首页|'Object-Agnostic Image Representation' in Patent Application Ap- proval Process (USPTO 20240020954)

'Object-Agnostic Image Representation' in Patent Application Ap- proval Process (USPTO 20240020954)

扫码查看
2024 FEB 02 (NewsRx) – By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A patent application by the inventors Harikumar, Midhun (Sunnyvale, CA, US); Kale, Ajinkya Gorakhnath (San Jose, CA, US); Kelkar, Sachin (San Jose, CA, US), filed on July 14, 2022, was made available online on January 18, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background information supplied by the inventors: “The following relates to generating image representations. Images can be encoded into different representations (e.g., multidimensional vectors) for downstream tasks. For example, two image representations can be compared using a distance metric to determine similarity between the images. If two images are determined to be similar, they can be similarly labeled or returned in response to an image search query.

CyborgsEmerging TechnologiesMachine LearningPatent Application

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Feb.2)