Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

Abstract: A first set of attributes (e.g., style) is generated through pre-trained single column neural networks and leveraged to regularize the training process of a regularized double-column convolutional neural network (RDCNN). Parameters of the first column (e.g., style) of the RDCNN are fixed during RDCNN training. Parameters of the second column (e.g., aesthetics) are fine-tuned while training the RDCNN and the learning process is supervised by the label identified by the second column (e.g., aesthetics). Thus, features of the images may be leveraged to boost classification accuracy of other features by learning a RDCNN.

Abstract: Embodiments of the present invention relate to finding semantic parts in images. In implementation, a convolutional neural network (CNN) is applied to a set of images to extract features for each image. Each feature is defined by a feature vector that enables a subset of the set of images to be clustered in accordance with a similarity between feature vectors. Normalized cuts may be utilized to help preserve pose within each cluster. The images in the cluster are aligned and part proposals are generated by sampling various regions in various sizes across the aligned images. To determine which part proposal corresponds to a semantic part, a classifier is trained for each part proposal and semantic part to determine which part proposal best fits the correlation pattern given by the true semantic part. In this way, semantic parts in images can be identified without any previous part annotations.

Abstract: Font recognition and similarity determination techniques and systems are described. For example, a computing device receives an image including a font and extracts font features corresponding to the font. The computing device computes font feature distances between the font and fonts from a set of training fonts. The computing device calculates, based on the font feature distances, similarity scores for the font and the training fonts used for calculating features distances. The computing device determines, based on the similarity scores, final similarity scores for the font relative to the training fonts.

Abstract: Font replacement based on visual similarity is described. In one or more embodiments, a font descriptor includes multiple font features derived from a visual appearance of a font by a font visual similarity model. The font visual similarity model can be trained using a machine learning system that recognizes similarity between visual appearances of two different fonts. A source computing device embeds a font descriptor in a document, which is transmitted to a destination computing device. The destination compares the embedded font descriptor to font descriptors corresponding to local fonts. Based on distances between the embedded and the local font descriptors, at least one matching font descriptor is determined. The local font corresponding to the matching font descriptor is deemed similar to the original font. The destination computing device controls presentations of the document using the similar local font. Computation of font descriptors can be outsourced to a remote location.

Abstract: Embodiments of the present invention are directed at providing a font similarity preview for non-resident fonts. In one embodiment, a font is selected on a computing device. In response to the selection of the font, a pre-computed font list is checked to determine what fonts are similar to the selected font. In response to a determination that similar fonts are not local to the computing device, a non-resident font list is sent to a font vendor. The font vendor sends back previews of the non-resident fonts based on entitlement information of a user. Further, a full non-resident font can be synced to the computing device. Other embodiments may be described and/or claimed.

Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

Abstract: A method and systems of identifying one or more patches in three or more frames in a video are provided. A region in a reference frame of the video may be detected. A set of regions in a prior frame and subsequent frame that are similar to the region in the reference frame may then be identified. Temporal consistency between the region in the reference frame and two or more regions in the set of regions in the prior and subsequent frames may then be calculated. Patches of regions in the first, reference, and third frames may be identified based at least in part on the calculated temporal consistencies, with each patch identifying a region in the reference frame that can be mapped to a similar region in the prior and subsequent frames.

Abstract: Patch partition and image processing techniques are described. In one or more implementations, a system includes one or more modules implemented at least partially in hardware. The one or more modules are configured to perform operations including grouping a plurality of patches taken from a plurality of training samples of images into respective ones of a plurality of partitions, calculating an image processing operator for each of the partitions, determining distances between the plurality of partitions that describe image similarity of patches of the plurality of partitions, one to another, and configuring a database to provide the determined distance and the image processing operator to process an image in response to identification of a respective partition that corresponds to a patch taken from the image.

Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

Abstract: Content update and suggestion techniques are described. In one or more implementations, techniques are implemented to generate suggestions that are usable to guide creative professionals in updating content such as images, video, sound, multimedia, and so forth. A variety of techniques are usable to generate suggestions for the content professionals. In one example, suggestions are based on shared characteristics of images licensed by users of a content sharing service, e.g., licensed by the users. In another example, suggestions are based on metadata of the images licensed by the users, the metadata describing characteristics of how the images are created. These suggestions are then used to guide transformation of a user's image such that the image exhibits these characteristics and thus has an increased likelihood of being desired for licensing by customers of the service.

Abstract: Techniques for image captioning with weak supervision are described herein. In implementations, weak supervision data regarding a target image is obtained and utilized to provide detail information that supplements global image concepts derived for image captioning. Weak supervision data refers to noisy data that is not closely curated and may include errors. Given a target image, weak supervision data for visually similar images may be collected from sources of weakly annotated images, such as online social networks. Generally, images posted online include “weak” annotations in the form of tags, titles, labels, and short descriptions added by users. Weak supervision data for the target image is generated by extracting keywords for visually similar images discovered in the different sources. The keywords included in the weak supervision data are then employed to modulate weights applied for probabilistic classifications during image captioning analysis.

