Adobe, Inc.

Brett Michael Butterfield

Zhe Lin

Jianming Zhang

Baldo Antonio Faieta

Mingyang Ling

Jason Kuen

Xiaohui Shen

Kent Andrew Edmonds

Samarth Gulati

Federico Perazzi

Bernard Kerr

Systems and methods for searching digital content are disclosed. A method includes receiving, from a user, a base search constraint. A search constraint includes search values or criteria. A recall set is generated based on the base search constraint. Recommended search constraints are determined and provided to the user. The recommended search constraints are statistically associated with the base search constraint. The method receives, from the user, a selection of a first search constraint included in the plurality of recommend search constraints. The method generates and provides search results to the user that include a re-ordering of the recall set. The re-ordering is based on a search constraint set that includes both the base search constraint and the selected first search constraint. The re-ordering is further based on a weight associated with the base search constraint and another user-provided weight associated with the first search constraint.

Automatically curated image searching

The present disclosure relates to systems, methods, and non-transitory computer readable media for utilizing a deep neural network-based model to identify similar digital images for query digital images. For example, the disclosed systems utilize a deep neural network-based model to analyze query digital images to generate deep neural network-based representations of the query digital images. In addition, the disclosed systems can generate results of visually-similar digital images for the query digital images based on comparing the deep neural network-based representations with representations of candidate digital images. Furthermore, the disclosed systems can identify visually similar digital images based on user-defined attributes and image masks to emphasize specific attributes or portions of query digital images.

Identifying visually similar digital images utilizing deep learning

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.

Robust training of large-scale object detectors with a noisy dataset

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.

Image searching by employing layered search constraints

Utilizing a deep neural network-based model to identify visually similar digital images based on user-selected visual attributes

Growing community of inventors

San Francisco, CA, United States of America

Brett Michael Butterfield