Intellectual Property India Publishes Patent Application for Performing Machine Learning Tasks By Processing Images As Videos

MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202617081704 A) filed by Gdm Holding LLC on July 02, 2026, for Performing Machine Learning Tasks By Processing Images As Videos.

Inventors include Miech, Antoine; Sharma, Abhanshu Pctus No; and Kamath, Aishwarya.

The application for the patent was published on August 28, 2026, under issue no. 35/2026.

Abstract: A method performed by one or more data processing apparatus. The method comprises receiving an image item; obtaining a mask for selecting portions of the image item; and generating, from the image item, one or more video item comprising a respective one or more sequences of image frames. Each image frame comprises a respective portion of the image item selected using the mask. For each image sequence, the mask is translated incrementally over the image item to select the respective portions of the image item for successive image frames in the sequence. The method further comprises performing a machine learning task by processing the one or more video items using a machine learning model.

Disclaimer: Curated by HT Syndication.