Abstract: Techniques for image captioning with word vector representations are described. In implementations, instead of outputting results of caption analysis directly, the framework is adapted to output points in a semantic word vector space. These word vector representations reflect distance values in the context of the semantic word vector space. In this approach, words are mapped into a vector space and the results of caption analysis are expressed as points in the vector space that capture semantics between words. In the vector space, similar concepts with have small distance values. The word vectors are not tied to particular words or a single dictionary. A post-processing step is employed to map the points to words and convert the word vector representations to captions. Accordingly, conversion is delayed to a later stage in the process.

Abstract: Patch partition and image processing techniques are described. In one or more implementations, a system includes one or more modules implemented at least partially in hardware. The one or more modules are configured to perform operations including grouping a plurality of patches taken from a plurality of training samples of images into respective ones of a plurality of partitions, calculating an image processing operator for each of the partitions, determining distances between the plurality of partitions that describe image similarity of patches of the plurality of partitions, one to another, and configuring a database to provide the determined distance and the image processing operator to process an image in response to identification of a respective partition that corresponds to a patch taken from the image.

Abstract: Embodiments of the present invention are directed at providing a font similarity system. In one embodiment, a new font is detected on a computing device. In response to the detection of the new font, a pre-computed font list is checked to determine whether the new font is included therein. The pre-computed font list including feature representations, generated independently of the computing device, for corresponding fonts. In response to a determination that the new font is absent from the pre-computed font list, a feature representation for the new font is generated. The generated feature representation capable of being utilized for a similarity analysis of the new font. The feature representation is then stored in a supplemental font list to enable identification of one or more fonts installed on the computing device that are similar to the new font. Other embodiments may be described and/or claimed.

Abstract: Techniques for predictively selecting a content presentation in a client-server computing environment are described. In an example, a content management system detects an interaction of a client with a server and accesses client features. Reponses of the client to potential content presentations are predicted based on a multi-task neural network. The client features are mapped to input nodes and the potential content presentations are associated with tasks mapped to output nodes of the multi-task neural network. The tasks specify usages of the potential content presentations in response to the interaction with the server. In an example, the content management system selects the content presentation from the potential content presentations based on the predicted responses. For instance, the content presentation is selected based on having the highest likelihood. The content management system provides the content presentation to the client based on the task corresponding to the content presentation.

Abstract: Plane detection and tracking algorithms are described that may take point trajectories as input and provide as output a set of inter-image homographies. The inter-image homographies may, for example, be used to generate estimates for 3D camera motion, camera intrinsic parameters, and plane normals using a plane-based self-calibration algorithm. A plane detection and tracking algorithm may obtain a set of point trajectories for a set of images (e.g., a video sequence, or a set of still photographs). A 2D plane may be detected from the trajectories, and trajectories that follow the 2D plane through the images may be identified. The identified trajectories may be used to compute a set of inter-image homographies for the images as output.

Abstract: In one embodiment, a computer accessible storage medium stores a plurality of instructions which, when executed: group a set of reconstructed three dimensional (3D) points derived from image data into a plurality of groups based on one or more attributes of the 3D points; select one or more groups from the plurality of groups; and sample data from the selected groups, wherein the sampled data is input to a consensus estimator to generate a model that describes a 3D model of a scene captured by the image data. Other embodiments may bias sampling into a consensus estimator for any data set, based on relative quality of the data set.

Abstract: Certain embodiments involve learning features of content items (e.g., images) based on web data and user behavior data. For example, a system determines latent factors from the content items based on data including a user's text query or keyword query for a content item and the user's interaction with the content items based on the query (e.g., a user's click on a content item resulting from a search using the text query). The system uses the latent factors to learn features of the content items. The system uses a previously learned feature of the content items for iterating the process of learning features of the content items to learn additional features of the content items, which improves the accuracy with which the system is used to learn other features of the content items.

Abstract: Embedding space for images with multiple text labels is described. In the embedding space both text labels and image regions are embedded. The text labels embedded describe semantic concepts that can be exhibited in image content. The embedding space is trained to semantically relate the embedded text labels so that labels like “sun” and “sunset” are more closely related than “sun” and “bird”. Training the embedding space also includes mapping representative images, having image content which exemplifies the semantic concepts, to respective text labels. Unlike conventional techniques that embed an entire training image into the embedding space for each text label associated with the training image, the techniques described herein process a training image to generate regions that correspond to the multiple text labels. The regions of the training image are then embedded into the training space in a manner that maps the regions to the corresponding text labels.