Ebay, Incorporated

Benjamin Eliot Klein

Adi Guila Haviv

Bo Li

Krutika Shetty

Stephen Anthony Neola

Maxim Manco

Hyuntae Kim

Mary Adaway Titus

Andrew Daniel Shea

A computer-implemented method includes determining a set of target listings, retrieving a seed image associated with the seed listing, the seed listing is categorized within a first item category, and generating a seed item feature vector for the seed image using a convolutional neural network (CNN) trained with images of items. The method also includes identifying a plurality of feature vectors associated with the first item category, comparing the seed item feature vector to the plurality of feature vectors using a k-nearest neighbors (kNN) algorithm, and generating a set of nearest neighbor listings to the seed listing. The method further includes storing the set of nearest neighbor listings as associated with the seed listing, selecting one or more nearest neighbor listings from the set of nearest neighbors, and presenting the one or more nearest neighbor listings as a recommendation to a user of the online e-commerce system.

System and method for detecting visually similar items

In various embodiments, methods and systems for implementing an integrated image search system are provided. The integrated image search system supports an image search feature of a content application on a mobile device. An image identifier is received to execute an image search operation. The image identifier is received via a native operating system action that is customized to support the image search feature. The native operating system action defines an entry point to the image search feature. The entry points can be based on image identifiers identified from a share image action, a share Uniform Resource Locator (URL) action, a copy share URL action, or a drag and drop action. An image of the image identifier is used to execute the image search operation to identify image search results. An image search results page having one or more images search results is caused to be displayed.

Integrated image system based on image search feature

A media analysis system includes one or more hardware processors, a memory storing synopses associated with catalog books, and a content analysis engine. The content analysis engine generates a media vector for each catalog book based on the associated synopsis by generating a word vector for each word in the synopsis, combining the plurality of word vectors into a mean vector for the catalog book, and storing the mean vector as the media vector associated with the catalog book. The content analysis engine also identifies a target book associated with a seed media vector, determines R nearest neighbors for the target book from the plurality of catalog books based on (1) the seed media vector and (2) the media vectors associated with the plurality of catalog books, clusters the R nearest neighbors into K clusters, and selects catalog books for recommendation to a user based on the K clusters.

System and method for content-based media analysis

Growing community of inventors

Princeton, NJ, United States of America

Benjamin Eliot Klein