Ebay, Incorporated

Paypal, Inc.

Microsoft Technology Licensing, LLC

Wei Di

Robinson Piramuthu

Anurag Bhardwaj

Vignesh Jagadeesh

Neelakantan Sundaresan

Elizabeth F Churchill

Muhammad Raffay Hamid

Mohammad Haris Baig

Mohammadhadi Kiapour

Chen-Yu Lee

Vicente Ordonez-Roman

Rohit Pandey

Nate L Lyman

Songtao Guo

Nidhi Sehgal

Ho Jeong Kim

Zixuan Wang

M Hadi Kiapour

Zhicheng Yan

Jilei Yang

Dennis Decoste

A machine may be configured to perform image evaluation of images depicting items for sale and to provide recommendations for improving the images depicting the items to increase the sales of the items depicted in the images. For example, the machine accesses a result of a user behavior analysis. The machine receives an image of an item from a user device. The machine performs an image evaluation of the received image based on an analysis of the received image and the result of the user behavior analysis. The performing of the image evaluation may include determining a likelihood of a user engaging in a desired user behavior in relation to the received image. Then, the machine generates, based on the evaluation of the received image, an output that references the received image and indicates the likelihood of a user engaging in the desired behavior.

Image evaluation

A machine may be configured to execute a machine-learning process for identifying and understanding fine properties of various items of various types by using images and associated corresponding annotations, such as titles, captions, tags, keywords, or other textual information applied to these images. By use of a machine-learning process, the machine may perform property identification accurately and without human intervention. These item properties may be used as annotations for other images that have similar features. Accordingly, the machine may answer user-submitted questions, such as 'What do rustic items look like?,' and items or images depicting items that are deemed to be rustic can be readily identified, classified, ranked, or any suitable combination thereof.

Correlating image annotations with foreground features

A machine is configured to determine fashion preferences of users and to provide item recommendations based on the fashion preferences. For example, the machine accesses an indication of a fashion style of a user. The fashion style is determined based on automatically captured data pertaining to the user. The machine identifies, based on the fashion style, one or more fashion items from an inventory of fashion items. The machine generates one or more selectable user interface elements for inclusion in a user interface. The one or more user interface elements correspond to the one or more fashion items. The machine causes generation and display of the user interface that includes the one or more selectable user interface elements. A selection of a selectable user interface element results in display of a combination of an image of a particular fashion item and an image of an item worn by the user.

Fashion preference analysis

In an example, for each feature of one or more features of a target sample data, feature values for one or more pseudo-samples are generated using, localized stratified sampling. The one or more pseudo-samples are fed into the trained machine learned model to obtain their prediction values. A piecewise linear regression model is trained using the one or more pseudo-samples and their prediction values, the piecewise linear regression model having two coefficients for each feature, a first coefficient describing prediction change when a corresponding feature value is increased and a second coefficient describing prediction change when a corresponding feature value is decreased. A top positive feature influencer is identified based on a feature of the one or more features of the target sample having a greatest magnitude of positive first coefficient or greatest magnitude of negative second coefficient. A top negative feature influencer is identified based on a feature of the one or more features of the target sample having a greatest magnitude of negative first coefficient or greatest magnitude of positive second coefficient. A top feature contributor is identified based on a feature of the one or more features of the target sample having a greatest magnitude of a combination of second coefficient and feature value in the target sample data.

Feature contributors and influencers in machine learned predictive models

An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.

Fine-grained categorization

A configured machine performs image matching and retrieval of natural images that may depict logos. The machine generates and uses color-localized spatial masks, which may be computationally less expensive than spatial verification techniques. Key points are detected within images that form a reference database of images. Local masks are defined by the machine around each key point based on the scale and orientation of the key point. To utilize color information presented in logo images, ordered color histograms may be extracted by the machine from locally masked regions of each image. A cascaded index may then be constructed for both visual descriptors and color histograms. For faster matching, the cascaded index maps the visual descriptors and color histograms to a list of relevant or similar images. This list may then be ranked to generate relevant matches for an input query image.

Image processing and matching

An apparatus and method to facilitate providing recommendations are disclosed herein. A networked system receives a query image, and performs image processing to extract a color histogram of an item depicted in the query image. The networked system identifies a dominant color of the item, whereby the dominant color is a color that is present on a most spatial area of the item relative to any other color of the item. The color histogram of the item is compared with a color histogram of an image of each of a plurality of available items, or the dominate color of the item is compared with a dominate color of the image of each of a plurality of available items. Based on the comparing, the networked system identifies item recommendations of the available items that closely match the item depicted in the query image, and the item recommendations are presented.

Item recommendations using image feature data

Hierarchical branching deep convolutional neural networks (HD-CNNs) improve existing convolutional neural network (CNN) technology. In a HD-CNN, classes that can be easily distinguished are classified in a higher layer coarse category CNN, while the most difficult classifications are done on lower layer fine category CNNs. Multinomial logistic loss and a novel temporal sparsity penalty may be used in HD-CNN training. The use of multinomial logistic loss and a temporal sparsity penalty causes each branching component to deal with distinct subsets of categories.

Hierarchical deep convolutional neural network for image classification

A content propagation system includes processors, memory storing user activity data and interaction data on a social network, and a content propagation engine configured to receive an indication of a share event from the sharing user, the share event including a content item, identify a plurality of target users for the share event, identify a plurality of time blocks, compute an activity value for each target user of the plurality of target users, and for each time block of the plurality of time blocks, the activity value is based on the user activity data, compute an engagement value for each target user based at least in part on the interaction data, determine a share time based at least in part on the plurality of activity values and the plurality of engagement values, and publish the content item to the plurality of target users at the share time.

Systems and methods for timely propagation of network content

During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.

Estimating depth from a single image

A machine may be configured to perform image evaluation of images depicting items for online publishing. For example, the machine performing a user behavior analysis based on data pertaining to interactions by a plurality of users with a plurality of images pertaining to a particular type of item. The machine determines, based on the user behavior analysis, that a presentation type associated with one or more images of the plurality of images corresponds to a user behavior in relation to the one or more images. The machine determines that an item included in a received image is of the particular type of item. The machine generates an output for display in a client device. The output includes a reference to the received image and a recommendation of the presentation type for the item included in the received image, for publication by a web server of a publication system.

Growing community of inventors

San Jose, CA, United States of America

Wei Di