Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly identifying and providing digital images of human figures in poses corresponding to a query pose. In particular, the disclosed systems can provide multiple approaches to searching for and providing pose images, including identifying a digital image depicting a human figure in a particular pose based on a query digital image that depicts the pose or identifying a digital image depicting a human figure in a particular pose based on a virtual mannequin. Indeed, the disclosed systems can provide a manipulable virtual mannequin that defines a query pose for searching a repository of digital images. Additionally, the disclosed systems can generate and provide digital pose image groups by clustering digital images together according to poses of human figures within a pose feature space.

Abstract: Systems and methods dynamically adjust an available range for editing an attribute in an image. An image editing system computes a metric for an attribute in an input image as a function of a latent space representation of the input image and a filtering vector for editing the input image. The image editing system compares the metric to a threshold. If the metric exceeds the threshold, then the image editing system selects a first range for editing the attribute in the input image. If the metric does not exceed the threshold, a second range is selected. The image editing system causes display of a user interface for editing the input image comprising an interface element for editing the attribute within the selected range.

Abstract: Systems and methods train an encoder neural network for fast and accurate projection into the latent space of a Generative Adversarial Network (GAN). The encoder is trained by providing an input training image to the encoder and producing, by the encoder, a latent space representation of the input training image. The latent space representation is provided as input to the GAN to generate a generated training image. A latent code is sampled from a latent space associated with the GAN and the sampled latent code is provided as input to the GAN. The GAN generates a synthetic training image based on the sampled latent code. The sampled latent code is provided as input to the encoder to produce a synthetic training code. The encoder is updated by minimizing a loss between the generated training image and the input training image, and the synthetic training code and the sampled latent code.

Abstract: Systems and methods train and apply a specialized encoder neural network for fast and accurate projection into the latent space of a Generative Adversarial Network (GAN). The specialized encoder neural network includes an input layer, a feature extraction layer, and a bottleneck layer positioned after the feature extraction layer. The projection process includes providing an input image to the encoder and producing, by the encoder, a latent space representation of the input image. Producing the latent space representation includes extracting a feature vector from the feature extraction layer, providing the feature vector to the bottleneck layer as input, and producing the latent space representation as output. The latent space representation produced by the encoder is provided as input to the GAN, which generates an output image based upon the latent space representation. The encoder is trained using specialized loss functions including a segmentation loss and a mean latent loss.

Abstract: Systems and methods use a non-linear latent filter neural network for editing an image. An image editing system trains a first neural network by minimizing a loss based upon a predicted attribute value for a target attribute in a training image. The image editing system obtains a latent space representation of an input image to be edited and a target attribute value for the target attribute in the input image. The image editing system provides the latent space representation and the target attribute value as input to the trained first neural network for modifying the target attribute in the input image to generate a modified latent space representation of the input image. The image editing system provides the modified latent space representation as input to a second neural network to generate an output image with a modification to the target attribute corresponding to the target attribute value.

Abstract: Systems and methods generate a filtering function for editing an image with reduced attribute correlation. An image editing system groups training data into bins according to a distribution of a target attribute. For each bin, the system samples a subset of the training data based on a pre-determined target distribution of a set of additional attributes in the training data. The system identifies a direction in the sampled training data corresponding to the distribution of the target attribute to generate a filtering vector for modifying the target attribute in an input image, obtains a latent space representation of an input image, applies the filtering vector to the latent space representation of the input image to generate a filtered latent space representation of the input image, and provides the filtered latent space representation as input to a neural network to generate an output image with a modification to the target attribute.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

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 determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

Abstract: Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.

Abstract: Systems and methods are described for object detection within a digital image using a hierarchical softmax function. The method may include applying a first softmax function of a softmax hierarchy on a digital image based on a first set of object classes that are children of a root node of a class hierarchy, then apply a second (and subsequent) softmax functions to the digital image based on a second (and subsequent) set of object classes, where the second (and subsequent) object classes are children nodes of an object class from the first (or parent) object classes. The methods may then include generating an object recognition output using a convolutional neural network (CNN) based at least in part on applying the first and second (and subsequent) softmax functions. In some cases, the hierarchical softmax function is the loss function for the CNN.

