Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

Abstract: Techniques are disclosed for a facial expression classification. In an embodiment, a multi-class classifier is trained using labelled training images, each training image including a facial expression. The trained classifier is then used to predict expressions for unlabelled video frames, whereby each frame is effectively labelled with a predicted expression. In addition, each predicted expression can be associated with a confidence score. Anchor frames can then be identified in the labelled video frames, based on the confidence scores of those frames (anchor frames are frames having a confidence score above an established threshold). Then, for each labelled video frame between two anchor frames, the predicted expression is refined or otherwise updated using interpolation, thereby providing a set of video frames having calibrated expression labels.

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media that automatically select an image from a plurality of images based on the multi-context aware rating of the image. In particular, systems described herein can generate a plurality of probability context scores for an image. Moreover, the disclosed systems can generate a plurality of context-specific scores for an image. Utilizing each of the probability context scores and each of the corresponding context-specific scores for an image, the disclosed systems can generate a multi-context aware rating for the image. Thereafter, the disclosed systems can select an image from the plurality of images with the highest multi-context aware rating for delivery to the user. The disclosed system can utilize one or more neural networks to both generate the probability context scores for an image and to generate the context-specific scores for an image.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for segmenting objects in digital visual media utilizing one or more salient content neural networks. In particular, in one or more embodiments, the disclosed systems and methods train one or more salient content neural networks to efficiently identify foreground pixels in digital visual media. Moreover, in one or more embodiments, the disclosed systems and methods provide a trained salient content neural network to a mobile device, allowing the mobile device to directly select salient objects in digital visual media utilizing a trained neural network. Furthermore, in one or more embodiments, the disclosed systems and methods train and provide multiple salient content neural networks, such that mobile devices can identify objects in real-time digital visual media feeds (utilizing a first salient content neural network) and identify objects in static digital images (utilizing a second salient content neural network).

Abstract: Techniques and system are described to control output of digital marketing content with respect to a digital video that address the added complexities of digital video over other types of digital content, such as webpages. In one example, the techniques and systems are configured to control a time, at which, digital marketing content is to be output with respect to the digital video, e.g., by selecting a commercial break or output as a banner ad in conjunction with the video.

Abstract: Application personalization techniques and systems are described that leverage an embedded machine learning module to preserve a user's privacy while still supporting rich personalization with improved accuracy and efficiency of use of computational resources over conventional techniques and systems. The machine learning module, for instance, may be embedded as part of an application to execute within a context of the application to learn user preferences to train a model using machine learning. This model is then used within the context of execution of the application to personalize the application, such as control access to digital content, make recommendations, control which items of digital marketing content are exposed to a user via the application, and so on.

Abstract: Application personalization techniques and systems are described that leverage an embedded machine learning module to preserve a user's privacy while still supporting rich personalization with improved accuracy and efficiency of use of computational resources over conventional techniques and systems. The machine learning module, for instance, may be embedded as part of an application to execute within a context of the application to learn user preferences to train a model using machine learning. This model is then used within the context of execution of the application to personalize the application, such as control access to digital content, make recommendations, control which items of digital marketing content are exposed to a user via the application, and so on.

Abstract: Techniques and system are described to control output of digital marketing content with respect to digital content. This is achieved by leveraging additional insight that may be gained from external service systems that describe the digital content, e.g., social network systems, digital content review systems, and so forth. In one example, the techniques and systems are configured to collect social network data that describes social network communications communicated via a social network system. Natural language processing techniques are then performed as part of machine learning to detect interest of a user population associated with the social network communications.

Abstract: Missing region prediction techniques are described. In implementations, an image pair is obtained that includes first and second images. The first image is corrupted by removing a region of content, resulting in a corrupted image having a missing region. The corrupted image and the second image of the image pair are then used to generate a training-image pair. Then, based on a plurality of training-image pairs including the generated training-image pair, a model is trained using machine learning. The model can subsequently be used to predict pixel values of pixels within a subsequent missing region of a subsequent image that is not used as part of the training.

Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

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: Methods and apparatus for manipulating digital images. A warping module is described that enables the manipulation of a surface by selectively deforming portions of the surface while maintaining local rigidity. The user may position multiple control points on a surface to constrain deformation. The user may specify multiple properties (e.g., translation, rotation, depth, and scale) at each control point. A mesh may be overlaid on the surface. The warping module may perform an initialization in which the properties are propagated other vertices in the mesh to generate an initial deformed mesh. The warping module may then perform an iterative optimization operation on the deformed mesh to improve the deformation while retaining local rigidity. Thus, instead of moving every pixel in the surface, the warping module moves or adjusts coordinates of the vertices of the mesh. The surface is then deformed according to the deformed mesh.

Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

Abstract: Methods and apparatus for manipulating digital images. A warping module is described that enables the manipulation of a surface by selectively deforming portions of the surface while maintaining local rigidity. The user may position multiple control points on a surface to constrain deformation. The user may specify multiple properties (e.g., translation, rotation, depth, and scale) at each control point. A mesh may be overlaid on the surface. The warping module may perform an initialization in which the properties are propagated other vertices in the mesh to generate an initial deformed mesh. The warping module may then perform an iterative optimization operation on the deformed mesh to improve the deformation while retaining local rigidity. Thus, instead of moving every pixel in the surface, the warping module moves or adjusts coordinates of the vertices of the mesh. The surface is then deformed according to the deformed mesh.