Visual intent triggering for visual search

US12346370B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Xi Chen · New Taipei, TW
• Houdong Hu · Redmond, US
• Li-Hsin Huang · Sammamish, US
• Jiapei Huang · Seattle, US
• Arun Sacheti · Sammamish, US
• Linjun Yang · Beijing, CN
• Rui Xia · Los Angeles, US
• Kuang-Huei Lee · Bellevue, US
• Meenaz Merchant · Kirkland, US
• Sean Chang Culatana · Seattle, US

Key dates

• Filing date: Jul 16, 2018
• Grant date: Jul 1, 2025
• Expiry date: Jun 30, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2210/12
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Representative embodiments disclose mechanisms to perform visual intent classification or visual intent detection or both on an image. Visual intent classification utilizes a trained machine learning model that classifies subjects in the image according to a classification taxonomy. The visual intent classification can be used as a pre-triggering mechanism to initiate further action in order to substantially save processing time. Example further actions include user scenarios, query formulation, user experience enhancement, and so forth. Visual intent detection utilizes a trained machine learning model to identify subjects in an image, place a bounding box around the image, and classify the subject according to the taxonomy. The trained machine learning model utilizes multiple feature detectors, multi-layer predictions, multilabel classifiers, and bounding box regression.