Abstract: Based on a received digital image and text, a neural network trained to identify candidate text placement areas within images may be used to generate a mask for the digital image that includes a candidate text placement area. A bounding box for the digital image may be defined for the text and based on the candidate text placement area, and the text may be superimposed onto the digital image within the bounding box.

Abstract: Content creation and licensing control techniques are described. In a first example, a content creation service is configured to support content creation using an image along with functionality to locate the image or a similar image that is available for licensing. In another example, previews of images are used to generate different versions of content along with an option to license images previewed in an approved version of the content. In a further example, fingerprints are used to locate images used as part of content creation by a content creation service without leaving a context of the service. In yet another example, location of licensable versions of images is based at least in part on identification of a watermark included as part of an image. In an additional example, an image itself is used as a basis to locate other images available for licensing by a content sharing service.

Abstract: Systems and methods for searching digital content, such as digital images, are disclosed. A method includes receiving a first search constraint and generating search results based on the first search constraint. A search constraint includes search values or criteria. The search results include a ranked set of digital images. A second search constraint and a weight value associated with the second search constraint are received. The search results are updated based on the second search constraint and the weight value. The updated search results are provided to a user. Updating the search results includes determining a ranking (or a re-ranking) for each item of content included in the search results based on the first search constraint, the second search constraint, and the weight value. Re-ranking the search results may further be based on a weight value associated with the first search constraint, such as a default or maximum weight value.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

Abstract: Content search and geographical consideration techniques and system employed as part of a digital environment are described. In one or more implementations, a digital medium environment is described for configuring image searches by one or more computing devices. Data is received by the one or more computing devices that identifies images obtained by users and used as part of content creation, indicates geographical locations of respective said users that obtained the images or associated with the content that includes the images, and indicates times associated with the users as obtaining the images or use of the images as part of the content. A map is built by the one or more computing devices that describes how use of the images as part of the content creation is diffused over the geographical locations over the indicated times. An image search is controlled by the one or more computing devices based on the map and a geographic location associated with the image search.

Abstract: Systems and methods are described for object detection within a digital image using a hierarchical softmax function. The method may include applying a first softmax function of a softmax hierarchy on a digital image based on a first set of object classes that are children of a root node of a class hierarchy, then apply a second (and subsequent) softmax functions to the digital image based on a second (and subsequent) set of object classes, where the second (and subsequent) object classes are children nodes of an object class from the first (or parent) object classes. The methods may then include generating an object recognition output using a convolutional neural network (CNN) based at least in part on applying the first and second (and subsequent) softmax functions. In some cases, the hierarchical softmax function is the loss function for the CNN.

Abstract: The present disclosure is directed toward systems and methods for detecting an object in an input image based on a target object keyword. For example, one or more embodiments described herein generate a heat map of the input image based on the target object keyword and generate various bounding boxes based on a pixel analysis of the heat map. One or more embodiments described herein then utilize the various bounding boxes to determine scores for generated object location proposals in order to provide a highest scoring object location proposal overlaid on the input image.

Abstract: In various implementations, specific attributes found in images can be used in a visual-based search. Utilizing machine learning, deep neural networks, and other computer vision techniques, attributes of images, such as color, composition, font, style, and texture can be extracted from a given image. A user can then select a specific attribute from a sample image the user is searching for and the search can be refined to focus on that specific attribute from the sample image. In some embodiments, the search includes specific attributes from more than one image.

Abstract: In various implementations, one or more specific attributes found in an image can be modified utilizing one or more specific attributes found in another image. Machine learning, deep neural networks, and other computer vision techniques can be utilized to extract attributes of images, such as color, composition, font, style, and texture from one or more images. A user may modify at least one of these attributes in a first image based on the attribute(s) of another image and initiate a visual-based search using the modified image.