Visual aspect localization presentation
AssigneeeBay Inc.
InventorsLicheng Yu, Mohammadhadi Kiapour, Ajinkya Gorakhnath Kale, Robinson Piramuthu
Life of this patent
Estimating the term…
Abstract
Various embodiments use a neural network to analyze images for aspects that characterize the images, to present locations of those aspects on the images, and, additionally, to permit a user to interact with those locations on the images. For example, a user may interact with a visual cue over one of those locations to modify, refine, or filter the results of a visual search, performed on a publication corpus, that uses an input image (e.g., one captured using a mobile device) as a search query.
Claims20
A method comprising:
- providing an input image as an input to a machine learning system;
- receiving, from the machine learning system, aspect value data indicating at least one predicted aspect value corresponding to an aspect of an object in the input image, the aspect value data including a set of locations on the input image that caused prediction of the predicted aspect value;
- and
- presenting, based on the aspect value data, a visual cue over the input image at a location of the set of locations.
A non-transitory machine-readable storage medium storing instructions that, when executed by one or more hardware processors, cause the one or more hardware processors to perform operations comprising:
- providing an input image as an input to a machine learning system;
- receiving, from the machine learning system, aspect value data indicating at least one predicted aspect value corresponding to an aspect of an object in the input image, the aspect value data including a set of locations on the input image that caused prediction of the predicted aspect value;
- and
- presenting, based on the aspect value data, a visual cue over the input image at a location of the set of locations.
A system comprising:
- a storage device storing instructions;
- and
- a hardware processor configured by the instructions to perform operations comprising:
- providing an input image as an input to a machine learning system;
- receiving, from the machine learning system, aspect value data indicating at least one predicted aspect value corresponding to an aspect of an object in the input image, the aspect value data including a set of locations on the input image that caused prediction of the predicted aspect value;
- and
- presenting, based on the aspect value data, a visual cue over the input image at a location of the set of locations.
Dependencies are inferred from the claim text.