversarial images) with a small computational overhead. To illustrate, the disclosed systems utilize a first objective function that iteratively identifies augmentations to increase contrastive loss. Moreover, the disclosed systems utilize a second objective function that iteratively learns parameters of a deep visual fingerprinting model to reduce the contrastive loss.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly identifying digital images with similar style to a query digital image using fine-grain style determination via weakly supervised style extraction neural networks. For example, the disclosed systems can extract a style embedding from a query digital image using a style extraction neural network such as a novel two-branch autoencoder architecture or a weakly supervised discriminative neural network. The disclosed systems can generate a combined style embedding by combining complementary style embeddings from different style extraction neural networks. Moreover, the disclosed systems can search a repository of digital images to identify digital images with similar style to the query digital image.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for guided visual search. A visual search query can be represented as a sketch sequence that includes ordering information of the constituent strokes in the sketch. The visual search query can be encoded into a structural search encoding in a common search space by a structural neural network. Indexed visual search results can be identified in the common search space and clustered in an auxiliary semantic space. Sketch suggestions can be identified from a plurality of indexed sketches in the common search space. A sketch suggestion can be identified for each semantic cluster of visual search results and presented with the cluster to guide a user towards relevant content through an iterative search process. Selecting a sketch suggestion as a target sketch can automatically transform the visual search query to the target sketch via adversarial images.

Abstract: Techniques and systems are provided for configuring neural networks to perform certain image manipulation operations. For instance, in response to obtaining an image for manipulation, an image manipulation system determines the fitness scores for a set of neural networks resulting from the processing of a noise map. Based on these fitness scores, the image manipulation system selects a subset of the set of neural networks for cross-breeding into a new generation of neural networks. The image manipulation system evaluates the performance of this new generation of neural networks and continues cross-breeding this neural networks until a fitness threshold is satisfied. From the final generation of neural networks, the image manipulation system selects a neural network that provides a desired output and uses the neural network to generate the manipulated image.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for guided visual search. A visual search query can be represented as a sketch sequence that includes ordering information of the constituent strokes in the sketch. The visual search query can be encoded into a structural search encoding in a common search space by a structural neural network. Indexed visual search results can be identified in the common search space and clustered in an auxiliary semantic space. Sketch suggestions can be identified from a plurality of indexed sketches in the common search space. A sketch suggestion can be identified for each semantic cluster of visual search results and presented with the cluster to guide a user towards relevant content through an iterative search process. Selecting a sketch suggestion as a target sketch can automatically transform the visual search query to the target sketch via adversarial images.